public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc(refs/users/meissner/heads/dmf008)] Revert patches
@ 2023-02-04 3:03 Michael Meissner
0 siblings, 0 replies; 4+ messages in thread
From: Michael Meissner @ 2023-02-04 3:03 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:fa4da6f15d0ca51e42f481bd9ac8e626f573f364
commit fa4da6f15d0ca51e42f481bd9ac8e626f573f364
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Fri Feb 3 22:03:04 2023 -0500
Revert patches
Diff:
---
gcc/config/rs6000/mma.md | 72 ++++++++++++++++++-------------------
gcc/config/rs6000/rs6000-builtin.cc | 8 ++---
gcc/config/rs6000/rs6000-call.cc | 4 +--
gcc/config/rs6000/rs6000-modes.def | 5 +--
gcc/config/rs6000/rs6000.cc | 58 +++++++++++++++---------------
gcc/config/rs6000/rs6000.h | 2 +-
gcc/tree-core.h | 24 ++++++-------
7 files changed, 85 insertions(+), 88 deletions(-)
diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md
index dc42731e4cf..0233c7b304a 100644
--- a/gcc/config/rs6000/mma.md
+++ b/gcc/config/rs6000/mma.md
@@ -879,22 +879,22 @@
(set_attr "isa" "dm,not_dm,not_dm")])
\f
-;; V8TImode (i.e. __dmr).
-(define_expand "movv8ti"
- [(set (match_operand:V8TI 0 "nonimmediate_operand")
- (match_operand:V8TI 1 "input_operand"))]
+;; TDOmode (i.e. __dmr).
+(define_expand "movtdo"
+ [(set (match_operand:TDO 0 "nonimmediate_operand")
+ (match_operand:TDO 1 "input_operand"))]
"TARGET_DENSE_MATH"
{
- rs6000_emit_move (operands[0], operands[1], V8TImode);
+ rs6000_emit_move (operands[0], operands[1], TDOmode);
DONE;
})
-(define_insn_and_split "*movv8ti"
- [(set (match_operand:V8TI 0 "nonimmediate_operand" "=wa,m,wa,wD,wD,wa")
- (match_operand:V8TI 1 "input_operand" "m,wa,wa,wa,wD,wD"))]
+(define_insn_and_split "*movtdo"
+ [(set (match_operand:TDO 0 "nonimmediate_operand" "=wa,m,wa,wD,wD,wa")
+ (match_operand:TDO 1 "input_operand" "m,wa,wa,wa,wD,wD"))]
"TARGET_DENSE_MATH
- && (gpc_reg_operand (operands[0], V8TImode)
- || gpc_reg_operand (operands[1], V8TImode))"
+ && (gpc_reg_operand (operands[0], TDOmode)
+ || gpc_reg_operand (operands[1], TDOmode))"
"@
#
#
@@ -903,7 +903,7 @@
dmmr %0,%1
#"
"&& reload_completed
- && (!dmr_operand (operands[0], V8TImode) || !dmr_operand (operands[1], V8TImode))"
+ && (!dmr_operand (operands[0], TDOmode) || !dmr_operand (operands[1], TDOmode))"
[(const_int 0)]
{
rtx op0 = operands[0];
@@ -918,8 +918,8 @@
{
rtx op1_upper = gen_rtx_REG (XOmode, regno1);
rtx op1_lower = gen_rtx_REG (XOmode, regno1 + 4);
- emit_insn (gen_movv8ti_insert512_upper (op0, op1_upper));
- emit_insn (gen_movv8ti_insert512_lower (op0, op0, op1_lower));
+ emit_insn (gen_movtdo_insert512_upper (op0, op1_upper));
+ emit_insn (gen_movtdo_insert512_lower (op0, op0, op1_lower));
DONE;
}
@@ -927,8 +927,8 @@
{
rtx op0_upper = gen_rtx_REG (XOmode, regno0);
rtx op0_lower = gen_rtx_REG (XOmode, regno0 + 4);
- emit_insn (gen_movv8ti_extract512 (op0_upper, op1, const0_rtx));
- emit_insn (gen_movv8ti_extract512 (op0_lower, op1, const1_rtx));
+ emit_insn (gen_movtdo_extract512 (op0_upper, op1, const0_rtx));
+ emit_insn (gen_movtdo_extract512 (op0_lower, op1, const1_rtx));
DONE;
}
}
@@ -942,28 +942,28 @@
;; Move from VSX registers to DMR registers via two insert 512 bit
;; instructions.
-(define_insn "movv8ti_insert512_upper"
- [(set (match_operand:V8TI 0 "dmr_operand" "=wD")
- (unspec:V8TI [(match_operand:XO 1 "vsx_register_operand" "wa")]
- UNSPEC_DM_INSERT512_UPPER))]
+(define_insn "movtdo_insert512_upper"
+ [(set (match_operand:TDO 0 "dmr_operand" "=wD")
+ (unspec:TDO [(match_operand:XO 1 "vsx_register_operand" "wa")]
+ UNSPEC_DM_INSERT512_UPPER))]
"TARGET_DENSE_MATH"
"dmxxinstdmr512 %0,%1,%Y1,0"
[(set_attr "type" "mma")])
-(define_insn "movv8ti_insert512_lower"
- [(set (match_operand:V8TI 0 "dmr_operand" "=wD")
- (unspec:V8TI [(match_operand:V8TI 1 "dmr_operand" "0")
- (match_operand:XO 2 "vsx_register_operand" "wa")]
- UNSPEC_DM_INSERT512_LOWER))]
+(define_insn "movtdo_insert512_lower"
+ [(set (match_operand:TDO 0 "dmr_operand" "=wD")
+ (unspec:TDO [(match_operand:TDO 1 "dmr_operand" "0")
+ (match_operand:XO 2 "vsx_register_operand" "wa")]
+ UNSPEC_DM_INSERT512_LOWER))]
"TARGET_DENSE_MATH"
"dmxxinstdmr512 %0,%2,%Y2,1"
[(set_attr "type" "mma")])
;; Move from DMR registers to VSX registers via two extract 512 bit
;; instructions.
-(define_insn "movv8ti_extract512"
+(define_insn "movtdo_extract512"
[(set (match_operand:XO 0 "vsx_register_operand" "=wa")
- (unspec:XO [(match_operand:V8TI 1 "dmr_operand" "wD")
+ (unspec:XO [(match_operand:TDO 1 "dmr_operand" "wD")
(match_operand 2 "const_0_to_1_operand" "n")]
UNSPEC_DM_EXTRACT512))]
"TARGET_DENSE_MATH"
@@ -972,9 +972,9 @@
;; Reload DMR registers from memory
(define_insn_and_split "reload_dmr_from_memory"
- [(set (match_operand:V8TI 0 "dmr_operand" "=wD")
- (unspec:V8TI [(match_operand:V8TI 1 "memory_operand" "m")]
- UNSPEC_DMR_RELOAD_FROM_MEMORY))
+ [(set (match_operand:TDO 0 "dmr_operand" "=wD")
+ (unspec:TDO [(match_operand:TDO 1 "memory_operand" "m")]
+ UNSPEC_DMR_RELOAD_FROM_MEMORY))
(clobber (match_operand:XO 2 "vsx_register_operand" "=wa"))]
"TARGET_DENSE_MATH"
"#"
@@ -988,10 +988,10 @@
rtx mem_lower = adjust_address (src, XOmode, BYTES_BIG_ENDIAN ? 32 : 0);
emit_move_insn (tmp, mem_upper);
- emit_insn (gen_movv8ti_insert512_upper (dest, tmp));
+ emit_insn (gen_movtdo_insert512_upper (dest, tmp));
emit_move_insn (tmp, mem_lower);
- emit_insn (gen_movv8ti_insert512_lower (dest, dest, tmp));
+ emit_insn (gen_movtdo_insert512_lower (dest, dest, tmp));
DONE;
}
[(set_attr "length" "16")
@@ -1000,9 +1000,9 @@
;; Reload dense math registers to memory
(define_insn_and_split "reload_dmr_to_memory"
- [(set (match_operand:V8TI 0 "memory_operand" "=m")
- (unspec:V8TI [(match_operand:V8TI 1 "dmr_operand" "wD")]
- UNSPEC_DMR_RELOAD_TO_MEMORY))
+ [(set (match_operand:TDO 0 "memory_operand" "=m")
+ (unspec:TDO [(match_operand:TDO 1 "dmr_operand" "wD")]
+ UNSPEC_DMR_RELOAD_TO_MEMORY))
(clobber (match_operand:XO 2 "vsx_register_operand" "=wa"))]
"TARGET_DENSE_MATH"
"#"
@@ -1015,10 +1015,10 @@
rtx mem_upper = adjust_address (dest, XOmode, BYTES_BIG_ENDIAN ? 0 : 32);
rtx mem_lower = adjust_address (dest, XOmode, BYTES_BIG_ENDIAN ? 32 : 0);
- emit_insn (gen_movv8ti_extract512 (tmp, src, const0_rtx));
+ emit_insn (gen_movtdo_extract512 (tmp, src, const0_rtx));
emit_move_insn (mem_upper, tmp);
- emit_insn (gen_movv8ti_extract512 (tmp, src, const1_rtx));
+ emit_insn (gen_movtdo_extract512 (tmp, src, const1_rtx));
emit_move_insn (mem_lower, tmp);
DONE;
}
diff --git a/gcc/config/rs6000/rs6000-builtin.cc b/gcc/config/rs6000/rs6000-builtin.cc
index 79f0312b625..b9b0b2d52d0 100644
--- a/gcc/config/rs6000/rs6000-builtin.cc
+++ b/gcc/config/rs6000/rs6000-builtin.cc
@@ -801,10 +801,10 @@ rs6000_init_builtins (void)
ptr_vector_quad_type_node = build_pointer_type (t);
dmr_type_node = make_node (OPAQUE_TYPE);
- SET_TYPE_MODE (dmr_type_node, V8TImode);
- TYPE_SIZE (dmr_type_node) = bitsize_int (GET_MODE_BITSIZE (V8TImode));
- TYPE_PRECISION (dmr_type_node) = GET_MODE_BITSIZE (V8TImode);
- TYPE_SIZE_UNIT (dmr_type_node) = size_int (GET_MODE_SIZE (V8TImode));
+ SET_TYPE_MODE (dmr_type_node, TDOmode);
+ TYPE_SIZE (dmr_type_node) = bitsize_int (GET_MODE_BITSIZE (TDOmode));
+ TYPE_PRECISION (dmr_type_node) = GET_MODE_BITSIZE (TDOmode);
+ TYPE_SIZE_UNIT (dmr_type_node) = size_int (GET_MODE_SIZE (TDOmode));
SET_TYPE_ALIGN (dmr_type_node, 512);
TYPE_USER_ALIGN (dmr_type_node) = 0;
lang_hooks.types.register_builtin_type (dmr_type_node, "__dmr");
diff --git a/gcc/config/rs6000/rs6000-call.cc b/gcc/config/rs6000/rs6000-call.cc
index f109c16bbe0..dcf5b470766 100644
--- a/gcc/config/rs6000/rs6000-call.cc
+++ b/gcc/config/rs6000/rs6000-call.cc
@@ -438,7 +438,7 @@ rs6000_return_in_memory (const_tree type, const_tree fntype ATTRIBUTE_UNUSED)
&& !cfun->machine->mma_return_type_error
&& TREE_TYPE (cfun->decl) == fntype
&& (TYPE_MODE (type) == OOmode || TYPE_MODE (type) == XOmode
- || TYPE_MODE (type) == V8TImode))
+ || TYPE_MODE (type) == TDOmode))
{
/* Record we have now handled function CFUN, so the next time we
are called, we do not re-report the same error. */
@@ -1642,7 +1642,7 @@ rs6000_function_arg (cumulative_args_t cum_v, const function_arg_info &arg)
return NULL_RTX;
}
- if (mode == V8TImode)
+ if (mode == TDOmode)
{
if (TYPE_CANONICAL (type) != NULL_TREE)
type = TYPE_CANONICAL (type);
diff --git a/gcc/config/rs6000/rs6000-modes.def b/gcc/config/rs6000/rs6000-modes.def
index a0ae087f4f7..d36bde9d2a0 100644
--- a/gcc/config/rs6000/rs6000-modes.def
+++ b/gcc/config/rs6000/rs6000-modes.def
@@ -88,8 +88,5 @@ OPAQUE_MODE (OO, 32);
OPAQUE_MODE (XO, 64);
/* Modes used by __dmr. */
-/* OPAQUE_MODE (TDO, 128); */
-VECTOR_MODE (INT, TI, 8); /* V8TI */
-
-
+OPAQUE_MODE (TDO, 128);
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index 2e0dfea5c16..58ee643260f 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -1843,7 +1843,7 @@ rs6000_hard_regno_nregs_internal (int regno, machine_mode mode)
if (FP_REGNO_P (regno))
reg_size = (VECTOR_MEM_VSX_P (mode)
|| VECTOR_ALIGNMENT_P (mode)
- || mode == V8TImode
+ || mode == TDOmode
? UNITS_PER_VSX_WORD
: UNITS_PER_FP_WORD);
@@ -1904,7 +1904,7 @@ rs6000_hard_regno_mode_ok_uncached (int regno, machine_mode mode)
/* Dense math register modes need DMR registers or VSX registers divisible by
2. We need to make sure we don't cross between the boundary of FPRs and
traditional Altiviec registers. */
- if (mode == V8TImode)
+ if (mode == TDOmode)
{
if (!TARGET_DENSE_MATH)
return 0;
@@ -1921,7 +1921,7 @@ rs6000_hard_regno_mode_ok_uncached (int regno, machine_mode mode)
return 0;
}
- /* No other types other than XOmode or V8TImode can go in DMRs. */
+ /* No other types other than XOmode or TDOmode can go in DMRs. */
if (DMR_REGNO_P (regno))
return 0;
@@ -2030,7 +2030,7 @@ rs6000_hard_regno_mode_ok (unsigned int regno, machine_mode mode)
57744).
Similarly, don't allow OOmode (vector pair), XOmode (vector quad), or
- V8TImode (dmr register) to pair with anything else. Vector pairs are
+ TDOmode (dmr register) to pair with anything else. Vector pairs are
restricted to even/odd VSX registers. Without dense math, vector quads are
limited to FPR registers divisible by 4. With dense math, vector quads are
limited to even VSX registers or DMR registers.
@@ -2042,8 +2042,8 @@ static bool
rs6000_modes_tieable_p (machine_mode mode1, machine_mode mode2)
{
if (mode1 == PTImode || mode1 == OOmode || mode1 == XOmode
- || mode1 == V8TImode || mode2 == PTImode || mode2 == OOmode
- || mode2 == XOmode || mode2 == V8TImode)
+ || mode1 == TDOmode || mode2 == PTImode || mode2 == OOmode
+ || mode2 == XOmode || mode2 == TDOmode)
return mode1 == mode2;
if (ALTIVEC_OR_VSX_VECTOR_MODE (mode1))
@@ -2334,7 +2334,7 @@ rs6000_debug_reg_global (void)
V4DFmode,
OOmode,
XOmode,
- V8TImode,
+ TDOmode,
CCmode,
CCUNSmode,
CCEQmode,
@@ -2700,7 +2700,7 @@ rs6000_setup_reg_addr_masks (void)
/* Special case DMR registers. */
if (rc == RELOAD_REG_DMR)
{
- if (TARGET_DENSE_MATH && (m2 == XOmode || m2 == V8TImode))
+ if (TARGET_DENSE_MATH && (m2 == XOmode || m2 == TDOmode))
{
addr_mask = RELOAD_REG_VALID;
reg_addr[m].addr_mask[rc] = addr_mask;
@@ -2810,7 +2810,7 @@ rs6000_setup_reg_addr_masks (void)
since it will be broken into two vector moves. Vector quads and
1,024 bit DMR values can only do offset loads. */
else if ((addr_mask != 0) && TARGET_MMA
- && (m2 == OOmode || m2 == XOmode || m2 == V8TImode))
+ && (m2 == OOmode || m2 == XOmode || m2 == TDOmode))
{
addr_mask |= RELOAD_REG_OFFSET;
if (rc == RELOAD_REG_FPR || rc == RELOAD_REG_VMX)
@@ -3041,9 +3041,9 @@ rs6000_init_hard_regno_mode_ok (bool global_init_p)
/* Add support for 1,024 bit DMR registers. */
if (TARGET_DENSE_MATH)
{
- rs6000_vector_unit[V8TImode] = VECTOR_NONE;
- rs6000_vector_mem[V8TImode] = VECTOR_VSX;
- rs6000_vector_align[V8TImode] = 512;
+ rs6000_vector_unit[TDOmode] = VECTOR_NONE;
+ rs6000_vector_mem[TDOmode] = VECTOR_VSX;
+ rs6000_vector_align[TDOmode] = 512;
}
/* Register class constraints for the constraints that depend on compile
@@ -3261,8 +3261,8 @@ rs6000_init_hard_regno_mode_ok (bool global_init_p)
if (TARGET_DENSE_MATH)
{
- reg_addr[V8TImode].reload_load = CODE_FOR_reload_dmr_from_memory;
- reg_addr[V8TImode].reload_store = CODE_FOR_reload_dmr_to_memory;
+ reg_addr[TDOmode].reload_load = CODE_FOR_reload_dmr_from_memory;
+ reg_addr[TDOmode].reload_store = CODE_FOR_reload_dmr_to_memory;
}
/* Precalculate HARD_REGNO_NREGS. */
@@ -8768,7 +8768,7 @@ reg_offset_addressing_ok_p (machine_mode mode)
case E_XOmode:
return TARGET_MMA;
- case E_V8TImode:
+ case E_TDOmode:
return TARGET_DENSE_MATH;
case E_SDmode:
@@ -11052,7 +11052,7 @@ rs6000_emit_move (rtx dest, rtx source, machine_mode mode)
(mode == OOmode) ? "__vector_pair" : "__vector_quad");
break;
- case E_V8TImode:
+ case E_TDOmode:
if (CONST_INT_P (operands[1]))
error ("%qs is an opaque type, and you cannot set it to constants",
"__dmr");
@@ -12512,7 +12512,7 @@ rs6000_secondary_reload_simple_move (enum rs6000_reg_type to_type,
/* We can transfer between VSX registers and DMR registers without needing
extra registers. */
- if (TARGET_DENSE_MATH && (mode == XOmode || mode == V8TImode)
+ if (TARGET_DENSE_MATH && (mode == XOmode || mode == TDOmode)
&& ((to_type == DMR_REG_TYPE && from_type == VSX_REG_TYPE)
|| (to_type == VSX_REG_TYPE && from_type == DMR_REG_TYPE)))
return true;
@@ -13313,7 +13313,7 @@ rs6000_preferred_reload_class (rtx x, enum reg_class rclass)
if (mode == XOmode)
return TARGET_DENSE_MATH ? VSX_REGS : FLOAT_REGS;
- if (mode == V8TImode)
+ if (mode == TDOmode)
return VSX_REGS;
if (GET_MODE_CLASS (mode) == MODE_INT)
@@ -13440,7 +13440,7 @@ rs6000_secondary_reload_class (enum reg_class rclass, machine_mode mode,
regno = -1;
/* Dense math registers don't have loads or stores. We have to go through
- the VSX registers to load XOmode (vector quad) and V8TImode (dmr 1024
+ the VSX registers to load XOmode (vector quad) and TDOmode (dmr 1024
bit). */
if (TARGET_DENSE_MATH && rclass == DM_REGS)
return VSX_REGS;
@@ -22649,8 +22649,8 @@ rs6000_dmr_register_move_cost (machine_mode mode, reg_class_t rclass)
if (mode == XOmode)
return reg_move_base;
- /* __dmr (i.e. V8TImode) is transferred in 2 instructions. */
- else if (mode == V8TImode)
+ /* __dmr (i.e. TDOmode) is transferred in 2 instructions. */
+ else if (mode == TDOmode)
return reg_move_base * 2;
else
@@ -27350,7 +27350,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we have a vector quad register for MMA or DMR register for dense math,
and this is a load or store, see if we can use vector paired
load/stores. */
- if ((mode == XOmode || mode == V8TImode) && TARGET_MMA
+ if ((mode == XOmode || mode == TDOmode) && TARGET_MMA
&& (MEM_P (dst) || MEM_P (src)))
{
reg_mode = OOmode;
@@ -27358,7 +27358,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
}
/* If we have a vector pair/quad mode, split it into two/four separate
vectors. */
- else if (mode == OOmode || mode == XOmode || mode == V8TImode)
+ else if (mode == OOmode || mode == XOmode || mode == TDOmode)
reg_mode = V1TImode;
else if (FP_REGNO_P (reg))
reg_mode = DECIMAL_FLOAT_MODE_P (mode) ? DDmode :
@@ -27410,7 +27410,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
the last register gets the first memory location. We also need to be
careful of using the right register numbers if we are splitting XO to
OO. */
- if (mode == OOmode || mode == XOmode || mode == V8TImode)
+ if (mode == OOmode || mode == XOmode || mode == TDOmode)
{
nregs = hard_regno_nregs (reg, mode);
int reg_mode_nregs = hard_regno_nregs (reg, reg_mode);
@@ -27547,7 +27547,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
overlap. */
int i;
/* XO/OO are opaque so cannot use subregs. */
- if (mode == OOmode || mode == XOmode || mode == V8TImode)
+ if (mode == OOmode || mode == XOmode || mode == TDOmode)
{
for (i = nregs - 1; i >= 0; i--)
{
@@ -27721,7 +27721,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
continue;
/* XO/OO are opaque so cannot use subregs. */
- if (mode == OOmode || mode == XOmode || mode == V8TImode)
+ if (mode == OOmode || mode == XOmode || mode == TDOmode)
{
rtx dst_i = gen_rtx_REG (reg_mode, REGNO (dst) + j);
rtx src_i = gen_rtx_REG (reg_mode, REGNO (src) + j);
@@ -28701,7 +28701,7 @@ rs6000_invalid_conversion (const_tree fromtype, const_tree totype)
if (frommode != tomode)
{
- /* Do not allow conversions to/from XOmode, OOmode, and V8TImode
+ /* Do not allow conversions to/from XOmode, OOmode, and TDOmode
types. */
if (frommode == XOmode)
return N_("invalid conversion from type %<__vector_quad%>");
@@ -28711,9 +28711,9 @@ rs6000_invalid_conversion (const_tree fromtype, const_tree totype)
return N_("invalid conversion from type %<__vector_pair%>");
if (tomode == OOmode)
return N_("invalid conversion to type %<__vector_pair%>");
- if (frommode == V8TImode)
+ if (frommode == TDOmode)
return N_("invalid conversion from type %<__dmr%>");
- if (tomode == V8TImode)
+ if (tomode == TDOmode)
return N_("invalid conversion to type %<__dmr%>");
}
diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index a8916a979f8..823de897603 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -1007,7 +1007,7 @@ enum data_align { align_abi, align_opt, align_both };
vectors in terms of loads and stores. */
#define VECTOR_ALIGNMENT_P(MODE) \
(FLOAT128_VECTOR_P (MODE) || (MODE) == OOmode || (MODE) == XOmode \
- || (MODE) == V8TImode)
+ || (MODE) == TDOmode)
#define ALTIVEC_VECTOR_MODE(MODE) \
((MODE) == V16QImode \
diff --git a/gcc/tree-core.h b/gcc/tree-core.h
index acd8deea34e..e5513208511 100644
--- a/gcc/tree-core.h
+++ b/gcc/tree-core.h
@@ -1686,18 +1686,8 @@ struct GTY(()) tree_type_common {
tree attributes;
unsigned int uid;
- unsigned int precision : 10;
- unsigned no_force_blk_flag : 1;
- unsigned needs_constructing_flag : 1;
- unsigned transparent_aggr_flag : 1;
- unsigned restrict_flag : 1;
- unsigned contains_placeholder_bits : 2;
-
+ unsigned int precision : 16;
ENUM_BITFIELD(machine_mode) mode : 8;
-
- /* TYPE_STRING_FLAG for INTEGER_TYPE and ARRAY_TYPE.
