* [PATCH 2/2] PowerPC: Add ISA 3.1 IEEE 128-bit min, max, and cmove.
2020-07-01 22:20 ` [PATCH 1/2] PowerPC: Rename FP min/max/cmove functions Michael Meissner
@ 2020-07-01 22:20 ` Michael Meissner
2020-07-06 20:19 ` Segher Boessenkool
2020-07-06 19:04 ` [PATCH 1/2] PowerPC: Rename FP min/max/cmove functions Segher Boessenkool
1 sibling, 1 reply; 5+ messages in thread
From: Michael Meissner @ 2020-07-01 22:20 UTC (permalink / raw)
To: gcc-patches, Segher Boessenkool, David Edelsohn, Michael Meissner
Cc: Bill Schmidt
This patch adds support for the IEEE 128-bit floating point minimum, maximum,
and compare instructions generating a mask. These instructions were added in
ISA 3.1 (i.e. power10).
Compared to the last time I submitted the patches, I changed from using
-mcpu=future to -mcpu=power10. Along with the previous patch, I have done
bootstrap compilers with/without the pages and there were no regressions. I
did this on a little endian power9 system and a big endian power8 system. The
power8 system had support for both 32/64-bit. Can I check these patches into
the master branch?
gcc/
2020-06-30 Michael Meissner <meissner@linux.ibm.com>
* config/rs6000/rs6000.c (emit_fp_min_max_insn): Update comment.
(emit_fp_cmove_with_mask_xxsel): Update comment.
(rs6000_emit_cmove): Add support for IEEE 128-bit min, max, and
comparisons on ISA 3.1.
(rs6000_emit_minmax): Add support for IEEE 128-bit min/max on ISA
3.1.
* config/rs6000/rs6000.md (s<minmax><mode>3, IEEE128 iterator):
New insns for IEEE 128-bit min/max.
(mov<mode>cc, IEEE128 iterator): New insns for IEEE 128-bit
conditional move.
(mov<mode>cc_future, IEEE128 iterator): New insns for IEEE 128-bit
conditional move.
(mov<mode>cc_invert_future, IEEE128 iterator): New insns for IEEE
128-bit conditional move.
(fpmask<mode>, IEEE128 iterator): New insns for IEEE 128-bit
conditional move.
gcc/testsuite/
2020-06-30 Michael Meissner <meissner@linux.ibm.com>
* gcc.target/powerpc/float128-minmax-2.c: New test.
---
gcc/config/rs6000/rs6000.c | 23 +++-
gcc/config/rs6000/rs6000.md | 121 +++++++++++++++++++++
.../gcc.target/powerpc/float128-minmax-2.c | 70 ++++++++++++
3 files changed, 211 insertions(+), 3 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/powerpc/float128-minmax-2.c
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 754431f..1c8d7c3 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -14965,7 +14965,7 @@ rs6000_emit_vector_cond_expr (rtx dest, rtx op_true, rtx op_false,
}
/* Min/max subcase to emit an appropriate instruction for SF/DF scalars on ISA
- 3.0.
+ 3.0 and for IEEE 128-bit scalars on ISA 3.1.
Move TRUE_COND to DEST if OP of the operands of the last comparison is
nonzero/true, FALSE_COND if it is zero/false. Return 0 if the hardware has
@@ -15009,7 +15009,8 @@ emit_fp_min_max_insn (rtx dest, rtx op, rtx true_cond, rtx false_cond)
}
/* Conditional move subcase to emit a floating point compare setting a mask
- instruction and a XXSEL select instruction for SF/DF scalars on ISA 3.0.
+ instruction and a XXSEL select instruction for SF/DF scalars on ISA 3.0 and
+ for IEEE 128-bit scalars on ISA 3.1.