- TYPE_CXX_ODR_P for RECORD_TYPE and UNION_TYPE. */
- unsigned string_flag : 1;
unsigned lang_flag_0 : 1;
unsigned lang_flag_1 : 1;
unsigned lang_flag_2 : 1;
@@ -1713,12 +1703,22 @@ struct GTY(()) tree_type_common {
so we need to store the value 32 (not 31, as we need the zero
as well), hence six bits. */
unsigned align : 6;
+ /* TYPE_STRING_FLAG for INTEGER_TYPE and ARRAY_TYPE.
+ TYPE_CXX_ODR_P for RECORD_TYPE and UNION_TYPE. */
+ unsigned string_flag : 1;
+ unsigned no_force_blk_flag : 1;
+
unsigned warn_if_not_align : 6;
+ unsigned needs_constructing_flag : 1;
+ unsigned transparent_aggr_flag : 1;
+
+ unsigned contains_placeholder_bits : 2;
+ unsigned restrict_flag : 1;
unsigned typeless_storage : 1;
unsigned empty_flag : 1;
unsigned indivisible_p : 1;
unsigned no_named_args_stdarg_p : 1;
- unsigned spare : 15;
+ unsigned spare : 9;
alias_set_type alias_set;
tree pointer_to;
^ permalink raw reply [flat|nested] 4+ messages in thread
* [gcc(refs/users/meissner/heads/dmf008)] Revert patches
@ 2023-02-03 19:25 Michael Meissner
0 siblings, 0 replies; 4+ messages in thread
From: Michael Meissner @ 2023-02-03 19:25 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:e625820b066fc5631c38bf0b83e5e905496e2931
commit e625820b066fc5631c38bf0b83e5e905496e2931
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Fri Feb 3 14:25:11 2023 -0500
Revert patches
Diff:
---
gcc/config/rs6000/rs6000-builtin.cc | 17 ----
gcc/config/rs6000/rs6000-builtins.def | 11 ---
gcc/config/rs6000/rs6000-gen-builtins.cc | 35 ++------
gcc/config/rs6000/rs6000-string.cc | 1 -
gcc/config/rs6000/rs6000.md | 60 --------------
gcc/config/rs6000/vsx.md | 122 +++++-----------------------
gcc/doc/extend.texi | 24 ------
gcc/testsuite/gcc.target/powerpc/lxvrl.c | 32 --------
gcc/testsuite/gcc.target/powerpc/subfus-1.c | 32 --------
gcc/testsuite/gcc.target/powerpc/subfus-2.c | 32 --------
gcc/testsuite/lib/target-supports.exp | 16 +---
11 files changed, 28 insertions(+), 354 deletions(-)
diff --git a/gcc/config/rs6000/rs6000-builtin.cc b/gcc/config/rs6000/rs6000-builtin.cc
index b9b0b2d52d0..d971cf90e51 100644
--- a/gcc/config/rs6000/rs6000-builtin.cc
+++ b/gcc/config/rs6000/rs6000-builtin.cc
@@ -139,17 +139,6 @@ rs6000_invalid_builtin (enum rs6000_gen_builtins fncode)
case ENB_MMA:
error ("%qs requires the %qs option", name, "-mmma");
break;
- case ENB_FUTURE:
- error ("%qs requires the %qs option", name, "-mcpu=future");
- break;
- case ENB_FUTURE_64:
- error ("%qs requires the %qs option and either the %qs or %qs option",
- name, "-mcpu=future", "-m64", "-mpowerpc64");
- break;
- case ENB_DM:
- error ("%qs requires the %qs or %qs options", name, "-mcpu=future",
- "-mdense-math");
- break;
default:
case ENB_ALWAYS:
gcc_unreachable ();
@@ -205,12 +194,6 @@ rs6000_builtin_is_supported (enum rs6000_gen_builtins fncode)
return TARGET_HTM;
case ENB_MMA:
return TARGET_MMA;
- case ENB_FUTURE:
- return TARGET_FUTURE;
- case ENB_FUTURE_64:
- return TARGET_FUTURE && TARGET_POWERPC64;
- case ENB_DM:
- return TARGET_DENSE_MATH;
default:
gcc_unreachable ();
}
diff --git a/gcc/config/rs6000/rs6000-builtins.def b/gcc/config/rs6000/rs6000-builtins.def
index 8b73e994558..e0d9f5adc97 100644
--- a/gcc/config/rs6000/rs6000-builtins.def
+++ b/gcc/config/rs6000/rs6000-builtins.def
@@ -139,8 +139,6 @@
; endian Needs special handling for endianness
; ibmld Restrict usage to the case when TFmode is IBM-128
; ibm128 Restrict usage to the case where __ibm128 is supported or if ibmld
-; future Restrict usage to future instructions
-; dm Restrict usage to dense math
;
; Each attribute corresponds to extra processing required when
; the built-in is expanded. All such special processing should
@@ -4110,12 +4108,3 @@
void __builtin_vsx_stxvp (v256, unsigned long, const v256 *);
STXVP nothing {mma,pair}
-
-[future]
- const signed int __builtin_saturate_subtract32 (signed int, signed int);
- SAT_SUBSI sat_subsi3 {}
-
-[future-64]
- const signed long __builtin_saturate_subtract64 (signed long, signed long);
- SAT_SUBDI sat_subdi3 {}
-
diff --git a/gcc/config/rs6000/rs6000-gen-builtins.cc b/gcc/config/rs6000/rs6000-gen-builtins.cc
index daf7fff079e..a2f442ed90d 100644
--- a/gcc/config/rs6000/rs6000-gen-builtins.cc
+++ b/gcc/config/rs6000/rs6000-gen-builtins.cc
@@ -233,9 +233,6 @@ enum bif_stanza
BSTZ_P10,
BSTZ_P10_64,
BSTZ_MMA,
- BSTZ_FUTURE,
- BSTZ_FUTURE_64,
- BSTZ_DM,
NUMBIFSTANZAS
};
@@ -269,10 +266,7 @@ static stanza_entry stanza_map[NUMBIFSTANZAS] =
{ "htm", BSTZ_HTM },
{ "power10", BSTZ_P10 },
{ "power10-64", BSTZ_P10_64 },
- { "mma", BSTZ_MMA },
- { "future", BSTZ_FUTURE },
- { "future-64", BSTZ_FUTURE_64 },
- { "dm", BSTZ_DM },
+ { "mma", BSTZ_MMA }
};
static const char *enable_string[NUMBIFSTANZAS] =
@@ -297,10 +291,7 @@ static const char *enable_string[NUMBIFSTANZAS] =
"ENB_HTM",
"ENB_P10",
"ENB_P10_64",
- "ENB_MMA",
- "ENB_FUTURE",
- "ENB_FUTURE_64",
- "ENB_DM",
+ "ENB_MMA"
};
/* Function modifiers provide special handling for const, pure, and fpmath
@@ -404,8 +395,6 @@ struct attrinfo
bool isendian;
bool isibmld;
bool isibm128;
- bool isfuture;
- bool isdm;
};
/* Fields associated with a function prototype (bif or overload). */
@@ -1488,8 +1477,7 @@ parse_bif_attrs (attrinfo *attrptr)
"ldvec = %d, stvec = %d, reve = %d, pred = %d, htm = %d, "
"htmspr = %d, htmcr = %d, mma = %d, quad = %d, pair = %d, "
"mmaint = %d, no32bit = %d, 32bit = %d, cpu = %d, ldstmask = %d, "
- "lxvrse = %d, lxvrze = %d, endian = %d, ibmdld = %d, ibm128 = %d,",
- "future = %d, dm = %d.\n",
+ "lxvrse = %d, lxvrze = %d, endian = %d, ibmdld = %d, ibm128 = %d.\n",
attrptr->isinit, attrptr->isset, attrptr->isextract,
attrptr->isnosoft, attrptr->isldvec, attrptr->isstvec,
attrptr->isreve, attrptr->ispred, attrptr->ishtm, attrptr->ishtmspr,
@@ -1497,7 +1485,7 @@ parse_bif_attrs (attrinfo *attrptr)
attrptr->ismmaint, attrptr->isno32bit, attrptr->is32bit,
attrptr->iscpu, attrptr->isldstmask, attrptr->islxvrse,
attrptr->islxvrze, attrptr->isendian, attrptr->isibmld,
- attrptr->isibm128, attrptr->isfuture, attrptr->isdm);
+ attrptr->isibm128);
#endif
return PC_OK;
@@ -2269,10 +2257,7 @@ write_decls (void)
fprintf (header_file, " ENB_HTM,\n");
fprintf (header_file, " ENB_P10,\n");
fprintf (header_file, " ENB_P10_64,\n");
- fprintf (header_file, " ENB_MMA,\n");
- fprintf (header_file, " ENB_FUTURE,\n");
- fprintf (header_file, " ENB_FUTURE_64,\n");
- fprintf (header_file, " ENB_DM\n");
+ fprintf (header_file, " ENB_MMA\n");
fprintf (header_file, "};\n\n");
fprintf (header_file, "#define PPC_MAXRESTROPNDS 3\n");
@@ -2316,8 +2301,6 @@ write_decls (void)
fprintf (header_file, "#define bif_endian_bit\t\t(0x00200000)\n");
fprintf (header_file, "#define bif_ibmld_bit\t\t(0x00400000)\n");
fprintf (header_file, "#define bif_ibm128_bit\t\t(0x00800000)\n");
- fprintf (header_file, "#define bif_future_bit\t\t(0x01000000)\n");
- fprintf (header_file, "#define bif_dm_bit\t\t(0x02000000)\n");
fprintf (header_file, "\n");
fprintf (header_file,
"#define bif_is_init(x)\t\t((x).bifattrs & bif_init_bit)\n");
@@ -2367,10 +2350,6 @@ write_decls (void)
"#define bif_is_ibmld(x)\t((x).bifattrs & bif_ibmld_bit)\n");
fprintf (header_file,
"#define bif_is_ibm128(x)\t((x).bifattrs & bif_ibm128_bit)\n");
- fprintf (header_file,
- "#define bif_is_future(x)\t((x).bifattrs & bif_future_bit)\n");
- fprintf (header_file,
- "#define bif_is_dm(x)\t((x).bifattrs & bif_dm_bit)\n");
fprintf (header_file, "\n");
fprintf (header_file,
@@ -2569,10 +2548,6 @@ write_bif_static_init (void)
fprintf (init_file, " | bif_ibmld_bit");
if (bifp->attrs.isibm128)
fprintf (init_file, " | bif_ibm128_bit");
- if (bifp->attrs.isfuture)
- fprintf (init_file, " | bif_future_bit");
- if (bifp->attrs.isdm)
- fprintf (init_file, " | bif_dm_bit");
fprintf (init_file, ",\n");
fprintf (init_file, " /* restr_opnd */\t{%d, %d, %d},\n",
bifp->proto.restr_opnd[0], bifp->proto.restr_opnd[1],
diff --git a/gcc/config/rs6000/rs6000-string.cc b/gcc/config/rs6000/rs6000-string.cc
index 9b2f1b83b22..75e6f8803a5 100644
--- a/gcc/config/rs6000/rs6000-string.cc
+++ b/gcc/config/rs6000/rs6000-string.cc
@@ -2811,7 +2811,6 @@ expand_block_move (rtx operands[], bool might_overlap)
gen_func.mov = gen_vsx_movv2di_64bit;
}
else if (TARGET_BLOCK_OPS_UNALIGNED_VSX
- && TARGET_POWERPC64
&& TARGET_POWER10 && bytes < 16
&& orig_bytes > 16
&& !(bytes == 1 || bytes == 2
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index f9e231c16be..ee7651d9b43 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -15654,66 +15654,6 @@
}
[(set_attr "type" "load")])
\f
-;; Signed saturation.
-
-;; The subfus instruction is defined as: SUBFUS RT,L,RA,RB. The extended
-;; mnemonic that we use (subdus and subwus) has the arguments RA and RB
-;; reversed (so it becomes a subtract instead of subtract from).
-
-(define_insn "sat_sub<mode>3"
- [(set (match_operand:GPR 0 "gpc_reg_operand" "=r")
- (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r")
- (match_operand:GPR 2 "gpc_reg_operand" "r")))]
- "TARGET_FUTURE"
- "sub<wd>us %0,%1,%2"
- [(set_attr "type" "add")])
-
-(define_insn_and_split "*sat_sub<mode>3_dot"
- [(set (match_operand:CC 3 "cc_reg_operand" "=x,?y")
- (compare:CC (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
- (match_operand:GPR 2 "gpc_reg_operand" "r,r"))
- (const_int 0)))
- (clobber (match_scratch:GPR 0 "=r,r"))]
- "TARGET_FUTURE"
- "@
- sub<wd>us. %0,%1,%2
- #"
- "&& reload_completed && cc_reg_not_cr0_operand (operands[3], CCmode)"
- [(set (match_dup 0)
- (ss_minus:GPR (match_dup 1)
- (match_dup 2)))
- (set (match_dup 3)
- (compare:CC (match_dup 0)
- (const_int 0)))]
- ""
- [(set_attr "type" "add")
- (set_attr "dot" "yes")
- (set_attr "length" "4,8")])
-
-(define_insn_and_split "*sat_sub<mode>3_dot2"
- [(set (match_operand:CC 3 "cc_reg_operand" "=x,?y")
- (compare:CC (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
- (match_operand:GPR 2 "gpc_reg_operand" "r,r"))
- (const_int 0)))
- (set (match_operand:GPR 0 "gpc_reg_operand" "=r,r")
- (ss_minus:GPR (match_dup 1)
- (match_dup 2)))]
- "TARGET_FUTURE"
- "@
- sub<wd>us. %0,%1,%2
- #"
- "&& reload_completed && cc_reg_not_cr0_operand (operands[3], CCmode)"
- [(set (match_dup 0)
- (ss_minus:GPR (match_dup 1)
- (match_dup 2)))
- (set (match_dup 3)
- (compare:CC (match_dup 0)
- (const_int 0)))]
- ""
- [(set_attr "type" "add")
- (set_attr "dot" "yes")
- (set_attr "length" "4,8")])
-\f
(include "sync.md")
(include "vector.md")
diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index 1ab8dc373c0..0865608f94a 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -5582,32 +5582,20 @@
DONE;
})
-;; Load VSX Vector with Length. If we have lxvrl, we don't have to do an
-;; explicit shift left into a pseudo.
+;; Load VSX Vector with Length
(define_expand "lxvl"
- [(use (match_operand:V16QI 0 "vsx_register_operand"))
- (use (match_operand:DI 1 "gpc_reg_operand"))
- (use (match_operand:DI 2 "gpc_reg_operand"))]
+ [(set (match_dup 3)
+ (ashift:DI (match_operand:DI 2 "register_operand")
+ (const_int 56)))
+ (set (match_operand:V16QI 0 "vsx_register_operand")
+ (unspec:V16QI
+ [(match_operand:DI 1 "gpc_reg_operand")
+ (mem:V16QI (match_dup 1))
+ (match_dup 3)]
+ UNSPEC_LXVL))]
"TARGET_P9_VECTOR && TARGET_64BIT"
{
- rtx shift_len = gen_rtx_ASHIFT (DImode, operands[2], GEN_INT (56));
- rtx len;
-
- if (TARGET_FUTURE)
- len = shift_len;
- else
- {
- len = gen_reg_rtx (DImode);
- emit_insn (gen_rtx_SET (len, shift_len));
- }
-
- rtx dest = operands[0];
- rtx addr = operands[1];
- rtx mem = gen_rtx_MEM (V16QImode, addr);
- rtvec rv = gen_rtvec (3, addr, mem, len);
- rtx lxvl = gen_rtx_UNSPEC (V16QImode, rv, UNSPEC_LXVL);
- emit_insn (gen_rtx_SET (dest, lxvl));
- DONE;
+ operands[3] = gen_reg_rtx (DImode);
})
(define_insn "*lxvl"
@@ -5631,34 +5619,6 @@
"lxvll %x0,%1,%2"
[(set_attr "type" "vecload")])
-;; For lxvrl and lxvrll, use the combiner to eliminate the shift. The
-;; define_expand for lxvl will already incorporate the shift in generating the
-;; insn. The lxvll buitl-in function required the user to have already done
-;; the shift. Defining lxvrll this way, will optimize cases where the user has
-;; done the shift immediately before the built-in.
-(define_insn "*lxvrl"
- [(set (match_operand:V16QI 0 "vsx_register_operand" "=wa")
- (unspec:V16QI
- [(match_operand:DI 1 "gpc_reg_operand" "b")
- (mem:V16QI (match_dup 1))
- (ashift:DI (match_operand:DI 2 "register_operand" "r")
- (const_int 56))]
- UNSPEC_LXVL))]
- "TARGET_FUTURE && TARGET_64BIT"
- "lxvrl %x0,%1,%2"
- [(set_attr "type" "vecload")])
-
-(define_insn "*lxvrll"
- [(set (match_operand:V16QI 0 "vsx_register_operand" "=wa")
- (unspec:V16QI [(match_operand:DI 1 "gpc_reg_operand" "b")
- (mem:V16QI (match_dup 1))
- (ashift:DI (match_operand:DI 2 "register_operand" "r")
- (const_int 56))]
- UNSPEC_LXVLL))]
- "TARGET_FUTURE"
- "lxvrll %x0,%1,%2"
- [(set_attr "type" "vecload")])
-
;; Expand for builtin xl_len_r
(define_expand "xl_len_r"
[(match_operand:V16QI 0 "vsx_register_operand")
@@ -5690,29 +5650,18 @@
;; Store VSX Vector with Length
(define_expand "stxvl"
- [(use (match_operand:V16QI 0 "vsx_register_operand"))
- (use (match_operand:DI 1 "gpc_reg_operand"))
- (use (match_operand:DI 2 "gpc_reg_operand"))]
+ [(set (match_dup 3)
+ (ashift:DI (match_operand:DI 2 "register_operand")
+ (const_int 56)))
+ (set (mem:V16QI (match_operand:DI 1 "gpc_reg_operand"))
+ (unspec:V16QI
+ [(match_operand:V16QI 0 "vsx_register_operand")
+ (mem:V16QI (match_dup 1))
+ (match_dup 3)]
+ UNSPEC_STXVL))]
"TARGET_P9_VECTOR && TARGET_64BIT"
{
- rtx shift_len = gen_rtx_ASHIFT (DImode, operands[2], GEN_INT (56));
- rtx len;
-
- if (TARGET_FUTURE)
- len = shift_len;
- else
- {
- len = gen_reg_rtx (DImode);
- emit_insn (gen_rtx_SET (len, shift_len));
- }
-
- rtx src = operands[0];
- rtx addr = operands[1];
- rtx mem = gen_rtx_MEM (V16QImode, addr);
- rtvec rv = gen_rtvec (3, src, mem, len);
- rtx stxvl = gen_rtx_UNSPEC (V16QImode, rv, UNSPEC_STXVL);
- emit_insn (gen_rtx_SET (mem, stxvl));
- DONE;
+ operands[3] = gen_reg_rtx (DImode);
})
;; Define optab for vector access with length vectorization exploitation.
@@ -5756,35 +5705,6 @@
"stxvl %x0,%1,%2"
[(set_attr "type" "vecstore")])
-;; For stxvrl and stxvrll, use the combiner to eliminate the shift. The
-;; define_expand for stxvl will already incorporate the shift in generating the
-;; insn. The stxvll buitl-in function required the user to have already done
-;; the shift. Defining stxvrll this way, will optimize cases where the user
-;; has done the shift immediately before the built-in.
-
-(define_insn "*stxvrl"
- [(set (mem:V16QI (match_operand:DI 1 "gpc_reg_operand" "b"))
- (unspec:V16QI
- [(match_operand:V16QI 0 "vsx_register_operand" "wa")
- (mem:V16QI (match_dup 1))
- (ashift:DI (match_operand:DI 2 "register_operand" "r")
- (const_int 56))]
- UNSPEC_STXVL))]
- "TARGET_FUTURE && TARGET_64BIT"
- "stxvrl %x0,%1,%2"
- [(set_attr "type" "vecstore")])
-
-(define_insn "*stxvrll"
- [(set (mem:V16QI (match_operand:DI 1 "gpc_reg_operand" "b"))
- (unspec:V16QI [(match_operand:V16QI 0 "vsx_register_operand" "wa")
- (mem:V16QI (match_dup 1))
- (ashift:DI (match_operand:DI 2 "register_operand" "r")
- (const_int 56))]
- UNSPEC_STXVLL))]
- "TARGET_FUTURE"
- "stxvrll %x0,%1,%2"
- [(set_attr "type" "vecstore")])
-
;; Expand for builtin xst_len_r
(define_expand "xst_len_r"
[(match_operand:V16QI 0 "vsx_register_operand" "=wa")
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index a6d25b5b618..5a026c4b48c 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -17839,7 +17839,6 @@ Disable global interrupt.
* Basic PowerPC Built-in Functions Available on ISA 2.07::
* Basic PowerPC Built-in Functions Available on ISA 3.0::
* Basic PowerPC Built-in Functions Available on ISA 3.1::
-* Basic Built-in Functions that may be available on future PowerPCs::
@end menu
This section describes PowerPC built-in functions that do not require
@@ -18497,29 +18496,6 @@ ISA 3.1 @code{stxvrbx}, @code{stxvrhx}, @code{stxvrwx}, and @code{stxvrdx}
instructions.
@findex vec_xst_trunc
-@node Basic Built-in Functions that may be available on future PowerPCs
-@subsubsection Potential future PowerPC Built-in Functions
-
-The built-in functions described in this section may be available on
-future PowerPC processors. At present, these built-ins exist to
-allowing testing of new instructions. There is no guarantee that
-these instructions will actually be implemented.
-
-The following built-in functions are available on Linux 64-bit systems
-that use a potential future instruction set (@option{-mcpu=future}):
-
-@table @code
-@item int __builtin_saturate_subtract32 (int, int)
-Subtract the second operand from the first operand. If the value
-would be less than 0, then the result is 0 instead of the negative
-value of the subtraction.
-
-@item long __builtin_saturate_subtract64 (long, long)
-Subtract the second operand from the first operand. If the value
-would be less than 0, then the result is 0 instead of the negative
-value of the subtraction.
-@end table
-
@node PowerPC AltiVec/VSX Built-in Functions
@subsection PowerPC AltiVec/VSX Built-in Functions
diff --git a/gcc/testsuite/gcc.target/powerpc/lxvrl.c b/gcc/testsuite/gcc.target/powerpc/lxvrl.c
deleted file mode 100644
index 71854c50c91..00000000000
--- a/gcc/testsuite/gcc.target/powerpc/lxvrl.c
+++ /dev/null
@@ -1,32 +0,0 @@
-/* { dg-do compile } */
-/* { dg-require-effective-target powerpc_future_ok } */
-/* { dg-require-effective-target lp64 } */
-/* { dg-options "-mdejagnu-cpu=future -O2" } */
-
-/* Test whether the lxvrl and stxvrl instructions are generated for
- -mcpu=future on memory copy operations. */
-
-#ifndef VSIZE
-#define VSIZE 2
-#endif
-
-#ifndef LSIZE
-#define LSIZE 5
-#endif
-
-struct foo {
- vector unsigned char vc[VSIZE];
- unsigned char leftover[LSIZE];
-};
-
-void memcpy_ptr (struct foo *p, struct foo *q)
-{
- __builtin_memcpy ((void *) p, /* lxvrl and stxvrl. */
- (void *) q,
- (sizeof (vector unsigned char) * VSIZE) + LSIZE);
-}
-
-/* { dg-final { scan-assembler {\mlxvrl\M} } } */
-/* { dg-final { scan-assembler {\mstxvrl\M} } } */
-/* { dg-final { scan-assembler-not {\mlxvl\M} } } */
-/* { dg-final { scan-assembler-not {\mstxvl\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/subfus-1.c b/gcc/testsuite/gcc.target/powerpc/subfus-1.c
deleted file mode 100644
index 535e7f8483d..00000000000
--- a/gcc/testsuite/gcc.target/powerpc/subfus-1.c
+++ /dev/null
@@ -1,32 +0,0 @@
-/* { dg-do compile } */
-/* { dg-require-effective-target powerpc_future_ok } */
-/* { dg-options "-mdejagnu-cpu=future -O2" } */
-
-/* Test whether the saturating subtract built-in generates subwus for 32-bit
- subtracts. */
-
-int do_sat_int (int a, int b)
-{
- return __builtin_saturate_subtract32 (a, b); /* subwus */
-}
-
-int do_sat_int_dot (int a, int b, int *p)
-{
- int r = __builtin_saturate_subtract32 (a, b); /* subwus. */
- if (r == 0)
- *p = 0;
-
- return r;
-}
-
-void do_sat_int_dot2 (int a, int b, int *p, int *q)
-{
- if (__builtin_saturate_subtract32 (a, b)) /* subwus. */
- *p = 0;
-
- *q = a + b;
- return;
-}
-
-/* { dg-final { scan-assembler {\msubwus\M} } } */
-/* { dg-final { scan-assembler-not {\msubf\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/subfus-2.c b/gcc/testsuite/gcc.target/powerpc/subfus-2.c
deleted file mode 100644
index b68e66dd2b0..00000000000
--- a/gcc/testsuite/gcc.target/powerpc/subfus-2.c
+++ /dev/null
@@ -1,32 +0,0 @@
-/* { dg-do compile { target lp64 } } */
-/* { dg-require-effective-target powerpc_future_ok } */
-/* { dg-options "-mdejagnu-cpu=future -O2" } */
-
-/* Test whether the saturating subtract built-in generates subwus for 64-bit
- subtracts. */
-
-long do_sat_long (long a, long b)
-{
- return __builtin_saturate_subtract64 (a, b); /* subwus */
-}
-
-long do_sat_long_dot (long a, long b, long *p)
-{
- long r = __builtin_saturate_subtract64 (a, b); /* subwus. */
- if (r == 0)
- *p = 0;
-
- return r;
-}
-
-void do_sat_long_dot2 (long a, long b, long *p, long *q)
-{
- if (__builtin_saturate_subtract64 (a, b)) /* subwus. */
- *p = 0;
-
- *q = a + b;
- return;
-}
-
-/* { dg-final { scan-assembler {\msubdus\M} } } */
-/* { dg-final { scan-assembler-not {\msubf\M} } } */
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index 47adf407f83..9586ed3ae47 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -6581,8 +6581,8 @@ proc check_effective_target_power10_ok { } {
}
}
-# Return 1 if this is a PowerPC target supporting -mcpu=future which enables
-# the dense math operations.
+# Return 1 if this is a PowerPC target supporting -mcpu=future or -mdense-math
+# which enables the dense math operations.
proc check_effective_target_powerpc_dense_math_ok { } {
return [check_no_compiler_messages_nocache powerpc_dense_math_ok assembly {
__vector_quad vq;
@@ -6600,18 +6600,6 @@ proc check_effective_target_powerpc_dense_math_ok { } {
} "-mcpu=future"]
}
-# Return 1 if this is a PowerPC target supporting -mcpu=future which enables
-# the saturating subtract instruction.
-proc check_effective_target_powerpc_future_ok { } {
- return [check_no_compiler_messages powerpc_future_ok object {
- #ifndef _ARCH_PWR_FUTURE
- #error "not -mcpu=future"
- #else
- int dummy;
- #endif
- } "-mcpu=future"]
-}
-
# Return 1 if this is a PowerPC target supporting -mfloat128 via either
# software emulation on power7/power8 systems or hardware support on power9.
^ permalink raw reply [flat|nested] 4+ messages in thread
* [gcc(refs/users/meissner/heads/dmf008)] Revert patches
@ 2023-02-02 20:05 Michael Meissner
0 siblings, 0 replies; 4+ messages in thread
From: Michael Meissner @ 2023-02-02 20:05 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:254c9b4bb2e58c4c05ac8fdbaf80d9f794aad6e1
commit 254c9b4bb2e58c4c05ac8fdbaf80d9f794aad6e1
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Thu Feb 2 15:05:25 2023 -0500
Revert patches
Diff:
---
gcc/config/rs6000/mma.md | 345 +++++++---------------
gcc/config/rs6000/rs6000-c.cc | 3 -
gcc/config/rs6000/rs6000.cc | 35 +--
gcc/testsuite/gcc.target/powerpc/dm-double-test.c | 194 ------------
gcc/testsuite/lib/target-supports.exp | 19 --
5 files changed, 121 insertions(+), 475 deletions(-)
diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md
index 411e2345291..59ca6835f7c 100644
--- a/gcc/config/rs6000/mma.md
+++ b/gcc/config/rs6000/mma.md
@@ -227,22 +227,13 @@
(define_int_attr vvi4i4i8 [(UNSPEC_MMA_PMXVI4GER8 "pmxvi4ger8")])
-(define_int_attr vvi4i4i8_dm [(UNSPEC_MMA_PMXVI4GER8 "pmdmxvi4ger8")])
-
(define_int_attr avvi4i4i8 [(UNSPEC_MMA_PMXVI4GER8PP "pmxvi4ger8pp")])
-(define_int_attr avvi4i4i8_dm [(UNSPEC_MMA_PMXVI4GER8PP "pmdmxvi4ger8pp")])
-
(define_int_attr vvi4i4i2 [(UNSPEC_MMA_PMXVI16GER2 "pmxvi16ger2")
(UNSPEC_MMA_PMXVI16GER2S "pmxvi16ger2s")
(UNSPEC_MMA_PMXVF16GER2 "pmxvf16ger2")
(UNSPEC_MMA_PMXVBF16GER2 "pmxvbf16ger2")])
-(define_int_attr vvi4i4i2_dm [(UNSPEC_MMA_PMXVI16GER2 "pmdmxvi16ger2")
- (UNSPEC_MMA_PMXVI16GER2S "pmdmxvi16ger2s")
- (UNSPEC_MMA_PMXVF16GER2 "pmdmxvf16ger2")
- (UNSPEC_MMA_PMXVBF16GER2 "pmdmxvbf16ger2")])
-
(define_int_attr avvi4i4i2 [(UNSPEC_MMA_PMXVI16GER2PP "pmxvi16ger2pp")
(UNSPEC_MMA_PMXVI16GER2SPP "pmxvi16ger2spp")
(UNSPEC_MMA_PMXVF16GER2PP "pmxvf16ger2pp")
@@ -254,54 +245,25 @@
(UNSPEC_MMA_PMXVBF16GER2NP "pmxvbf16ger2np")
(UNSPEC_MMA_PMXVBF16GER2NN "pmxvbf16ger2nn")])
-(define_int_attr avvi4i4i2_dm [(UNSPEC_MMA_PMXVI16GER2PP "pmdmxvi16ger2pp")
- (UNSPEC_MMA_PMXVI16GER2SPP "pmdmxvi16ger2spp")
- (UNSPEC_MMA_PMXVF16GER2PP "pmdmxvf16ger2pp")
- (UNSPEC_MMA_PMXVF16GER2PN "pmdmxvf16ger2pn")
- (UNSPEC_MMA_PMXVF16GER2NP "pmdmxvf16ger2np")
- (UNSPEC_MMA_PMXVF16GER2NN "pmdmxvf16ger2nn")
- (UNSPEC_MMA_PMXVBF16GER2PP "pmdmxvbf16ger2pp")
- (UNSPEC_MMA_PMXVBF16GER2PN "pmdmxvbf16ger2pn")
- (UNSPEC_MMA_PMXVBF16GER2NP "pmdmxvbf16ger2np")
- (UNSPEC_MMA_PMXVBF16GER2NN "pmdmxvbf16ger2nn")])
-
(define_int_attr vvi4i4 [(UNSPEC_MMA_PMXVF32GER "pmxvf32ger")])
-(define_int_attr vvi4i4_dm [(UNSPEC_MMA_PMXVF32GER "pmdmxvf32ger")])
-
(define_int_attr avvi4i4 [(UNSPEC_MMA_PMXVF32GERPP "pmxvf32gerpp")
(UNSPEC_MMA_PMXVF32GERPN "pmxvf32gerpn")
(UNSPEC_MMA_PMXVF32GERNP "pmxvf32gernp")
(UNSPEC_MMA_PMXVF32GERNN "pmxvf32gernn")])
-(define_int_attr avvi4i4_dm [(UNSPEC_MMA_PMXVF32GERPP "pmdmxvf32gerpp")
- (UNSPEC_MMA_PMXVF32GERPN "pmdmxvf32gerpn")
- (UNSPEC_MMA_PMXVF32GERNP "pmdmxvf32gernp")
- (UNSPEC_MMA_PMXVF32GERNN "pmdmxvf32gernn")])
-
(define_int_attr pvi4i2 [(UNSPEC_MMA_PMXVF64GER "pmxvf64ger")])
-(define_int_attr pvi4i2_dm [(UNSPEC_MMA_PMXVF64GER "pmdmxvf64ger")])
-
(define_int_attr apvi4i2 [(UNSPEC_MMA_PMXVF64GERPP "pmxvf64gerpp")
(UNSPEC_MMA_PMXVF64GERPN "pmxvf64gerpn")
(UNSPEC_MMA_PMXVF64GERNP "pmxvf64gernp")
(UNSPEC_MMA_PMXVF64GERNN "pmxvf64gernn")])
-(define_int_attr apvi4i2_dm [(UNSPEC_MMA_PMXVF64GERPP "pmdmxvf64gerpp")
- (UNSPEC_MMA_PMXVF64GERPN "pmdmxvf64gerpn")
- (UNSPEC_MMA_PMXVF64GERNP "pmdmxvf64gernp")
- (UNSPEC_MMA_PMXVF64GERNN "pmdmxvf64gernn")])
-
(define_int_attr vvi4i4i4 [(UNSPEC_MMA_PMXVI8GER4 "pmxvi8ger4")])
-(define_int_attr vvi4i4i4_dm [(UNSPEC_MMA_PMXVI8GER4 "pmdmxvi8ger4")])
-
(define_int_attr avvi4i4i4 [(UNSPEC_MMA_PMXVI8GER4PP "pmxvi8ger4pp")
(UNSPEC_MMA_PMXVI8GER4SPP "pmxvi8ger4spp")])
-(define_int_attr avvi4i4i4_dm [(UNSPEC_MMA_PMXVI8GER4PP "pmdmxvi8ger4pp")
- (UNSPEC_MMA_PMXVI8GER4SPP "pmdmxvi8ger4spp")])
;; Vector pair support. OOmode can only live in VSRs.
(define_expand "movoo"
@@ -590,285 +552,190 @@
"dmxxextfdmr256 %0,%1,2"
[(set_attr "type" "mma")])
-;; MMA instructions that do not use their accumulators as an input, still must
-;; not allow their vector operands to overlap the registers used by the
-;; accumulator. We enforce this by marking the output as early clobber. If we
-;; have dense math, we don't need the whole prime/de-prime action, so just make
-;; thse instructions be NOPs.
-
-(define_expand "mma_<acc>"
- [(set (match_operand:XO 0 "register_operand")
- (unspec:XO [(match_operand:XO 1 "register_operand")]
- MMA_ACC))]
- "TARGET_MMA"
-{
- if (TARGET_DENSE_MATH)
- {
- if (!rtx_equal_p (operands[0], operands[1]))
- emit_move_insn (operands[0], operands[1]);
- DONE;
- }
-
- /* Generate the prime/de-prime code. */
-})
-
-(define_insn "*mma_<acc>"
+(define_insn "mma_<acc>"
[(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")]
MMA_ACC))]
- "TARGET_MMA && !TARGET_DENSE_MATH"
+ "TARGET_MMA"
"<acc> %A0"
[(set_attr "type" "mma")])
;; We can't have integer constants in XOmode so we wrap this in an
-;; UNSPEC_VOLATILE for the non-dense math case. For dense math, we don't need
-;; to disable optimization and we can do a normal UNSPEC.
+;; UNSPEC_VOLATILE.
-(define_expand "mma_xxsetaccz"
- [(set (match_operand:XO 0 "register_operand")
- (unspec_volatile:XO [(const_int 0)]
- UNSPECV_MMA_XXSETACCZ))]
- "TARGET_MMA"
-{
- if (TARGET_DENSE_MATH)
- {
- emit_insn (gen_mma_xxsetaccz_dm (operands[0]));
- DONE;
- }
-})
-
-(define_insn "*mma_xxsetaccz_vsx"
+(define_insn "mma_xxsetaccz"
[(set (match_operand:XO 0 "fpr_reg_operand" "=d")
(unspec_volatile:XO [(const_int 0)]
UNSPECV_MMA_XXSETACCZ))]
- "TARGET_MMA && !TARGET_DENSE_MATH"
+ "TARGET_MMA"
"xxsetaccz %A0"
[(set_attr "type" "mma")])
-
-(define_insn "mma_xxsetaccz_dm"
- [(set (match_operand:XO 0 "dmr_operand" "=wD")
- (unspec:XO [(const_int 0)]
- UNSPECV_MMA_XXSETACCZ))]
- "TARGET_DENSE_MATH"
- "dmsetdmrz %0"
- [(set_attr "type" "mma")])
-
(define_insn "mma_<vv>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
MMA_VV))]
"TARGET_MMA"
- "@
- dm<vv> %A0,%x1,%x2
- <vv> %A0,%x1,%x2
- <vv> %A0,%x1,%x2"
- [(set_attr "type" "mma")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ "<vv> %A0,%x1,%x2"
+ [(set_attr "type" "mma")])
(define_insn "mma_<avv>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
MMA_AVV))]
"TARGET_MMA"
"<avv> %A0,%x2,%x3"
- [(set_attr "type" "mma")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ [(set_attr "type" "mma")])
(define_insn "mma_<pv>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
MMA_PV))]
"TARGET_MMA"
- "@
- dm<pv> %A0,%x1,%x2
- <pv> %A0,%x1,%x2
- <pv> %A0,%x1,%x2"
- [(set_attr "type" "mma")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ "<pv> %A0,%x1,%x2"
+ [(set_attr "type" "mma")])
(define_insn "mma_<apv>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:OO 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
MMA_APV))]
"TARGET_MMA"
- "@
- dm<apv> %A0,%x2,%x3
- <apv> %A0,%x2,%x3
- <apv> %A0,%x2,%x3"
- [(set_attr "type" "mma")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ "<apv> %A0,%x2,%x3"
+ [(set_attr "type" "mma")])
(define_insn "mma_<vvi4i4i8>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "u8bit_cint_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "u8bit_cint_operand" "n,n")]
MMA_VVI4I4I8))]
"TARGET_MMA"
- "@
- dm<vvi4i4i8> %A0,%x1,%x2,%3,%4,%5
- <vvi4i4i8> %A0,%x1,%x2,%3,%4,%5
- <vvi4i4i8> %A0,%x1,%x2,%3,%4,%5"
+ "<vvi4i4i8> %A0,%x1,%x2,%3,%4,%5"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<avvi4i4i8>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 6 "u8bit_cint_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 6 "u8bit_cint_operand" "n,n")]
MMA_AVVI4I4I8))]
"TARGET_MMA"
"<avvi4i4i8> %A0,%x2,%x3,%4,%5,%6"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<vvi4i4i2>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_3_operand" "n,n")]
MMA_VVI4I4I2))]
"TARGET_MMA"
- "@
- <vvi4i4i2_dm> %A0,%x1,%x2,%3,%4,%5
- <vvi4i4i2> %A0,%x1,%x2,%3,%4,%5
- <vvi4i4i2> %A0,%x1,%x2,%3,%4,%5"
+ "<vvi4i4i2> %A0,%x1,%x2,%3,%4,%5"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<avvi4i4i2>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 6 "const_0_to_3_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 6 "const_0_to_3_operand" "n,n")]
MMA_AVVI4I4I2))]
"TARGET_MMA"
- "@
- <avvi4i4i2_dm> %A0,%x2,%x3,%4,%5,%6
- <avvi4i4i2> %A0,%x2,%x3,%4,%5,%6
- <avvi4i4i2> %A0,%x2,%x3,%4,%5,%6"
+ "<avvi4i4i2> %A0,%x2,%x3,%4,%5,%6"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<vvi4i4>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")]
MMA_VVI4I4))]
"TARGET_MMA"
- "@
- <vvi4i4_dm> %A0,%x1,%x2,%3,%4
- <vvi4i4> %A0,%x1,%x2,%3,%4
- <vvi4i4> %A0,%x1,%x2,%3,%4"
+ "<vvi4i4> %A0,%x1,%x2,%3,%4"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<avvi4i4>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n,n")]
MMA_AVVI4I4))]
"TARGET_MMA"
- "@
- <avvi4i4_dm> %A0,%x2,%x3,%4,%5
- <avvi4i4> %A0,%x2,%x3,%4,%5
- <avvi4i4> %A0,%x2,%x3,%4,%5"
+ "<avvi4i4> %A0,%x2,%x3,%4,%5"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<pvi4i2>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 4 "const_0_to_3_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 4 "const_0_to_3_operand" "n,n")]
MMA_PVI4I2))]
"TARGET_MMA"
- "@
- <pvi4i2_dm> %A0,%x1,%x2,%3,%4
- <pvi4i2> %A0,%x1,%x2,%3,%4
- <pvi4i2> %A0,%x1,%x2,%3,%4"
+ "<pvi4i2> %A0,%x1,%x2,%3,%4"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<apvi4i2>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:OO 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_3_operand" "n,n")]
MMA_APVI4I2))]
"TARGET_MMA"
- "@
- <apvi4i2_dm> %A0,%x2,%x3,%4,%5
- <apvi4i2> %A0,%x2,%x3,%4,%5
- <apvi4i2> %A0,%x2,%x3,%4,%5"
+ "<apvi4i2> %A0,%x2,%x3,%4,%5"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<vvi4i4i4>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n,n")]
MMA_VVI4I4I4))]
"TARGET_MMA"
- "@
- <vvi4i4i4_dm> %A0,%x1,%x2,%3,%4,%5
- <vvi4i4i4> %A0,%x1,%x2,%3,%4,%5
- <vvi4i4i4> %A0,%x1,%x2,%3,%4,%5"
+ "<vvi4i4i4> %A0,%x1,%x2,%3,%4,%5"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<avvi4i4i4>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 6 "const_0_to_15_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 6 "const_0_to_15_operand" "n,n")]
MMA_AVVI4I4I4))]
"TARGET_MMA"
- "@
- <avvi4i4i4_dm> %A0,%x2,%x3,%4,%5,%6
- <avvi4i4i4> %A0,%x2,%x3,%4,%5,%6
- <avvi4i4i4> %A0,%x2,%x3,%4,%5,%6"
+ "<avvi4i4i4> %A0,%x2,%x3,%4,%5,%6"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
diff --git a/gcc/config/rs6000/rs6000-c.cc b/gcc/config/rs6000/rs6000-c.cc
index baf1f4dc92b..2803014f2b6 100644
--- a/gcc/config/rs6000/rs6000-c.cc
+++ b/gcc/config/rs6000/rs6000-c.cc
@@ -600,9 +600,6 @@ rs6000_target_modify_macros (bool define_p, HOST_WIDE_INT flags)
/* Tell the user if we support the MMA instructions. */
if ((flags & OPTION_MASK_MMA) != 0)
rs6000_define_or_undefine_macro (define_p, "__MMA__");
- /* Tell the user if we support the dense math instructions. */
- if ((flags & OPTION_MASK_DENSE_MATH) != 0)
- rs6000_define_or_undefine_macro (define_p, "__PPC_DMR__");
/* Whether pc-relative code is being generated. */
if ((flags & OPTION_MASK_PCREL) != 0)
rs6000_define_or_undefine_macro (define_p, "__PCREL__");
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index c8f05f6f2d7..8ecb3021ff9 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -13910,13 +13910,8 @@ print_operand (FILE *file, rtx x, int code)
overlapping with the FPR registers. */
if (!REG_P (x))
output_operand_lossage ("invalid %%A value");
- else if (TARGET_DENSE_MATH)
- {
- if (DMR_REGNO_P (REGNO (x)))
- fprintf (file, "%d", REGNO (x) - FIRST_DMR_REGNO);
- else
- output_operand_lossage ("%%A operand is not a DMR");
- }
+ else if (TARGET_DENSE_MATH && DMR_REGNO_P (REGNO (x)))
+ fprintf (file, "%d", REGNO (x) - FIRST_DMR_REGNO);
else if (!FP_REGNO_P (REGNO (x)) || (REGNO (x) % 4) != 0)
output_operand_lossage ("invalid %%A value");
else
@@ -27361,7 +27356,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are reading an accumulator register, we have to
deprime it before we can access it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH
+ if (TARGET_MMA
&& GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
emit_insn (gen_mma_xxmfacc (src, src));
@@ -27393,9 +27388,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
emit_insn (gen_rtx_SET (dst2, src2));
}
- /* If we are writing an accumulator register that overlaps with the
- FPR registers, we have to prime it after we've written it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH
+ /* If we are writing an accumulator register, we have to
+ prime it after we've written it. */
+ if (TARGET_MMA
&& GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
emit_insn (gen_mma_xxmtacc (dst, dst));
@@ -27464,9 +27459,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
emit_insn (gen_rtx_SET (dst_i, op));
}
- /* On systems without dense math where accumulators overlap with the
- vector registers, we have to prime it after we've written it. */
- if (GET_MODE (src) == XOmode && !TARGET_DENSE_MATH)
+ /* We are writing an accumulator register, so we have to
+ prime it after we've written it. */
+ if (GET_MODE (src) == XOmode)
emit_insn (gen_mma_xxmtacc (dst, dst));
return;
@@ -27477,9 +27472,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
if (REG_P (src) && REG_P (dst) && (REGNO (src) < REGNO (dst)))
{
- /* If we are reading an accumulator register and we don't have dense
- math, we have to deprime it before we can access it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH
+ /* If we are reading an accumulator register, we have to
+ deprime it before we can access it. */
+ if (TARGET_MMA
&& GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
emit_insn (gen_mma_xxmfacc (src, src));
@@ -27507,7 +27502,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are writing an accumulator register, we have to
prime it after we've written it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH
+ if (TARGET_MMA
&& GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
emit_insn (gen_mma_xxmtacc (dst, dst));
}
@@ -27644,7 +27639,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are reading an accumulator register, we have to
deprime it before we can access it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (src)
+ if (TARGET_MMA && REG_P (src)
&& GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
emit_insn (gen_mma_xxmfacc (src, src));
@@ -27676,7 +27671,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are writing an accumulator register, we have to
prime it after we've written it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (dst)
+ if (TARGET_MMA && REG_P (dst)
&& GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
emit_insn (gen_mma_xxmtacc (dst, dst));
diff --git a/gcc/testsuite/gcc.target/powerpc/dm-double-test.c b/gcc/testsuite/gcc.target/powerpc/dm-double-test.c
deleted file mode 100644
index 66c19779585..00000000000
--- a/gcc/testsuite/gcc.target/powerpc/dm-double-test.c
+++ /dev/null
@@ -1,194 +0,0 @@
-/* Test derived from mma-double-1.c, modified for dense math. */
-/* { dg-do compile } */
-/* { dg-require-effective-target powerpc_dense_math_ok } */
-/* { dg-options "-mdejagnu-cpu=future -O2" } */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <altivec.h>
-
-typedef unsigned char vec_t __attribute__ ((vector_size (16)));
-typedef double v4sf_t __attribute__ ((vector_size (16)));
-#define SAVE_ACC(ACC, ldc, J) \
- __builtin_mma_disassemble_acc (result, ACC); \
- rowC = (v4sf_t *) &CO[0*ldc+J]; \
- rowC[0] += result[0]; \
- rowC = (v4sf_t *) &CO[1*ldc+J]; \
- rowC[0] += result[1]; \
- rowC = (v4sf_t *) &CO[2*ldc+J]; \
- rowC[0] += result[2]; \
- rowC = (v4sf_t *) &CO[3*ldc+J]; \
- rowC[0] += result[3];
-
-void
-DM (int m, int n, int k, double *A, double *B, double *C)
-{
- __vector_quad acc0, acc1, acc2, acc3, acc4, acc5, acc6, acc7;
- v4sf_t result[4];
- v4sf_t *rowC;
- for (int l = 0; l < n; l += 4)
- {
- double *CO;
- double *AO;
- AO = A;
- CO = C;
- C += m * 4;
- for (int j = 0; j < m; j += 16)
- {
- double *BO = B;
- __builtin_mma_xxsetaccz (&acc0);
- __builtin_mma_xxsetaccz (&acc1);
- __builtin_mma_xxsetaccz (&acc2);
- __builtin_mma_xxsetaccz (&acc3);
- __builtin_mma_xxsetaccz (&acc4);
- __builtin_mma_xxsetaccz (&acc5);
- __builtin_mma_xxsetaccz (&acc6);
- __builtin_mma_xxsetaccz (&acc7);
- unsigned long i;
-
- for (i = 0; i < k; i++)
- {
- vec_t *rowA = (vec_t *) & AO[i * 16];
- __vector_pair rowB;
- vec_t *rb = (vec_t *) & BO[i * 4];
- __builtin_mma_assemble_pair (&rowB, rb[1], rb[0]);
- __builtin_mma_xvf64gerpp (&acc0, rowB, rowA[0]);
- __builtin_mma_xvf64gerpp (&acc1, rowB, rowA[1]);
- __builtin_mma_xvf64gerpp (&acc2, rowB, rowA[2]);
- __builtin_mma_xvf64gerpp (&acc3, rowB, rowA[3]);
- __builtin_mma_xvf64gerpp (&acc4, rowB, rowA[4]);
- __builtin_mma_xvf64gerpp (&acc5, rowB, rowA[5]);
- __builtin_mma_xvf64gerpp (&acc6, rowB, rowA[6]);
- __builtin_mma_xvf64gerpp (&acc7, rowB, rowA[7]);
- }
- SAVE_ACC (&acc0, m, 0);
- SAVE_ACC (&acc2, m, 4);
- SAVE_ACC (&acc1, m, 2);
- SAVE_ACC (&acc3, m, 6);
- SAVE_ACC (&acc4, m, 8);
- SAVE_ACC (&acc6, m, 12);
- SAVE_ACC (&acc5, m, 10);
- SAVE_ACC (&acc7, m, 14);
- AO += k * 16;
- BO += k * 4;
- CO += 16;
- }
- B += k * 4;
- }
-}
-
-void
-init (double *matrix, int row, int column)
-{
- for (int j = 0; j < column; j++)
- {
- for (int i = 0; i < row; i++)
- {
- matrix[j * row + i] = (i * 16 + 2 + j) / 0.123;
- }
- }
-}
-
-void
-init0 (double *matrix, double *matrix1, int row, int column)
-{
- for (int j = 0; j < column; j++)
- for (int i = 0; i < row; i++)
- matrix[j * row + i] = matrix1[j * row + i] = 0;
-}
-
-
-void
-print (const char *name, const double *matrix, int row, int column)
-{
- printf ("Matrix %s has %d rows and %d columns:\n", name, row, column);
- for (int i = 0; i < row; i++)
- {
- for (int j = 0; j < column; j++)
- {
- printf ("%f ", matrix[j * row + i]);
- }
- printf ("\n");
- }
- printf ("\n");
-}
-
-int
-main (int argc, char *argv[])
-{
- int rowsA, colsB, common;
- int i, j, k;
- int ret = 0;
-
- for (int t = 16; t <= 128; t += 16)
- {
- for (int t1 = 4; t1 <= 16; t1 += 4)
- {
- rowsA = t;
- colsB = t1;
- common = 1;
- /* printf ("Running test for rows = %d,cols = %d\n", t, t1); */
- double A[rowsA * common];
- double B[common * colsB];
- double C[rowsA * colsB];
- double D[rowsA * colsB];
-
-
- init (A, rowsA, common);
- init (B, common, colsB);
- init0 (C, D, rowsA, colsB);
- DM (rowsA, colsB, common, A, B, C);
-
- for (i = 0; i < colsB; i++)
- {
- for (j = 0; j < rowsA; j++)
- {
- D[i * rowsA + j] = 0;
- for (k = 0; k < common; k++)
- {
- D[i * rowsA + j] +=
- A[k * rowsA + j] * B[k + common * i];
- }
- }
- }
- for (i = 0; i < colsB; i++)
- {
- for (j = 0; j < rowsA; j++)
- {
- for (k = 0; k < common; k++)
- {
- if (D[i * rowsA + j] != C[i * rowsA + j])
- {
- printf ("Error %d,%d,%d\n",i,j,k);
- ret++;
- }
- }
- }
- }
- if (ret)
- {
- print ("A", A, rowsA, common);
- print ("B", B, common, colsB);
- print ("C", C, rowsA, colsB);
- print ("D", D, rowsA, colsB);
- }
- }
- }
-
-#ifdef VERBOSE
- if (ret)
- printf ("DM double test fail: %d errors\n",ret);
- else
- printf ("DM double test success: 0 DM errors\n");
-#else
- if (ret)
- abort();
-#endif
-
- return ret;
-}
-
-/* { dg-final { scan-assembler {\mdmsetdmrz\M} } } */
-/* { dg-final { scan-assembler {\mdmxvf64gerpp\M} } } */
-/* { dg-final { scan-assembler {\mdmxxextfdmr512\M} } } */
-
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index 9586ed3ae47..227e3004077 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -6581,25 +6581,6 @@ proc check_effective_target_power10_ok { } {
}
}
-# Return 1 if this is a PowerPC target supporting -mcpu=future or -mdense-math
-# which enables the dense math operations.
-proc check_effective_target_powerpc_dense_math_ok { } {
- return [check_no_compiler_messages_nocache powerpc_dense_math_ok assembly {
- __vector_quad vq;
- void test (void)
- {
- #ifndef __PPC_DMR__
- #error "target does not have dense math support."
- #else
- /* Make sure we have dense math support. */
- __vector_quad dmr;
- __asm__ ("dmsetaccz %A0" : "=wD" (dmr));
- vq = dmr;
- #endif
- }
- } "-mcpu=future"]
-}
-
# Return 1 if this is a PowerPC target supporting -mfloat128 via either
# software emulation on power7/power8 systems or hardware support on power9.
^ permalink raw reply [flat|nested] 4+ messages in thread
* [gcc(refs/users/meissner/heads/dmf008)] Revert patches
@ 2023-02-02 19:55 Michael Meissner
0 siblings, 0 replies; 4+ messages in thread
From: Michael Meissner @ 2023-02-02 19:55 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:f6ace2134c5d4eb3819d8577c044d5c39f315aac
commit f6ace2134c5d4eb3819d8577c044d5c39f315aac
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Thu Feb 2 14:55:25 2023 -0500
Revert patches
Diff:
---
gcc/config/rs6000/constraints.md | 3 -
gcc/config/rs6000/mma.md | 362 ++++++++--------------
gcc/config/rs6000/power10.md | 142 ++++-----
gcc/config/rs6000/predicates.md | 32 --
gcc/config/rs6000/rs6000-c.cc | 5 -
gcc/config/rs6000/rs6000-cpus.def | 10 -
gcc/config/rs6000/rs6000-opts.h | 4 +-
gcc/config/rs6000/rs6000-tables.opt | 3 -
gcc/config/rs6000/rs6000.cc | 275 +++-------------
gcc/config/rs6000/rs6000.h | 39 +--
gcc/config/rs6000/rs6000.md | 14 +-
gcc/config/rs6000/rs6000.opt | 8 -
gcc/doc/invoke.texi | 2 +-
gcc/doc/md.texi | 7 -
gcc/testsuite/gcc.target/powerpc/dm-double-test.c | 194 ------------
15 files changed, 248 insertions(+), 852 deletions(-)
diff --git a/gcc/config/rs6000/constraints.md b/gcc/config/rs6000/constraints.md
index 218e41d82a8..c4a6ccf4efb 100644
--- a/gcc/config/rs6000/constraints.md
+++ b/gcc/config/rs6000/constraints.md
@@ -107,9 +107,6 @@
(match_test "TARGET_P8_VECTOR")
(match_operand 0 "s5bit_cint_operand")))
-(define_register_constraint "wD" "rs6000_constraints[RS6000_CONSTRAINT_wD]"
- "Accumulator register.")
-
(define_constraint "wE"
"@internal Vector constant that can be loaded with the XXSPLTIB instruction."
(match_test "xxspltib_constant_nosplit (op, mode)"))
diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md
index 9e3feb3ea54..d36dc13872b 100644
--- a/gcc/config/rs6000/mma.md
+++ b/gcc/config/rs6000/mma.md
@@ -91,7 +91,6 @@
UNSPEC_MMA_XVI8GER4SPP
UNSPEC_MMA_XXMFACC
UNSPEC_MMA_XXMTACC
- UNSPEC_DM_ASSEMBLE_ACC
])
(define_c_enum "unspecv"
@@ -315,9 +314,7 @@
(set_attr "length" "*,*,8")])
\f
-;; Vector quad support. Under the original MMA, XOmode can only live in VSX
-;; vector registers 0..31. With dense math, XOmode can live in either VSX
-;; registers (0..63) or DMR registers.
+;; Vector quad support. XOmode can only live in FPRs.
(define_expand "movxo"
[(set (match_operand:XO 0 "nonimmediate_operand")
(match_operand:XO 1 "input_operand"))]
@@ -342,10 +339,10 @@
gcc_assert (false);
})
-(define_insn_and_split "*movxo_vsx"
+(define_insn_and_split "*movxo"
[(set (match_operand:XO 0 "nonimmediate_operand" "=d,m,d")
(match_operand:XO 1 "input_operand" "m,d,d"))]
- "TARGET_MMA && !TARGET_DENSE_MATH
+ "TARGET_MMA
&& (gpc_reg_operand (operands[0], XOmode)
|| gpc_reg_operand (operands[1], XOmode))"
"@
@@ -362,31 +359,6 @@
(set_attr "length" "*,*,16")
(set_attr "max_prefixed_insns" "2,2,*")])
-(define_insn_and_split "*movxo_dm"
- [(set (match_operand:XO 0 "nonimmediate_operand" "=wa,m, wa,wD,wD,wa")
- (match_operand:XO 1 "input_operand" "m,wa,wa,wa,wD,wD"))]
- "TARGET_DENSE_MATH
- && (gpc_reg_operand (operands[0], XOmode)
- || gpc_reg_operand (operands[1], XOmode))"
- "@
- #
- #
- #
- dmxxinstdmr512 %0,%1,%Y1,0
- dmmr %0,%1
- dmxxextfdmr512 %0,%Y0,%1,0"
- "&& reload_completed
- && !dmr_operand (operands[0], XOmode)
- && !dmr_operand (operands[1], XOmode)"
- [(const_int 0)]
-{
- rs6000_split_multireg_move (operands[0], operands[1]);
- DONE;
-}
- [(set_attr "type" "vecload,vecstore,veclogical,mma,mma,mma")
- (set_attr "length" "*,*,16,*,*,*")
- (set_attr "max_prefixed_insns" "2,2,*,*,*,*")])
-
(define_expand "vsx_assemble_pair"
[(match_operand:OO 0 "vsx_register_operand")
(match_operand:V16QI 1 "mma_assemble_input_operand")
@@ -454,38 +426,25 @@
})
(define_expand "mma_assemble_acc"
- [(match_operand:XO 0 "register_operand")
+ [(match_operand:XO 0 "fpr_reg_operand")
(match_operand:V16QI 1 "mma_assemble_input_operand")
(match_operand:V16QI 2 "mma_assemble_input_operand")
(match_operand:V16QI 3 "mma_assemble_input_operand")
(match_operand:V16QI 4 "mma_assemble_input_operand")]
"TARGET_MMA"
{
- rtx op0 = operands[0];
- rtx op1 = operands[1];
- rtx op2 = operands[2];
- rtx op3 = operands[3];
- rtx op4 = operands[4];
-
- if (TARGET_DENSE_MATH)
- {
- rtx vpair1 = gen_reg_rtx (OOmode);
- rtx vpair2 = gen_reg_rtx (OOmode);
- emit_insn (gen_vsx_assemble_pair (vpair1, op1, op2));
- emit_insn (gen_vsx_assemble_pair (vpair2, op3, op4));
- emit_insn (gen_mma_assemble_acc_dm (op0, vpair1, vpair2));
- }
-
- else
- emit_insn (gen_mma_assemble_acc_vsx (op0, op1, op2, op3, op4));
-
+ rtx src = gen_rtx_UNSPEC_VOLATILE (XOmode,
+ gen_rtvec (4, operands[1], operands[2],
+ operands[3], operands[4]),
+ UNSPECV_MMA_ASSEMBLE);
+ emit_move_insn (operands[0], src);
DONE;
})
;; We cannot update the four output registers atomically, so mark the output
-;; as an early clobber so we don't accidentally clobber the input operands.
+;; as an early clobber so we don't accidentally clobber the input operands. */
-(define_insn_and_split "mma_assemble_acc_vsx"
+(define_insn_and_split "*mma_assemble_acc"
[(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
(unspec_volatile:XO
[(match_operand:V16QI 1 "mma_assemble_input_operand" "mwa")
@@ -493,7 +452,7 @@
(match_operand:V16QI 3 "mma_assemble_input_operand" "mwa")
(match_operand:V16QI 4 "mma_assemble_input_operand" "mwa")]
UNSPECV_MMA_ASSEMBLE))]
- "TARGET_MMA && !TARGET_DENSE_MATH
+ "TARGET_MMA
&& fpr_reg_operand (operands[0], XOmode)"
"#"
"&& reload_completed"
@@ -507,31 +466,28 @@
DONE;
})
-;; On a system with dense math, we build the accumulators from two vector
-;; pairs.
-
-(define_insn "mma_assemble_acc_dm"
- [(set (match_operand:XO 0 "dmr_operand" "=wD")
- (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa")
- (match_operand:OO 2 "vsx_register_operand" "wa")]
- UNSPEC_DM_ASSEMBLE_ACC))]
- "TARGET_MMA && TARGET_DENSE_MATH"
- "dmxxinstdmr512 %0,%1,%2,0"
- [(set_attr "type" "mma")])
-
(define_expand "mma_disassemble_acc"
- [(set (match_operand:V16QI 0 "register_operand")
- (unspec:V16QI [(match_operand:XO 1 "register_operand")
- (match_operand 2 "const_0_to_3_operand")]
- UNSPEC_MMA_EXTRACT))]
- "TARGET_MMA")
+ [(match_operand:V16QI 0 "mma_disassemble_output_operand")
+ (match_operand:XO 1 "fpr_reg_operand")
+ (match_operand 2 "const_0_to_3_operand")]
+ "TARGET_MMA"
+{
+ rtx src;
+ int regoff = INTVAL (operands[2]);
+ src = gen_rtx_UNSPEC (V16QImode,
+ gen_rtvec (2, operands[1], GEN_INT (regoff)),
+ UNSPEC_MMA_EXTRACT);
+ emit_move_insn (operands[0], src);
+ DONE;
+})
-(define_insn_and_split "*mma_disassemble_acc_vsx"
+(define_insn_and_split "*mma_disassemble_acc"
[(set (match_operand:V16QI 0 "mma_disassemble_output_operand" "=mwa")
- (unspec:V16QI [(match_operand:XO 1 "fpr_reg_operand" "d")
- (match_operand 2 "const_0_to_3_operand")]
+ (unspec:V16QI [(match_operand:XO 1 "fpr_reg_operand" "d")
+ (match_operand 2 "const_0_to_3_operand")]
UNSPEC_MMA_EXTRACT))]
- "TARGET_MMA"
+ "TARGET_MMA
+ && fpr_reg_operand (operands[1], XOmode)"
"#"
"&& reload_completed"
[(const_int 0)]
@@ -543,258 +499,194 @@
DONE;
})
-(define_insn "*mma_disassemble_acc_dm"
- [(set (match_operand:V16QI 0 "vsx_register_operand" "=wa")
- (unspec:V16QI [(match_operand:XO 1 "dmr_operand" "wD")
- (match_operand 2 "const_0_to_3_operand")]
- UNSPEC_MMA_EXTRACT))]
- "TARGET_DENSE_MATH"
- "dmxxextfdmr256 %0,%1,2"
- [(set_attr "type" "mma")])
-
-;; MMA instructions that do not use their accumulators as an input, still must
-;; not allow their vector operands to overlap the registers used by the
-;; accumulator. We enforce this by marking the output as early clobber. If we
-;; have dense math, we don't need the whole prime/de-prime action, so just make
-;; thse instructions be NOPs.
+;; MMA instructions that do not use their accumulators as an input, still
+;; must not allow their vector operands to overlap the registers used by
+;; the accumulator. We enforce this by marking the output as early clobber.
-(define_expand "mma_<acc>"
- [(set (match_operand:XO 0 "register_operand")
- (unspec:XO [(match_operand:XO 1 "register_operand")]
- MMA_ACC))]
- "TARGET_MMA"
-{
- if (TARGET_DENSE_MATH)
- {
- if (!rtx_equal_p (operands[0], operands[1]))
- emit_move_insn (operands[0], operands[1]);
- DONE;
- }
-
- /* Generate the prime/de-prime code. */
-})
-
-(define_insn "*mma_<acc>"
+(define_insn "mma_<acc>"
[(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")]
MMA_ACC))]
- "TARGET_MMA && !TARGET_DENSE_MATH"
+ "TARGET_MMA"
"<acc> %A0"
[(set_attr "type" "mma")])
;; We can't have integer constants in XOmode so we wrap this in an
-;; UNSPEC_VOLATILE for the non-dense math case. For dense math, we don't need
-;; to disable optimization and we can do a normal UNSPEC.
-
-(define_expand "mma_xxsetaccz"
- [(set (match_operand:XO 0 "register_operand")
- (unspec_volatile:XO [(const_int 0)]
- UNSPECV_MMA_XXSETACCZ))]
- "TARGET_MMA"
-{
- if (TARGET_DENSE_MATH)
- {
- emit_insn (gen_mma_xxsetaccz_dm (operands[0]));
- DONE;
- }
-})
+;; UNSPEC_VOLATILE.
-(define_insn "*mma_xxsetaccz_vsx"
+(define_insn "mma_xxsetaccz"
[(set (match_operand:XO 0 "fpr_reg_operand" "=d")
(unspec_volatile:XO [(const_int 0)]
UNSPECV_MMA_XXSETACCZ))]
- "TARGET_MMA && !TARGET_DENSE_MATH"
+ "TARGET_MMA"
"xxsetaccz %A0"
[(set_attr "type" "mma")])
-
-(define_insn "mma_xxsetaccz_dm"
- [(set (match_operand:XO 0 "dmr_operand" "=wD")
- (unspec:XO [(const_int 0)]
- UNSPECV_MMA_XXSETACCZ))]
- "TARGET_DENSE_MATH"
- "dmsetdmrz %0"
- [(set_attr "type" "mma")])
-
(define_insn "mma_<vv>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
MMA_VV))]
"TARGET_MMA"
"<vv> %A0,%x1,%x2"
- [(set_attr "type" "mma")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ [(set_attr "type" "mma")])
(define_insn "mma_<avv>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
MMA_AVV))]
"TARGET_MMA"
"<avv> %A0,%x2,%x3"
- [(set_attr "type" "mma")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ [(set_attr "type" "mma")])
(define_insn "mma_<pv>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
MMA_PV))]
"TARGET_MMA"
"<pv> %A0,%x1,%x2"
- [(set_attr "type" "mma")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ [(set_attr "type" "mma")])
(define_insn "mma_<apv>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:OO 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
MMA_APV))]
"TARGET_MMA"
"<apv> %A0,%x2,%x3"
- [(set_attr "type" "mma")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ [(set_attr "type" "mma")])
(define_insn "mma_<vvi4i4i8>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "u8bit_cint_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "u8bit_cint_operand" "n,n")]
MMA_VVI4I4I8))]
"TARGET_MMA"
"<vvi4i4i8> %A0,%x1,%x2,%3,%4,%5"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<avvi4i4i8>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 6 "u8bit_cint_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 6 "u8bit_cint_operand" "n,n")]
MMA_AVVI4I4I8))]
"TARGET_MMA"
"<avvi4i4i8> %A0,%x2,%x3,%4,%5,%6"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<vvi4i4i2>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_3_operand" "n,n")]
MMA_VVI4I4I2))]
"TARGET_MMA"
"<vvi4i4i2> %A0,%x1,%x2,%3,%4,%5"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<avvi4i4i2>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 6 "const_0_to_3_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 6 "const_0_to_3_operand" "n,n")]
MMA_AVVI4I4I2))]
"TARGET_MMA"
"<avvi4i4i2> %A0,%x2,%x3,%4,%5,%6"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<vvi4i4>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")]
MMA_VVI4I4))]
"TARGET_MMA"
"<vvi4i4> %A0,%x1,%x2,%3,%4"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<avvi4i4>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n,n")]
MMA_AVVI4I4))]
"TARGET_MMA"
"<avvi4i4> %A0,%x2,%x3,%4,%5"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<pvi4i2>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 4 "const_0_to_3_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 4 "const_0_to_3_operand" "n,n")]
MMA_PVI4I2))]
"TARGET_MMA"
"<pvi4i2> %A0,%x1,%x2,%3,%4"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<apvi4i2>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:OO 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_3_operand" "n,n")]
MMA_APVI4I2))]
"TARGET_MMA"
"<apvi4i2> %A0,%x2,%x3,%4,%5"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<vvi4i4i4>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n,n")]
MMA_VVI4I4I4))]
"TARGET_MMA"
"<vvi4i4i4> %A0,%x1,%x2,%3,%4,%5"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
(define_insn "mma_<avvi4i4i4>"
- [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
- (unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
- (match_operand:SI 6 "const_0_to_15_operand" "n,n,n")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+ (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n,n")
+ (match_operand:SI 6 "const_0_to_15_operand" "n,n")]
MMA_AVVI4I4I4))]
"TARGET_MMA"
"<avvi4i4i4> %A0,%x2,%x3,%4,%5,%6"
[(set_attr "type" "mma")
- (set_attr "prefixed" "yes")
- (set_attr "isa" "dm,not_dm,not_dm")])
+ (set_attr "prefixed" "yes")])
diff --git a/gcc/config/rs6000/power10.md b/gcc/config/rs6000/power10.md
index caed2d53668..8e1d4e1afc6 100644
--- a/gcc/config/rs6000/power10.md
+++ b/gcc/config/rs6000/power10.md
@@ -97,12 +97,12 @@
(eq_attr "update" "no")
(eq_attr "size" "!128")
(eq_attr "prefixed" "no")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,LU_power10")
(define_insn_reservation "power10-fused-load" 4
(and (eq_attr "type" "fused_load_cmpi,fused_addis_load,fused_load_load")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,LU_power10")
(define_insn_reservation "power10-prefixed-load" 4
@@ -110,13 +110,13 @@
(eq_attr "update" "no")
(eq_attr "size" "!128")
(eq_attr "prefixed" "yes")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,LU_power10")
(define_insn_reservation "power10-load-update" 4
(and (eq_attr "type" "load")
(eq_attr "update" "yes")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,LU_power10+SXU_power10")
(define_insn_reservation "power10-fpload-double" 4
@@ -124,7 +124,7 @@
(eq_attr "update" "no")
(eq_attr "size" "64")
(eq_attr "prefixed" "no")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,LU_power10")
(define_insn_reservation "power10-prefixed-fpload-double" 4
@@ -132,14 +132,14 @@
(eq_attr "update" "no")
(eq_attr "size" "64")
(eq_attr "prefixed" "yes")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,LU_power10")
(define_insn_reservation "power10-fpload-update-double" 4
(and (eq_attr "type" "fpload")
(eq_attr "update" "yes")
(eq_attr "size" "64")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,LU_power10+SXU_power10")
; SFmode loads are cracked and have additional 3 cycles over DFmode
@@ -148,27 +148,27 @@
(and (eq_attr "type" "fpload")
(eq_attr "update" "no")
(eq_attr "size" "32")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,LU_power10")
(define_insn_reservation "power10-fpload-update-single" 7
(and (eq_attr "type" "fpload")
(eq_attr "update" "yes")
(eq_attr "size" "32")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,LU_power10+SXU_power10")
(define_insn_reservation "power10-vecload" 4
(and (eq_attr "type" "vecload")
(eq_attr "size" "!256")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,LU_power10")
; lxvp
(define_insn_reservation "power10-vecload-pair" 4
(and (eq_attr "type" "vecload")
(eq_attr "size" "256")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,LU_power10+SXU_power10")
; Store Unit
@@ -178,12 +178,12 @@
(eq_attr "prefixed" "no")
(eq_attr "size" "!128")
(eq_attr "size" "!256")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,STU_power10")
(define_insn_reservation "power10-fused-store" 0
(and (eq_attr "type" "fused_store_store")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,STU_power10")
(define_insn_reservation "power10-prefixed-store" 0
@@ -191,52 +191,52 @@
(eq_attr "prefixed" "yes")
(eq_attr "size" "!128")
(eq_attr "size" "!256")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,STU_power10")
; Update forms have 2 cycle latency for updated addr reg
(define_insn_reservation "power10-store-update" 2
(and (eq_attr "type" "store,fpstore")
(eq_attr "update" "yes")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,STU_power10")
; stxvp
(define_insn_reservation "power10-vecstore-pair" 0
(and (eq_attr "type" "vecstore")
(eq_attr "size" "256")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,stu0_power10+stu1_power10")
(define_insn_reservation "power10-larx" 4
(and (eq_attr "type" "load_l")
(eq_attr "size" "!128")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,LU_power10")
; All load quad forms
(define_insn_reservation "power10-lq" 4
(and (eq_attr "type" "load,load_l")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,LU_power10+SXU_power10")
(define_insn_reservation "power10-stcx" 0
(and (eq_attr "type" "store_c")
(eq_attr "size" "!128")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,STU_power10")
; All store quad forms
(define_insn_reservation "power10-stq" 0
(and (eq_attr "type" "store,store_c")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,stu0_power10+stu1_power10")
(define_insn_reservation "power10-sync" 1
(and (eq_attr "type" "sync,isync")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,STU_power10")
@@ -248,7 +248,7 @@
(define_insn_reservation "power10-alu" 2
(and (eq_attr "type" "add,exts,integer,logical,isel")
(eq_attr "prefixed" "no")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
; 4 cycle CR latency
(define_bypass 4 "power10-alu"
@@ -256,28 +256,28 @@
(define_insn_reservation "power10-fused_alu" 2
(and (eq_attr "type" "fused_arith_logical,fused_cmp_isel,fused_carry")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,EXU_power10")
; paddi
(define_insn_reservation "power10-paddi" 2
(and (eq_attr "type" "add")
(eq_attr "prefixed" "yes")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,EXU_power10")
; Rotate/shift (non-record form)
(define_insn_reservation "power10-rot" 2
(and (eq_attr "type" "insert,shift")
(eq_attr "dot" "no")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
; Record form rotate/shift
(define_insn_reservation "power10-rot-compare" 3
(and (eq_attr "type" "insert,shift")
(eq_attr "dot" "yes")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
; 5 cycle CR latency
(define_bypass 5 "power10-rot-compare"
@@ -285,7 +285,7 @@
(define_insn_reservation "power10-alu2" 3
(and (eq_attr "type" "cntlz,popcnt,trap")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
; 5 cycle CR latency
(define_bypass 5 "power10-alu2"
@@ -293,24 +293,24 @@
(define_insn_reservation "power10-cmp" 2
(and (eq_attr "type" "cmp")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
; Treat 'two' and 'three' types as 2 or 3 way cracked
(define_insn_reservation "power10-two" 4
(and (eq_attr "type" "two")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,EXU_power10")
(define_insn_reservation "power10-three" 6
(and (eq_attr "type" "three")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_all_power10,EXU_power10")
(define_insn_reservation "power10-mul" 5
(and (eq_attr "type" "mul")
(eq_attr "dot" "no")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
; 4 cycle MUL->MUL latency
(define_bypass 4 "power10-mul"
@@ -319,7 +319,7 @@
(define_insn_reservation "power10-mul-compare" 5
(and (eq_attr "type" "mul")
(eq_attr "dot" "yes")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,EXU_power10")
; 4 cycle MUL->MUL latency
(define_bypass 4 "power10-mul-compare"
@@ -331,13 +331,13 @@
(define_insn_reservation "power10-div" 12
(and (eq_attr "type" "div")
(eq_attr "dot" "no")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-div-compare" 12
(and (eq_attr "type" "div")
(eq_attr "dot" "yes")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,EXU_power10")
; 14 cycle CR latency
(define_bypass 14 "power10-div-compare"
@@ -345,34 +345,34 @@
(define_insn_reservation "power10-crlogical" 2
(and (eq_attr "type" "cr_logical")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mfcrf" 2
(and (eq_attr "type" "mfcrf")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mfcr" 3
(and (eq_attr "type" "mfcr")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,EXU_power10")
; Should differentiate between 1 cr field and > 1 since target of > 1 cr
; is cracked
(define_insn_reservation "power10-mtcr" 3
(and (eq_attr "type" "mtcr")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mtjmpr" 3
(and (eq_attr "type" "mtjmpr")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mfjmpr" 2
(and (eq_attr "type" "mfjmpr")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
@@ -380,126 +380,126 @@
(define_insn_reservation "power10-fpsimple" 3
(and (eq_attr "type" "fpsimple")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-fp" 5
(and (eq_attr "type" "fp,dmul")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-fpcompare" 3
(and (eq_attr "type" "fpcompare")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-sdiv" 22
(and (eq_attr "type" "sdiv")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-ddiv" 27
(and (eq_attr "type" "ddiv")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-sqrt" 26
(and (eq_attr "type" "ssqrt")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-dsqrt" 36
(and (eq_attr "type" "dsqrt")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vec-2cyc" 2
(and (eq_attr "type" "vecmove,veclogical,vecexts,veccmpfx")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-fused-vec" 2
(and (eq_attr "type" "fused_vector")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,EXU_power10")
(define_insn_reservation "power10-veccmp" 3
(and (eq_attr "type" "veccmp")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecsimple" 2
(and (eq_attr "type" "vecsimple")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecnormal" 5
(and (eq_attr "type" "vecfloat,vecdouble")
(eq_attr "size" "!128")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-qp" 12
(and (eq_attr "type" "vecfloat,vecdouble")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecperm" 3
(and (eq_attr "type" "vecperm")
(eq_attr "prefixed" "no")
(eq_attr "dot" "no")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecperm-compare" 3
(and (eq_attr "type" "vecperm")
(eq_attr "dot" "yes")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,EXU_power10")
(define_insn_reservation "power10-prefixed-vecperm" 3
(and (eq_attr "type" "vecperm")
(eq_attr "prefixed" "yes")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,EXU_power10")
(define_insn_reservation "power10-veccomplex" 6
(and (eq_attr "type" "veccomplex")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecfdiv" 24
(and (eq_attr "type" "vecfdiv")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecdiv" 27
(and (eq_attr "type" "vecdiv")
(eq_attr "size" "!128")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-qpdiv" 56
(and (eq_attr "type" "vecdiv")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-qpmul" 24
(and (eq_attr "type" "qmul")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mtvsr" 2
(and (eq_attr "type" "mtvsr")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mfvsr" 2
(and (eq_attr "type" "mfvsr")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
@@ -507,26 +507,26 @@
; Branch is 2 cycles, grouped with STU for issue
(define_insn_reservation "power10-branch" 2
(and (eq_attr "type" "jmpreg,branch")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,STU_power10")
(define_insn_reservation "power10-fused-branch" 3
(and (eq_attr "type" "fused_mtbc")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,STU_power10")
; Crypto
(define_insn_reservation "power10-crypto" 4
(and (eq_attr "type" "crypto")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
; HTM
(define_insn_reservation "power10-htm" 2
(and (eq_attr "type" "htmsimple,htm")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
@@ -535,26 +535,26 @@
(define_insn_reservation "power10-dfp" 12
(and (eq_attr "type" "dfp")
(eq_attr "size" "!128")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-dfpq" 12
(and (eq_attr "type" "dfp")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,EXU_power10")
; MMA
(define_insn_reservation "power10-mma" 9
(and (eq_attr "type" "mma")
(eq_attr "prefixed" "no")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_any_power10,EXU_super_power10")
(define_insn_reservation "power10-prefixed-mma" 9
(and (eq_attr "type" "mma")
(eq_attr "prefixed" "yes")
- (eq_attr "cpu" "power10,future"))
+ (eq_attr "cpu" "power10"))
"DU_even_power10,EXU_super_power10")
; 4 cycle MMA->MMA latency
(define_bypass 4 "power10-mma,power10-prefixed-mma"
diff --git a/gcc/config/rs6000/predicates.md b/gcc/config/rs6000/predicates.md
index 4ac9afd2c11..52c65534e51 100644
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -186,38 +186,6 @@
return VLOGICAL_REGNO_P (REGNO (op));
})
-;; Return 1 if op is a DMR register
-(define_predicate "dmr_operand"
- (match_operand 0 "register_operand")
-{
- if (!REG_P (op))
- return 0;
-
- if (!HARD_REGISTER_P (op))
- return 1;
-
- return DMR_REGNO_P (REGNO (op));
-})
-
-;; Return 1 if op is an accumulator. On power10 systems, the accumulators
-;; overlap with the FPRs, while on systems with dense math, the accumulators
-;; are separate dense math registers and do not overlap with the FPR
-;; registers..
-(define_predicate "accumulator_operand"
- (match_operand 0 "register_operand")
-{
- if (!REG_P (op))
- return 0;
-
- if (!HARD_REGISTER_P (op))
- return 1;
-
- int r = REGNO (op);
- return (TARGET_DENSE_MATH
- ? DMR_REGNO_P (r)
- : FP_REGNO_P (r) && (r & 3) == 0);
-})
-
;; Return 1 if op is the carry register.
(define_predicate "ca_operand"
(match_operand 0 "register_operand")
diff --git a/gcc/config/rs6000/rs6000-c.cc b/gcc/config/rs6000/rs6000-c.cc
index baf1f4dc92b..8555174d36e 100644
--- a/gcc/config/rs6000/rs6000-c.cc
+++ b/gcc/config/rs6000/rs6000-c.cc
@@ -447,8 +447,6 @@ rs6000_target_modify_macros (bool define_p, HOST_WIDE_INT flags)
rs6000_define_or_undefine_macro (define_p, "_ARCH_PWR9");
if ((flags & OPTION_MASK_POWER10) != 0)
rs6000_define_or_undefine_macro (define_p, "_ARCH_PWR10");
- if ((flags & OPTION_MASK_FUTURE) != 0)
- rs6000_define_or_undefine_macro (define_p, "_ARCH_PWR_FUTURE");
if ((flags & OPTION_MASK_SOFT_FLOAT) != 0)
rs6000_define_or_undefine_macro (define_p, "_SOFT_FLOAT");
if ((flags & OPTION_MASK_RECIP_PRECISION) != 0)
@@ -600,9 +598,6 @@ rs6000_target_modify_macros (bool define_p, HOST_WIDE_INT flags)
/* Tell the user if we support the MMA instructions. */
if ((flags & OPTION_MASK_MMA) != 0)
rs6000_define_or_undefine_macro (define_p, "__MMA__");
- /* Tell the user if we support the dense math instructions. */
- if ((flags & OPTION_MASK_DENSE_MATH) != 0)
- rs6000_define_or_undefine_macro (define_p, "__PPC_DMR__");
/* Whether pc-relative code is being generated. */
if ((flags & OPTION_MASK_PCREL) != 0)
rs6000_define_or_undefine_macro (define_p, "__PCREL__");
diff --git a/gcc/config/rs6000/rs6000-cpus.def b/gcc/config/rs6000/rs6000-cpus.def
index a4cce08d727..4f350da378c 100644
--- a/gcc/config/rs6000/rs6000-cpus.def
+++ b/gcc/config/rs6000/rs6000-cpus.def
@@ -86,12 +86,6 @@
| OPTION_MASK_POWER10 \
| OTHER_POWER10_MASKS)
-/* Flags for a potential future processor that may or may not be delivered. */
-#define ISA_FUTURE_MASKS (ISA_3_1_MASKS_SERVER \
- | OPTION_MASK_BLOCK_OPS_VECTOR_PAIR \
- | OPTION_MASK_DENSE_MATH \
- | OPTION_MASK_FUTURE)
-
/* Flags that need to be turned off if -mno-power9-vector. */
#define OTHER_P9_VECTOR_MASKS (OPTION_MASK_FLOAT128_HW \
| OPTION_MASK_P9_MINMAX)
@@ -127,20 +121,17 @@
/* Mask of all options to set the default isa flags based on -mcpu=<xxx>. */
#define POWERPC_MASKS (OPTION_MASK_ALTIVEC \
- | OPTION_MASK_BLOCK_OPS_VECTOR_PAIR \
| OPTION_MASK_CMPB \
| OPTION_MASK_CRYPTO \
| OPTION_MASK_DFP \
| OPTION_MASK_DIRECT_MOVE \
| OPTION_MASK_DLMZB \
- | OPTION_MASK_DENSE_MATH \
| OPTION_MASK_EFFICIENT_UNALIGNED_VSX \
| OPTION_MASK_FLOAT128_HW \
| OPTION_MASK_FLOAT128_KEYWORD \
| OPTION_MASK_FPRND \
| OPTION_MASK_POWER10 \
| OPTION_MASK_P10_FUSION \
- | OPTION_MASK_FUTURE \
| OPTION_MASK_HTM \
| OPTION_MASK_ISEL \
| OPTION_MASK_MFCRF \
@@ -272,4 +263,3 @@ RS6000_CPU ("powerpc64", PROCESSOR_POWERPC64, OPTION_MASK_PPC_GFXOPT
RS6000_CPU ("powerpc64le", PROCESSOR_POWER8, MASK_POWERPC64
| ISA_2_7_MASKS_SERVER | OPTION_MASK_HTM)
RS6000_CPU ("rs64", PROCESSOR_RS64A, OPTION_MASK_PPC_GFXOPT | MASK_POWERPC64)
-RS6000_CPU ("future", PROCESSOR_FUTURE, MASK_POWERPC64 | ISA_FUTURE_MASKS)
diff --git a/gcc/config/rs6000/rs6000-opts.h b/gcc/config/rs6000/rs6000-opts.h
index f56f01d6fa5..8040cfdc06e 100644
--- a/gcc/config/rs6000/rs6000-opts.h
+++ b/gcc/config/rs6000/rs6000-opts.h
@@ -67,9 +67,7 @@ enum processor_type
PROCESSOR_MPCCORE,
PROCESSOR_CELL,
PROCESSOR_PPCA2,
- PROCESSOR_TITAN,
-
- PROCESSOR_FUTURE
+ PROCESSOR_TITAN
};
diff --git a/gcc/config/rs6000/rs6000-tables.opt b/gcc/config/rs6000/rs6000-tables.opt
index 3ff28e39f6c..b82f8205fa1 100644
--- a/gcc/config/rs6000/rs6000-tables.opt
+++ b/gcc/config/rs6000/rs6000-tables.opt
@@ -197,6 +197,3 @@ Enum(rs6000_cpu_opt_value) String(powerpc64le) Value(55)
EnumValue
Enum(rs6000_cpu_opt_value) String(rs64) Value(56)
-EnumValue
-Enum(rs6000_cpu_opt_value) String(future) Value(57)
-
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index c8f05f6f2d7..7e76c37fdab 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -290,8 +290,7 @@ enum rs6000_reg_type {
ALTIVEC_REG_TYPE,
FPR_REG_TYPE,
SPR_REG_TYPE,
- CR_REG_TYPE,
- DMR_REG_TYPE
+ CR_REG_TYPE
};
/* Map register class to register type. */
@@ -305,23 +304,22 @@ static enum rs6000_reg_type reg_class_to_reg_type[N_REG_CLASSES];
/* Register classes we care about in secondary reload or go if legitimate
- address. We only need to worry about GPR, FPR, Altivec, and DMR registers
- here, along an ANY field that is the OR of the 4 register classes. */
+ address. We only need to worry about GPR, FPR, and Altivec registers here,
+ along an ANY field that is the OR of the 3 register classes. */
enum rs6000_reload_reg_type {
RELOAD_REG_GPR, /* General purpose registers. */
RELOAD_REG_FPR, /* Traditional floating point regs. */
RELOAD_REG_VMX, /* Altivec (VMX) registers. */
- RELOAD_REG_DMR, /* DMR registers. */
- RELOAD_REG_ANY, /* OR of GPR/FPR/VMX/DMR masks. */
+ RELOAD_REG_ANY, /* OR of GPR, FPR, Altivec masks. */
N_RELOAD_REG
};
-/* For setting up register classes, loop through the 4 register classes mapping
+/* For setting up register classes, loop through the 3 register classes mapping
into real registers, and skip the ANY class, which is just an OR of the
bits. */
#define FIRST_RELOAD_REG_CLASS RELOAD_REG_GPR
-#define LAST_RELOAD_REG_CLASS RELOAD_REG_DMR
+#define LAST_RELOAD_REG_CLASS RELOAD_REG_VMX
/* Map reload register type to a register in the register class. */
struct reload_reg_map_type {
@@ -333,7 +331,6 @@ static const struct reload_reg_map_type reload_reg_map[N_RELOAD_REG] = {
{ "Gpr", FIRST_GPR_REGNO }, /* RELOAD_REG_GPR. */
{ "Fpr", FIRST_FPR_REGNO }, /* RELOAD_REG_FPR. */
{ "VMX", FIRST_ALTIVEC_REGNO }, /* RELOAD_REG_VMX. */
- { "DMR", FIRST_DMR_REGNO }, /* RELOAD_REG_DMR. */
{ "Any", -1 }, /* RELOAD_REG_ANY. */
};
@@ -1088,27 +1085,6 @@ struct processor_costs power10_cost = {
COSTS_N_INSNS (2), /* SF->DF convert */
};
-/* Instruction costs on Future processors. At the moment, this is a copy of
- the power10 costs, but it is expected to change over time.. */
-static const
-struct processor_costs future_cost = {
- COSTS_N_INSNS (2), /* mulsi */
- COSTS_N_INSNS (2), /* mulsi_const */
- COSTS_N_INSNS (2), /* mulsi_const9 */
- COSTS_N_INSNS (2), /* muldi */
- COSTS_N_INSNS (6), /* divsi */
- COSTS_N_INSNS (6), /* divdi */
- COSTS_N_INSNS (2), /* fp */
- COSTS_N_INSNS (2), /* dmul */
- COSTS_N_INSNS (11), /* sdiv */
- COSTS_N_INSNS (13), /* ddiv */
- 128, /* cache line size */
- 32, /* l1 cache */
- 512, /* l2 cache */
- 16, /* prefetch streams */
- COSTS_N_INSNS (2), /* SF->DF convert */
-};
-
/* Instruction costs on POWER A2 processors. */
static const
struct processor_costs ppca2_cost = {
@@ -1247,8 +1223,6 @@ char rs6000_reg_names[][8] =
"0", "1", "2", "3", "4", "5", "6", "7",
/* vrsave vscr sfp */
"vrsave", "vscr", "sfp",
- /* DMRs */
- "0", "1", "2", "3", "4", "5", "6", "7",
};
#ifdef TARGET_REGNAMES
@@ -1275,8 +1249,6 @@ static const char alt_reg_names[][8] =
"%cr0", "%cr1", "%cr2", "%cr3", "%cr4", "%cr5", "%cr6", "%cr7",
/* vrsave vscr sfp */
"vrsave", "vscr", "sfp",
- /* DMRs */
- "%dmr0", "%dmr1", "%dmr2", "%dmr3", "%dmr4", "%dmr5", "%dmr6", "%dmr7",
};
#endif
@@ -1848,9 +1820,6 @@ rs6000_hard_regno_nregs_internal (int regno, machine_mode mode)
else if (ALTIVEC_REGNO_P (regno))
reg_size = UNITS_PER_ALTIVEC_WORD;
- else if (DMR_REGNO_P (regno))
- reg_size = UNITS_PER_DMR_WORD;
-
else
reg_size = UNITS_PER_WORD;
@@ -1872,36 +1841,9 @@ rs6000_hard_regno_mode_ok_uncached (int regno, machine_mode mode)
if (mode == OOmode)
return (TARGET_MMA && VSX_REGNO_P (regno) && (regno & 1) == 0);
- /* On ISA 3.1 (power10), MMA accumulator modes need FPR registers divisible
- by 4.
-
- If dense math is enabled, allow all VSX registers plus the DMR registers.
- We need to make sure we don't cross between the boundary of FPRs and
- traditional Altiviec registers. */
+ /* MMA accumulator modes need FPR registers divisible by 4. */
if (mode == XOmode)
- {
- if (TARGET_MMA && !TARGET_DENSE_MATH)
- return (FP_REGNO_P (regno) && (regno & 3) == 0);
-
- else if (TARGET_DENSE_MATH)
- {
- if (DMR_REGNO_P (regno))
- return 1;
-
- if (FP_REGNO_P (regno))
- return ((regno & 1) == 0 && regno <= LAST_FPR_REGNO - 3);
-
- if (ALTIVEC_REGNO_P (regno))
- return ((regno & 1) == 0 && regno <= LAST_ALTIVEC_REGNO - 3);
- }
-
- else
- return 0;
- }
-
- /* No other types other than XOmode can go in DMRs. */
- if (DMR_REGNO_P (regno))
- return 0;
+ return (TARGET_MMA && FP_REGNO_P (regno) && (regno & 3) == 0);
/* PTImode can only go in GPRs. Quad word memory operations require even/odd
register combinations, and use PTImode where we need to deal with quad
@@ -2344,7 +2286,6 @@ rs6000_debug_reg_global (void)
rs6000_debug_reg_print (FIRST_ALTIVEC_REGNO,
LAST_ALTIVEC_REGNO,
"vs");
- rs6000_debug_reg_print (FIRST_DMR_REGNO, LAST_DMR_REGNO, "dmr");
rs6000_debug_reg_print (LR_REGNO, LR_REGNO, "lr");
rs6000_debug_reg_print (CTR_REGNO, CTR_REGNO, "ctr");
rs6000_debug_reg_print (CR0_REGNO, CR7_REGNO, "cr");
@@ -2365,7 +2306,6 @@ rs6000_debug_reg_global (void)
"wr reg_class = %s\n"
"wx reg_class = %s\n"
"wA reg_class = %s\n"
- "wD reg_class = %s\n"
"\n",
reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_d]],
reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_v]],
@@ -2373,8 +2313,7 @@ rs6000_debug_reg_global (void)
reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_we]],
reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wr]],
reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wx]],
- reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wA]],
- reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wD]]);
+ reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wA]]);
nl = "\n";
for (m = 0; m < NUM_MACHINE_MODES; ++m)
@@ -2671,21 +2610,6 @@ rs6000_setup_reg_addr_masks (void)
addr_mask = 0;
reg = reload_reg_map[rc].reg;
- /* Special case DMR registers. */
- if (rc == RELOAD_REG_DMR)
- {
- if (TARGET_DENSE_MATH && m2 == XOmode)
- {
- addr_mask = RELOAD_REG_VALID;
- reg_addr[m].addr_mask[rc] = addr_mask;
- any_addr_mask |= addr_mask;
- }
- else
- reg_addr[m].addr_mask[rc] = 0;
-
- continue;
- }
-
/* Can mode values go in the GPR/FPR/Altivec registers? */
if (reg >= 0 && rs6000_hard_regno_mode_ok_p[m][reg])
{
@@ -2781,8 +2705,8 @@ rs6000_setup_reg_addr_masks (void)
/* Vector pairs can do both indexed and offset loads if the
instructions are enabled, otherwise they can only do offset loads
- since it will be broken into two vector moves. Vector quads and
- 1,024 bit DMR values can only do offset loads. */
+ since it will be broken into two vector moves. Vector quads can
+ only do offset loads. */
else if ((addr_mask != 0) && TARGET_MMA
&& (m2 == OOmode || m2 == XOmode))
{
@@ -2836,9 +2760,6 @@ rs6000_init_hard_regno_mode_ok (bool global_init_p)
for (r = CR1_REGNO; r <= CR7_REGNO; ++r)
rs6000_regno_regclass[r] = CR_REGS;
- for (r = FIRST_DMR_REGNO; r <= LAST_DMR_REGNO; ++r)
- rs6000_regno_regclass[r] = DM_REGS;
-
rs6000_regno_regclass[LR_REGNO] = LINK_REGS;
rs6000_regno_regclass[CTR_REGNO] = CTR_REGS;
rs6000_regno_regclass[CA_REGNO] = NO_REGS;
@@ -2863,7 +2784,6 @@ rs6000_init_hard_regno_mode_ok (bool global_init_p)
reg_class_to_reg_type[(int)LINK_OR_CTR_REGS] = SPR_REG_TYPE;
reg_class_to_reg_type[(int)CR_REGS] = CR_REG_TYPE;
reg_class_to_reg_type[(int)CR0_REGS] = CR_REG_TYPE;
- reg_class_to_reg_type[(int)DM_REGS] = DMR_REG_TYPE;
if (TARGET_VSX)
{
@@ -3050,13 +2970,6 @@ rs6000_init_hard_regno_mode_ok (bool global_init_p)
if (TARGET_DIRECT_MOVE_128)
rs6000_constraints[RS6000_CONSTRAINT_we] = VSX_REGS;
- /* Support for the accumulator registers, either FPR registers (aka original
- mma) or DMR registers (dense math). */
- if (TARGET_DENSE_MATH)
- rs6000_constraints[RS6000_CONSTRAINT_wD] = DM_REGS;
- else if (TARGET_MMA)
- rs6000_constraints[RS6000_CONSTRAINT_wD] = FLOAT_REGS;
-
/* Set up the reload helper and direct move functions. */
if (TARGET_VSX || TARGET_ALTIVEC)
{
@@ -4507,14 +4420,6 @@ rs6000_option_override_internal (bool global_init_p)
if (!TARGET_PCREL && TARGET_PCREL_OPT)
rs6000_isa_flags &= ~OPTION_MASK_PCREL_OPT;
- /* Dense math requires MMA. */
- if (TARGET_DENSE_MATH && !TARGET_MMA)
- {
- if ((rs6000_isa_flags_explicit & OPTION_MASK_DENSE_MATH) != 0)
- error ("%qs requires %qs", "-mdense-math", "-mmma");
- rs6000_isa_flags &= ~OPTION_MASK_DENSE_MATH;
- }
-
if (TARGET_DEBUG_REG || TARGET_DEBUG_TARGET)
rs6000_print_isa_options (stderr, 0, "after subtarget", rs6000_isa_flags);
@@ -4525,7 +4430,6 @@ rs6000_option_override_internal (bool global_init_p)
&& rs6000_tune != PROCESSOR_POWER8
&& rs6000_tune != PROCESSOR_POWER9
&& rs6000_tune != PROCESSOR_POWER10
- && rs6000_tune != PROCESSOR_FUTURE
&& rs6000_tune != PROCESSOR_PPCA2
&& rs6000_tune != PROCESSOR_CELL
&& rs6000_tune != PROCESSOR_PPC476);
@@ -4540,7 +4444,6 @@ rs6000_option_override_internal (bool global_init_p)
|| rs6000_tune == PROCESSOR_POWER8
|| rs6000_tune == PROCESSOR_POWER9
|| rs6000_tune == PROCESSOR_POWER10
- || rs6000_tune == PROCESSOR_FUTURE
|| rs6000_tune == PROCESSOR_PPCE500MC
|| rs6000_tune == PROCESSOR_PPCE500MC64
|| rs6000_tune == PROCESSOR_PPCE5500
@@ -4843,10 +4746,6 @@ rs6000_option_override_internal (bool global_init_p)
rs6000_cost = &power10_cost;
break;
- case PROCESSOR_FUTURE:
- rs6000_cost = &future_cost;
- break;
-
case PROCESSOR_PPCA2:
rs6000_cost = &ppca2_cost;
break;
@@ -6003,8 +5902,6 @@ rs6000_machine_from_flags (void)
/* Disable the flags that should never influence the .machine selection. */
flags &= ~(OPTION_MASK_PPC_GFXOPT | OPTION_MASK_PPC_GPOPT | OPTION_MASK_ISEL);
- if ((flags & (ISA_FUTURE_MASKS & ~ISA_3_1_MASKS_SERVER)) != 0)
- return "future";
if ((flags & (ISA_3_1_MASKS_SERVER & ~ISA_3_0_MASKS_SERVER)) != 0)
return "power10";
if ((flags & (ISA_3_0_MASKS_SERVER & ~ISA_2_7_MASKS_SERVER)) != 0)
@@ -10216,7 +10113,6 @@ rs6000_reassociation_width (unsigned int opc ATTRIBUTE_UNUSED,
case PROCESSOR_POWER8:
case PROCESSOR_POWER9:
case PROCESSOR_POWER10:
- case PROCESSOR_FUTURE:
if (DECIMAL_FLOAT_MODE_P (mode))
return 1;
if (VECTOR_MODE_P (mode))
@@ -12128,11 +12024,6 @@ rs6000_secondary_reload_memory (rtx addr,
addr_mask = (reg_addr[mode].addr_mask[RELOAD_REG_VMX]
& ~RELOAD_REG_AND_M16);
- /* DMR registers use VSX registers, and need to generate some extra
- instructions. */
- else if (rclass == DM_REGS)
- return 2;
-
/* If the register allocator hasn't made up its mind yet on the register
class to use, settle on defaults to use. */
else if (rclass == NO_REGS)
@@ -12461,13 +12352,6 @@ rs6000_secondary_reload_simple_move (enum rs6000_reg_type to_type,
|| (to_type == SPR_REG_TYPE && from_type == GPR_REG_TYPE)))
return true;
- /* We can transfer between VSX registers and DMR registers without needing
- extra registers. */
- if (TARGET_DENSE_MATH && mode == XOmode
- && ((to_type == DMR_REG_TYPE && from_type == VSX_REG_TYPE)
- || (to_type == VSX_REG_TYPE && from_type == DMR_REG_TYPE)))
- return true;
-
return false;
}
@@ -13162,10 +13046,6 @@ rs6000_preferred_reload_class (rtx x, enum reg_class rclass)
machine_mode mode = GET_MODE (x);
bool is_constant = CONSTANT_P (x);
- /* DMR registers can't be loaded or stored. */
- if (rclass == DM_REGS)
- return NO_REGS;
-
/* If a mode can't go in FPR/ALTIVEC/VSX registers, don't return a preferred
reload class for it. */
if ((rclass == ALTIVEC_REGS || rclass == VSX_REGS)
@@ -13262,7 +13142,7 @@ rs6000_preferred_reload_class (rtx x, enum reg_class rclass)
return VSX_REGS;
if (mode == XOmode)
- return TARGET_DENSE_MATH ? VSX_REGS : FLOAT_REGS;
+ return FLOAT_REGS;
if (GET_MODE_CLASS (mode) == MODE_INT)
return GENERAL_REGS;
@@ -13387,11 +13267,6 @@ rs6000_secondary_reload_class (enum reg_class rclass, machine_mode mode,
else
regno = -1;
- /* DMR registers don't have loads or stores. We have to go through the VSX
- registers to load XOmode (vector quad). */
- if (TARGET_DENSE_MATH && rclass == DM_REGS)
- return VSX_REGS;
-
/* If we have VSX register moves, prefer moving scalar values between
Altivec registers and GPR by going via an FPR (and then via memory)
instead of reloading the secondary memory address for Altivec moves. */
@@ -13905,19 +13780,8 @@ print_operand (FILE *file, rtx x, int code)
output_operand. */
case 'A':
- /* Write the MMA accumulator number associated with VSX register X. On
- dense math systems, only allow DMR accumulators, not accumulators
- overlapping with the FPR registers. */
- if (!REG_P (x))
- output_operand_lossage ("invalid %%A value");
- else if (TARGET_DENSE_MATH)
- {
- if (DMR_REGNO_P (REGNO (x)))
- fprintf (file, "%d", REGNO (x) - FIRST_DMR_REGNO);
- else
- output_operand_lossage ("%%A operand is not a DMR");
- }
- else if (!FP_REGNO_P (REGNO (x)) || (REGNO (x) % 4) != 0)
+ /* Write the MMA accumulator number associated with VSX register X. */
+ if (!REG_P (x) || !FP_REGNO_P (REGNO (x)) || (REGNO (x) % 4) != 0)
output_operand_lossage ("invalid %%A value");
else
fprintf (file, "%d", (REGNO (x) - FIRST_FPR_REGNO) / 4);
@@ -18048,8 +17912,7 @@ rs6000_adjust_cost (rtx_insn *insn, int dep_type, rtx_insn *dep_insn, int cost,
/* Separate a load from a narrower, dependent store. */
if ((rs6000_sched_groups || rs6000_tune == PROCESSOR_POWER9
- || rs6000_tune == PROCESSOR_POWER10
- || rs6000_tune == PROCESSOR_FUTURE)
+ || rs6000_tune == PROCESSOR_POWER10)
&& GET_CODE (PATTERN (insn)) == SET
&& GET_CODE (PATTERN (dep_insn)) == SET
&& MEM_P (XEXP (PATTERN (insn), 1))
@@ -18088,7 +17951,6 @@ rs6000_adjust_cost (rtx_insn *insn, int dep_type, rtx_insn *dep_insn, int cost,
|| rs6000_tune == PROCESSOR_POWER8
|| rs6000_tune == PROCESSOR_POWER9
|| rs6000_tune == PROCESSOR_POWER10
- || rs6000_tune == PROCESSOR_FUTURE
|| rs6000_tune == PROCESSOR_CELL)
&& recog_memoized (dep_insn)
&& (INSN_CODE (dep_insn) >= 0))
@@ -18663,7 +18525,6 @@ rs6000_issue_rate (void)
case PROCESSOR_POWER9:
return 6;
case PROCESSOR_POWER10:
- case PROCESSOR_FUTURE:
return 8;
default:
return 1;
@@ -19379,10 +19240,8 @@ rs6000_sched_reorder (FILE *dump ATTRIBUTE_UNUSED, int sched_verbose,
if (rs6000_tune == PROCESSOR_POWER6)
load_store_pendulum = 0;
- /* Do Power10 dependent reordering. For now, assume "future" has the same
- dependent reordering as power10. */
- if ((rs6000_tune == PROCESSOR_POWER10
- || rs6000_tune == PROCESSOR_FUTURE) && last_scheduled_insn)
+ /* Do Power10 dependent reordering. */
+ if (rs6000_tune == PROCESSOR_POWER10 && last_scheduled_insn)
power10_sched_reorder (ready, n_ready - 1);
return rs6000_issue_rate ();
@@ -19406,10 +19265,8 @@ rs6000_sched_reorder2 (FILE *dump, int sched_verbose, rtx_insn **ready,
&& recog_memoized (last_scheduled_insn) >= 0)
return power9_sched_reorder2 (ready, *pn_ready - 1);
- /* Do Power10 dependent reordering. For now, assume "future" has the same
- dependent reordering as power10. */
- if ((rs6000_tune == PROCESSOR_POWER10
- || rs6000_tune == PROCESSOR_FUTURE) && last_scheduled_insn)
+ /* Do Power10 dependent reordering. */
+ if (rs6000_tune == PROCESSOR_POWER10 && last_scheduled_insn)
return power10_sched_reorder (ready, *pn_ready - 1);
return cached_can_issue_more;
@@ -22576,31 +22433,6 @@ rs6000_debug_address_cost (rtx x, machine_mode mode,
}
-/* Subroutine to determine the move cost of dense math registers. If we are
- moving to/from VSX_REGISTER registers, the cost is either 1 move (for
- 512-bit accumulators) or 2 moves (for 1,024 dmr registers). If we are
- moving to anything else like GPR registers, make the cost very high. */
-
-static int
-rs6000_dmr_register_move_cost (machine_mode mode, reg_class_t rclass)
-{
- const int reg_move_base = 2;
- HARD_REG_SET vsx_set = (reg_class_contents[rclass]
- & reg_class_contents[VSX_REGS]);
-
- if (TARGET_DENSE_MATH && !hard_reg_set_empty_p (vsx_set))
- {
- /* __vector_quad (i.e. XOmode) is tranfered in 1 instruction. */
- if (mode == XOmode)
- return reg_move_base;
-
- else
- return reg_move_base * 2 * hard_regno_nregs (FIRST_DMR_REGNO, mode);
- }
-
- return 1000 * 2 * hard_regno_nregs (FIRST_DMR_REGNO, mode);
-}
-
/* A C expression returning the cost of moving data from a register of class
CLASS1 to one of CLASS2. */
@@ -22614,28 +22446,17 @@ rs6000_register_move_cost (machine_mode mode,
if (TARGET_DEBUG_COST)
dbg_cost_ctrl++;
- HARD_REG_SET to_vsx, from_vsx;
- to_vsx = reg_class_contents[to] & reg_class_contents[VSX_REGS];
- from_vsx = reg_class_contents[from] & reg_class_contents[VSX_REGS];
-
- /* Special case DMR registers, that can only move to/from VSX registers. */
- if (from == DM_REGS && to == DM_REGS)
- ret = 2 * hard_regno_nregs (FIRST_DMR_REGNO, mode);
-
- else if (from == DM_REGS)
- ret = rs6000_dmr_register_move_cost (mode, to);
-
- else if (to == DM_REGS)
- ret = rs6000_dmr_register_move_cost (mode, from);
-
/* If we have VSX, we can easily move between FPR or Altivec registers,
otherwise we can only easily move within classes.
Do this first so we give best-case answers for union classes
containing both gprs and vsx regs. */
- else if (!hard_reg_set_empty_p (to_vsx)
- && !hard_reg_set_empty_p (from_vsx)
- && (TARGET_VSX
- || hard_reg_set_intersect_p (to_vsx, from_vsx)))
+ HARD_REG_SET to_vsx, from_vsx;
+ to_vsx = reg_class_contents[to] & reg_class_contents[VSX_REGS];
+ from_vsx = reg_class_contents[from] & reg_class_contents[VSX_REGS];
+ if (!hard_reg_set_empty_p (to_vsx)
+ && !hard_reg_set_empty_p (from_vsx)
+ && (TARGET_VSX
+ || hard_reg_set_intersect_p (to_vsx, from_vsx)))
{
int reg = FIRST_FPR_REGNO;
if (TARGET_VSX
@@ -22660,8 +22481,7 @@ rs6000_register_move_cost (machine_mode mode,
allocation a move within the same class might turn
out to be a nop. */
if (rs6000_tune == PROCESSOR_POWER9
- || rs6000_tune == PROCESSOR_POWER10
- || rs6000_tune == PROCESSOR_FUTURE)
+ || rs6000_tune == PROCESSOR_POWER10)
ret = 3 * hard_regno_nregs (FIRST_GPR_REGNO, mode);
else
ret = 4 * hard_regno_nregs (FIRST_GPR_REGNO, mode);
@@ -22731,9 +22551,6 @@ rs6000_memory_move_cost (machine_mode mode, reg_class_t rclass,
ret = 4 * hard_regno_nregs (32, mode);
else if (reg_classes_intersect_p (rclass, ALTIVEC_REGS))
ret = 4 * hard_regno_nregs (FIRST_ALTIVEC_REGNO, mode);
- else if (reg_classes_intersect_p (rclass, DM_REGS))
- ret = (rs6000_dmr_register_move_cost (mode, VSX_REGS)
- + rs6000_memory_move_cost (mode, VSX_REGS, false));
else
ret = 4 + rs6000_register_move_cost (mode, rclass, GENERAL_REGS);
@@ -23942,8 +23759,6 @@ rs6000_compute_pressure_classes (enum reg_class *pressure_classes)
if (TARGET_HARD_FLOAT)
pressure_classes[n++] = FLOAT_REGS;
}
- if (TARGET_DENSE_MATH)
- pressure_classes[n++] = DM_REGS;
pressure_classes[n++] = CR_REGS;
pressure_classes[n++] = SPECIAL_REGS;
@@ -24108,10 +23923,6 @@ rs6000_debugger_regno (unsigned int regno, unsigned int format)
return 67;
if (regno == 64)
return 64;
- /* XXX: This is a guess. The GCC register number for FIRST_DMR_REGNO is 111,
- but the frame pointer regnum uses that. */
- if (DMR_REGNO_P (regno))
- return regno - FIRST_DMR_REGNO + 112;
gcc_unreachable ();
}
@@ -24322,14 +24133,12 @@ static struct rs6000_opt_mask const rs6000_opt_masks[] =
{ "crypto", OPTION_MASK_CRYPTO, false, true },
{ "direct-move", OPTION_MASK_DIRECT_MOVE, false, true },
{ "dlmzb", OPTION_MASK_DLMZB, false, true },
- { "dense-math", OPTION_MASK_DENSE_MATH, false, true },
{ "efficient-unaligned-vsx", OPTION_MASK_EFFICIENT_UNALIGNED_VSX,
false, true },
{ "float128", OPTION_MASK_FLOAT128_KEYWORD, false, true },
{ "float128-hardware", OPTION_MASK_FLOAT128_HW, false, true },
{ "fprnd", OPTION_MASK_FPRND, false, true },
{ "power10", OPTION_MASK_POWER10, false, true },
- { "future", OPTION_MASK_FUTURE, false, true },
{ "hard-dfp", OPTION_MASK_DFP, false, true },
{ "htm", OPTION_MASK_HTM, false, true },
{ "isel", OPTION_MASK_ISEL, false, true },
@@ -27361,7 +27170,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are reading an accumulator register, we have to
deprime it before we can access it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH
+ if (TARGET_MMA
&& GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
emit_insn (gen_mma_xxmfacc (src, src));
@@ -27393,9 +27202,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
emit_insn (gen_rtx_SET (dst2, src2));
}
- /* If we are writing an accumulator register that overlaps with the
- FPR registers, we have to prime it after we've written it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH
+ /* If we are writing an accumulator register, we have to
+ prime it after we've written it. */
+ if (TARGET_MMA
&& GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
emit_insn (gen_mma_xxmtacc (dst, dst));
@@ -27409,9 +27218,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
|| XINT (src, 1) == UNSPECV_MMA_ASSEMBLE);
gcc_assert (REG_P (dst));
if (GET_MODE (src) == XOmode)
- gcc_assert ((TARGET_DENSE_MATH
- ? VSX_REGNO_P (REGNO (dst))
- : FP_REGNO_P (REGNO (dst))));
+ gcc_assert (FP_REGNO_P (REGNO (dst)));
if (GET_MODE (src) == OOmode)
gcc_assert (VSX_REGNO_P (REGNO (dst)));
@@ -27464,9 +27271,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
emit_insn (gen_rtx_SET (dst_i, op));
}
- /* On systems without dense math where accumulators overlap with the
- vector registers, we have to prime it after we've written it. */
- if (GET_MODE (src) == XOmode && !TARGET_DENSE_MATH)
+ /* We are writing an accumulator register, so we have to
+ prime it after we've written it. */
+ if (GET_MODE (src) == XOmode)
emit_insn (gen_mma_xxmtacc (dst, dst));
return;
@@ -27477,9 +27284,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
if (REG_P (src) && REG_P (dst) && (REGNO (src) < REGNO (dst)))
{
- /* If we are reading an accumulator register and we don't have dense
- math, we have to deprime it before we can access it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH
+ /* If we are reading an accumulator register, we have to
+ deprime it before we can access it. */
+ if (TARGET_MMA
&& GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
emit_insn (gen_mma_xxmfacc (src, src));
@@ -27507,7 +27314,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are writing an accumulator register, we have to
prime it after we've written it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH
+ if (TARGET_MMA
&& GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
emit_insn (gen_mma_xxmtacc (dst, dst));
}
@@ -27644,7 +27451,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are reading an accumulator register, we have to
deprime it before we can access it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (src)
+ if (TARGET_MMA && REG_P (src)
&& GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
emit_insn (gen_mma_xxmfacc (src, src));
@@ -27676,7 +27483,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are writing an accumulator register, we have to
prime it after we've written it. */
- if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (dst)
+ if (TARGET_MMA && REG_P (dst)
&& GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
emit_insn (gen_mma_xxmtacc (dst, dst));
diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index c034b9ed179..3503614efbd 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -163,7 +163,6 @@
mcpu=e5500: -me5500; \
mcpu=e6500: -me6500; \
mcpu=titan: -mtitan; \
- mcpu=future: -mfuture; \
!mcpu*: %{mpower9-vector: -mpower9; \
mpower8-vector|mcrypto|mdirect-move|mhtm: -mpower8; \
mvsx: -mpower7; \
@@ -662,7 +661,6 @@ extern unsigned char rs6000_recip_bits[];
#define UNITS_PER_FP_WORD 8
#define UNITS_PER_ALTIVEC_WORD 16
#define UNITS_PER_VSX_WORD 16
-#define UNITS_PER_DMR_WORD 128
/* Type used for ptrdiff_t, as a string used in a declaration. */
#define PTRDIFF_TYPE "int"
@@ -790,7 +788,7 @@ enum data_align { align_abi, align_opt, align_both };
Another pseudo (not included in DWARF_FRAME_REGISTERS) is soft frame
pointer, which is eventually eliminated in favor of SP or FP. */
-#define FIRST_PSEUDO_REGISTER 119
+#define FIRST_PSEUDO_REGISTER 111
/* Use standard DWARF numbering for DWARF debugging information. */
#define DEBUGGER_REGNO(REGNO) rs6000_debugger_regno ((REGNO), 0)
@@ -827,9 +825,7 @@ enum data_align { align_abi, align_opt, align_both };
/* cr0..cr7 */ \
0, 0, 0, 0, 0, 0, 0, 0, \
/* vrsave vscr sfp */ \
- 1, 1, 1, \
- /* DMR registers. */ \
- 0, 0, 0, 0, 0, 0, 0, 0 \
+ 1, 1, 1 \
}
/* Like `CALL_USED_REGISTERS' except this macro doesn't require that
@@ -853,9 +849,7 @@ enum data_align { align_abi, align_opt, align_both };
/* cr0..cr7 */ \
1, 1, 0, 0, 0, 1, 1, 1, \
/* vrsave vscr sfp */ \
- 0, 0, 0, \
- /* DMR registers. */ \
- 0, 0, 0, 0, 0, 0, 0, 0 \
+ 0, 0, 0 \
}
#define TOTAL_ALTIVEC_REGS (LAST_ALTIVEC_REGNO - FIRST_ALTIVEC_REGNO + 1)
@@ -892,7 +886,6 @@ enum data_align { align_abi, align_opt, align_both };
v2 (not saved; incoming vector arg reg; return value)
v19 - v14 (not saved or used for anything)
v31 - v20 (saved; order given to save least number)
- dmr0 - dmr7 (not saved)
vrsave, vscr (fixed)
sfp (fixed)
*/
@@ -935,9 +928,6 @@ enum data_align { align_abi, align_opt, align_both };
66, \
83, 82, 81, 80, 79, 78, \
95, 94, 93, 92, 91, 90, 89, 88, 87, 86, 85, 84, \
- /* DMR registers. */ \
- 111, 112, 113, 114, 115, 116, 117, 118, \
- /* Vrsave, vscr, sfp. */ \
108, 109, \
110 \
}
@@ -964,9 +954,6 @@ enum data_align { align_abi, align_opt, align_both };
/* True if register is a VSX register. */
#define VSX_REGNO_P(N) (FP_REGNO_P (N) || ALTIVEC_REGNO_P (N))
-/* True if register is a DMR register. */
-#define DMR_REGNO_P(N) ((N) >= FIRST_DMR_REGNO && (N) <= LAST_DMR_REGNO)
-
/* Alternate name for any vector register supporting floating point, no matter
which instruction set(s) are available. */
#define VFLOAT_REGNO_P(N) \
@@ -1102,7 +1089,6 @@ enum reg_class
FLOAT_REGS,
ALTIVEC_REGS,
VSX_REGS,
- DM_REGS,
VRSAVE_REGS,
VSCR_REGS,
GEN_OR_FLOAT_REGS,
@@ -1132,7 +1118,6 @@ enum reg_class
"FLOAT_REGS", \
"ALTIVEC_REGS", \
"VSX_REGS", \
- "DM_REGS", \
"VRSAVE_REGS", \
"VSCR_REGS", \
"GEN_OR_FLOAT_REGS", \
@@ -1167,8 +1152,6 @@ enum reg_class
{ 0x00000000, 0x00000000, 0xffffffff, 0x00000000 }, \
/* VSX_REGS. */ \
{ 0x00000000, 0xffffffff, 0xffffffff, 0x00000000 }, \
- /* DM_REGS. */ \
- { 0x00000000, 0x00000000, 0x00000000, 0x007f8000 }, \
/* VRSAVE_REGS. */ \
{ 0x00000000, 0x00000000, 0x00000000, 0x00001000 }, \
/* VSCR_REGS. */ \
@@ -1196,7 +1179,7 @@ enum reg_class
/* CA_REGS. */ \
{ 0x00000000, 0x00000000, 0x00000000, 0x00000004 }, \
/* ALL_REGS. */ \
- { 0xffffffff, 0xffffffff, 0xffffffff, 0x007fffff } \
+ { 0xffffffff, 0xffffffff, 0xffffffff, 0x00007fff } \
}
/* The same information, inverted:
@@ -1220,7 +1203,6 @@ enum r6000_reg_class_enum {
RS6000_CONSTRAINT_wr, /* GPR register if 64-bit */
RS6000_CONSTRAINT_wx, /* FPR register for STFIWX */
RS6000_CONSTRAINT_wA, /* BASE_REGS if 64-bit. */
- RS6000_CONSTRAINT_wD, /* Accumulator regs if MMA/Dense Math. */
RS6000_CONSTRAINT_MAX
};
@@ -2094,16 +2076,7 @@ extern char rs6000_reg_names[][8]; /* register names (0 vs. %r0). */
&rs6000_reg_names[108][0], /* vrsave */ \
&rs6000_reg_names[109][0], /* vscr */ \
\
- &rs6000_reg_names[110][0], /* sfp */ \
- \
- &rs6000_reg_names[111][0], /* dmr0 */ \
- &rs6000_reg_names[112][0], /* dmr1 */ \
- &rs6000_reg_names[113][0], /* dmr2 */ \
- &rs6000_reg_names[114][0], /* dmr3 */ \
- &rs6000_reg_names[115][0], /* dmr4 */ \
- &rs6000_reg_names[116][0], /* dmr5 */ \
- &rs6000_reg_names[117][0], /* dmr6 */ \
- &rs6000_reg_names[118][0], /* dmr7 */ \
+ &rs6000_reg_names[110][0] /* sfp */ \
}
/* Table of additional register names to use in user input. */
@@ -2157,8 +2130,6 @@ extern char rs6000_reg_names[][8]; /* register names (0 vs. %r0). */
{"vs52", 84}, {"vs53", 85}, {"vs54", 86}, {"vs55", 87}, \
{"vs56", 88}, {"vs57", 89}, {"vs58", 90}, {"vs59", 91}, \
{"vs60", 92}, {"vs61", 93}, {"vs62", 94}, {"vs63", 95}, \
- {"dmr0", 111}, {"dmr1", 112}, {"dmr2", 113}, {"dmr3", 114}, \
- {"dmr4", 115}, {"dmr5", 116}, {"dmr6", 117}, {"dmr7", 118}, \
}
/* This is how to output an element of a case-vector that is relative. */
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index ee7651d9b43..4a7812fa592 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -51,8 +51,6 @@
(VRSAVE_REGNO 108)
(VSCR_REGNO 109)
(FRAME_POINTER_REGNUM 110)
- (FIRST_DMR_REGNO 111)
- (LAST_DMR_REGNO 118)
])
;;
@@ -352,11 +350,11 @@
ppc403,ppc405,ppc440,ppc476,
ppc8540,ppc8548,ppce300c2,ppce300c3,ppce500mc,ppce500mc64,ppce5500,ppce6500,
power4,power5,power6,power7,power8,power9,power10,
- rs64a,mpccore,cell,ppca2,titan,future"
+ rs64a,mpccore,cell,ppca2,titan"
(const (symbol_ref "(enum attr_cpu) rs6000_tune")))
;; The ISA we implement.
-(define_attr "isa" "any,p5,p6,p7,p7v,p8v,p9,p9v,p9kf,p9tf,p10,dm,not_dm"
+(define_attr "isa" "any,p5,p6,p7,p7v,p8v,p9,p9v,p9kf,p9tf,p10"
(const_string "any"))
;; Is this alternative enabled for the current CPU/ISA/etc.?
@@ -404,14 +402,6 @@
(and (eq_attr "isa" "p10")
(match_test "TARGET_POWER10"))
(const_int 1)
-
- (and (eq_attr "isa" "dm")
- (match_test "TARGET_DENSE_MATH"))
- (const_int 1)
-
- (and (eq_attr "isa" "not_dm")
- (match_test "!TARGET_DENSE_MATH"))
- (const_int 1)
] (const_int 0)))
;; If this instruction is microcoded on the CELL processor
diff --git a/gcc/config/rs6000/rs6000.opt b/gcc/config/rs6000/rs6000.opt
index e45faf4a4ef..bde6d3ff664 100644
--- a/gcc/config/rs6000/rs6000.opt
+++ b/gcc/config/rs6000/rs6000.opt
@@ -620,14 +620,6 @@ mieee128-constant
Target Var(TARGET_IEEE128_CONSTANT) Init(1) Save
Generate (do not generate) code that uses the LXVKQ instruction.
-mfuture
-Target Undocumented Mask(FUTURE) Var(rs6000_isa_flags)
-Generate (do not generate) future instructions.
-
-mdense-math
-Target Undocumented Mask(DENSE_MATH) Var(rs6000_isa_flags)
-Generate (do not generate) dense math instructions.
-
; Documented parameters
-param=rs6000-vect-unroll-limit=
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 696f941c1c5..1eda0e0396b 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -29209,7 +29209,7 @@ Supported values for @var{cpu_type} are @samp{401}, @samp{403},
@samp{titan}, @samp{power3}, @samp{power4}, @samp{power5}, @samp{power5+},
@samp{power6}, @samp{power6x}, @samp{power7}, @samp{power8},
@samp{power9}, @samp{power10}, @samp{powerpc}, @samp{powerpc64},
-@samp{powerpc64le}, @samp{rs64}, @samp{future}, and @samp{native}.
+@samp{powerpc64le}, @samp{rs64}, and @samp{native}.
@option{-mcpu=powerpc}, @option{-mcpu=powerpc64}, and
@option{-mcpu=powerpc64le} specify pure 32-bit PowerPC (either
diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi
index f8a02b25772..7235d34c4b3 100644
--- a/gcc/doc/md.texi
+++ b/gcc/doc/md.texi
@@ -3264,13 +3264,6 @@ Like @code{d}, if @option{-mpowerpc-gfxopt} is used; otherwise, @code{NO_REGS}.
@item wA
Like @code{b}, if @option{-mpowerpc64} is used; otherwise, @code{NO_REGS}.
-@item wD
-Accumulator register if @option{-mma} is used; otherwise,
-@code{NO_REGS}. If @option{-mdense-math} is used, the accumulator
-register will be in the dense match register set. If
-@option{-mno-dense-math} is used, the accumulator register will
-overlap with the VSX vector registers 0..31.
-
@item wB
Signed 5-bit constant integer that can be loaded into an Altivec register.
diff --git a/gcc/testsuite/gcc.target/powerpc/dm-double-test.c b/gcc/testsuite/gcc.target/powerpc/dm-double-test.c
deleted file mode 100644
index eaa01426c78..00000000000
--- a/gcc/testsuite/gcc.target/powerpc/dm-double-test.c
+++ /dev/null
@@ -1,194 +0,0 @@
-/* Test derived from mma-double-1.c, modified for dense math. */
-/* { dg-do compile } */
-/* { dg-require-effective-target powerpc_dense_math_ok } */
-/* { dg-options "-mdejagnu-cpu=future -O2" } */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <altivec.h>
-
-typedef unsigned char vec_t __attribute__ ((vector_size (16)));
-typedef double v4sf_t __attribute__ ((vector_size (16)));
-#define SAVE_ACC(ACC, ldc, J) \
- __builtin_mma_disassemble_acc (result, ACC); \
- rowC = (v4sf_t *) &CO[0*ldc+J]; \
- rowC[0] += result[0]; \
- rowC = (v4sf_t *) &CO[1*ldc+J]; \
- rowC[0] += result[1]; \
- rowC = (v4sf_t *) &CO[2*ldc+J]; \
- rowC[0] += result[2]; \
- rowC = (v4sf_t *) &CO[3*ldc+J]; \
- rowC[0] += result[3];
-
-void
-DM (int m, int n, int k, double *A, double *B, double *C)
-{
- __vector_quad acc0, acc1, acc2, acc3, acc4, acc5, acc6, acc7;
- v4sf_t result[4];
- v4sf_t *rowC;
- for (int l = 0; l < n; l += 4)
- {
- double *CO;
- double *AO;
- AO = A;
- CO = C;
- C += m * 4;
- for (int j = 0; j < m; j += 16)
- {
- double *BO = B;
- __builtin_mma_xxsetaccz (&acc0);
- __builtin_mma_xxsetaccz (&acc1);
- __builtin_mma_xxsetaccz (&acc2);
- __builtin_mma_xxsetaccz (&acc3);
- __builtin_mma_xxsetaccz (&acc4);
- __builtin_mma_xxsetaccz (&acc5);
- __builtin_mma_xxsetaccz (&acc6);
- __builtin_mma_xxsetaccz (&acc7);
- unsigned long i;
-
- for (i = 0; i < k; i++)
- {
- vec_t *rowA = (vec_t *) & AO[i * 16];
- __vector_pair rowB;
- vec_t *rb = (vec_t *) & BO[i * 4];
- __builtin_mma_assemble_pair (&rowB, rb[1], rb[0]);
- __builtin_mma_xvf64gerpp (&acc0, rowB, rowA[0]);
- __builtin_mma_xvf64gerpp (&acc1, rowB, rowA[1]);
- __builtin_mma_xvf64gerpp (&acc2, rowB, rowA[2]);
- __builtin_mma_xvf64gerpp (&acc3, rowB, rowA[3]);
- __builtin_mma_xvf64gerpp (&acc4, rowB, rowA[4]);
- __builtin_mma_xvf64gerpp (&acc5, rowB, rowA[5]);
- __builtin_mma_xvf64gerpp (&acc6, rowB, rowA[6]);
- __builtin_mma_xvf64gerpp (&acc7, rowB, rowA[7]);
- }
- SAVE_ACC (&acc0, m, 0);
- SAVE_ACC (&acc2, m, 4);
- SAVE_ACC (&acc1, m, 2);
- SAVE_ACC (&acc3, m, 6);
- SAVE_ACC (&acc4, m, 8);
- SAVE_ACC (&acc6, m, 12);
- SAVE_ACC (&acc5, m, 10);
- SAVE_ACC (&acc7, m, 14);
- AO += k * 16;
- BO += k * 4;
- CO += 16;
- }
- B += k * 4;
- }
-}
-
-void
-init (double *matrix, int row, int column)
-{
- for (int j = 0; j < column; j++)
- {
- for (int i = 0; i < row; i++)
- {
- matrix[j * row + i] = (i * 16 + 2 + j) / 0.123;
- }
- }
-}
-
-void
-init0 (double *matrix, double *matrix1, int row, int column)
-{
- for (int j = 0; j < column; j++)
- for (int i = 0; i < row; i++)
- matrix[j * row + i] = matrix1[j * row + i] = 0;
-}
-
-
-void
-print (const char *name, const double *matrix, int row, int column)
-{
- printf ("Matrix %s has %d rows and %d columns:\n", name, row, column);
- for (int i = 0; i < row; i++)
- {
- for (int j = 0; j < column; j++)
- {
- printf ("%f ", matrix[j * row + i]);
- }
- printf ("\n");
- }
- printf ("\n");
-}
-
-int
-main (int argc, char *argv[])
-{
- int rowsA, colsB, common;
- int i, j, k;
- int ret = 0;
-
- for (int t = 16; t <= 128; t += 16)
- {
- for (int t1 = 4; t1 <= 16; t1 += 4)
- {
- rowsA = t;
- colsB = t1;
- common = 1;
- /* printf ("Running test for rows = %d,cols = %d\n", t, t1); */
- double A[rowsA * common];
- double B[common * colsB];
- double C[rowsA * colsB];
- double D[rowsA * colsB];
-
-
- init (A, rowsA, common);
- init (B, common, colsB);
- init0 (C, D, rowsA, colsB);
- DM (rowsA, colsB, common, A, B, C);
-
- for (i = 0; i < colsB; i++)
- {
- for (j = 0; j < rowsA; j++)
- {
- D[i * rowsA + j] = 0;
- for (k = 0; k < common; k++)
- {
- D[i * rowsA + j] +=
- A[k * rowsA + j] * B[k + common * i];
- }
- }
- }
- for (i = 0; i < colsB; i++)
- {
- for (j = 0; j < rowsA; j++)
- {
- for (k = 0; k < common; k++)
- {
- if (D[i * rowsA + j] != C[i * rowsA + j])
- {
- printf ("Error %d,%d,%d\n",i,j,k);
- ret++;
- }
- }
- }
- }
- if (ret)
- {
- print ("A", A, rowsA, common);
- print ("B", B, common, colsB);
- print ("C", C, rowsA, colsB);
- print ("D", D, rowsA, colsB);
- }
- }
- }
-
-#ifdef VERBOSE
- if (ret)
- printf ("DM double test fail: %d errors\n",ret);
- else
- printf ("DM double test success: 0 DM errors\n");
-#else
- if (ret)
- abort();
-#endif
-
- return ret;
-}
-
-/* { dg-final { scan-assembler {\mdmsetaccz\M} } } */
-/* { dg-final { scan-assembler {\mdmxvf64gerpp\M} } } */
-/* { dg-final { scan-assembler {\mdmxxextfdmr512\M} } } */
-
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2023-02-04 3:03 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-02-04 3:03 [gcc(refs/users/meissner/heads/dmf008)] Revert patches Michael Meissner
-- strict thread matches above, loose matches on Subject: below --
2023-02-03 19:25 Michael Meissner
2023-02-02 20:05 Michael Meissner
2023-02-02 19:55 Michael Meissner
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).