Move TRUE_COND to DEST if OP of the operands of the last comparison is
nonzero/true, FALSE_COND if it is zero/false. Return 0 if the hardware has
@@ -15105,6 +15106,21 @@ rs6000_emit_cmove (rtx dest, rtx op, rtx true_cond, rtx false_cond)
return 1;
}
+ /* See if we can use the ISA 3.1 min/max/compare instructions for IEEE
+ 128-bit floating point. At present, don't worry about doing conditional
+ moves with different types for the comparison and movement (unlike SF/DF,
+ where you can do a conditional test between double and use float as the
+ if/then parts. */
+ if (TARGET_FLOAT128_HW && TARGET_POWER10 && FLOAT128_IEEE_P (compare_mode)
+ && compare_mode == result_mode)
+ {
+ if (emit_fp_min_max_insn (dest, op, true_cond, false_cond))
+ return 1;
+
+ if (emit_fp_cmove_with_mask_xxsel (dest, op, true_cond, false_cond))
+ return 1;
+ }
+
/* Don't allow using floating point comparisons for integer results for
now. */
if (FLOAT_MODE_P (compare_mode) && !FLOAT_MODE_P (result_mode))
@@ -15328,7 +15344,8 @@ rs6000_emit_minmax (rtx dest, enum rtx_code code, rtx op0, rtx op1)
/* VSX/altivec have direct min/max insns. */
if ((code == SMAX || code == SMIN)
&& (VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)
- || (mode == SFmode && VECTOR_UNIT_VSX_P (DFmode))))
+ || (mode == SFmode && VECTOR_UNIT_VSX_P (DFmode))
+ || (TARGET_FLOAT128_HW && TARGET_POWER10 && FLOAT128_IEEE_P (mode))))
{
emit_insn (gen_rtx_SET (dest, gen_rtx_fmt_ee (code, mode, op0, op1)));
return;
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 86c8c02..0964891 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -14646,6 +14646,127 @@ (define_insn "*cmp<mode>_hw"
"xscmpuqp %0,%1,%2"
[(set_attr "type" "veccmp")
(set_attr "size" "128")])
+
+;; IEEE 128-bit min/max
+(define_insn "s<minmax><mode>3"
+ [(set (match_operand:IEEE128 0 "altivec_register_operand" "=v")
+ (fp_minmax:IEEE128
+ (match_operand:IEEE128 1 "altivec_register_operand" "v")
+ (match_operand:IEEE128 2 "altivec_register_operand" "v")))]
+ "TARGET_FLOAT128_HW && TARGET_POWER10 && FLOAT128_IEEE_P (<MODE>mode)"
+ "xs<minmax>cqp %0,%1,%2"
+ [(set_attr "type" "fp")
+ (set_attr "size" "128")])
+
+;; IEEE 128-bit conditional move. At present, don't worry about doing
+;; conditional moves with different types for the comparison and movement
+;; (unlike SF/DF, where you can do a conditional test between double and use
+;; float as the if/then parts.
+(define_expand "mov<mode>cc"
+ [(set (match_operand:IEEE128 0 "gpc_reg_operand")
+ (if_then_else:IEEE128 (match_operand 1 "comparison_operator")
+ (match_operand:IEEE128 2 "gpc_reg_operand")
+ (match_operand:IEEE128 3 "gpc_reg_operand")))]
+ "TARGET_FLOAT128_HW && TARGET_POWER10 && FLOAT128_IEEE_P (<MODE>mode)"
+{
+ if (rs6000_emit_cmove (operands[0], operands[1], operands[2], operands[3]))
+ DONE;
+ else
+ FAIL;
+})
+
+(define_insn_and_split "*mov<mode>cc_hardware"
+ [(set (match_operand:IEEE128 0 "altivec_register_operand" "=&v,v")
+ (if_then_else:IEEE128
+ (match_operator:CCFP 1 "fpmask_comparison_operator"
+ [(match_operand:IEEE128 2 "altivec_register_operand" "v,v")
+ (match_operand:IEEE128 3 "altivec_register_operand" "v,v")])
+ (match_operand:IEEE128 4 "vsx_register_operand" "wa,wa")
+ (match_operand:IEEE128 5 "vsx_register_operand" "wa,wa")))
+ (clobber (match_scratch:V2DI 6 "=0,&wa"))]
+ "TARGET_FLOAT128_HW && TARGET_POWER10"
+ "#"
+ ""
+ [(set (match_dup 6)
+ (if_then_else:V2DI (match_dup 1)
+ (match_dup 7)
+ (match_dup 8)))
+ (set (match_dup 0)
+ (if_then_else:IEEE128 (ne (match_dup 6)
+ (match_dup 8))
+ (match_dup 4)
+ (match_dup 5)))]
+{
+ if (GET_CODE (operands[6]) == SCRATCH)
+ operands[6] = gen_reg_rtx (V2DImode);
+
+ operands[7] = CONSTM1_RTX (V2DImode);
+ operands[8] = CONST0_RTX (V2DImode);
+}
+ [(set_attr "length" "8")
+ (set_attr "type" "vecperm")])
+
+;; Handle inverting the fpmask comparisons.
+(define_insn_and_split "*mov<mode>cc_invert_hardware"
+ [(set (match_operand:IEEE128 0 "altivec_register_operand" "=&v,v")
+ (if_then_else:IEEE128
+ (match_operator:CCFP 1 "invert_fpmask_comparison_operator"
+ [(match_operand:IEEE128 2 "altivec_register_operand" "v,v")
+ (match_operand:IEEE128 3 "altivec_register_operand" "v,v")])
+ (match_operand:IEEE128 4 "vsx_register_operand" "wa,wa")
+ (match_operand:IEEE128 5 "vsx_register_operand" "wa,wa")))
+ (clobber (match_scratch:V2DI 6 "=0,&wa"))]
+ "TARGET_FLOAT128_HW && TARGET_POWER10"
+ "#"
+ "&& 1"
+ [(set (match_dup 6)
+ (if_then_else:V2DI (match_dup 9)
+ (match_dup 7)
+ (match_dup 8)))
+ (set (match_dup 0)
+ (if_then_else:IEEE128 (ne (match_dup 6)
+ (match_dup 8))
+ (match_dup 5)
+ (match_dup 4)))]
+{
+ rtx op1 = operands[1];
+ enum rtx_code cond = reverse_condition_maybe_unordered (GET_CODE (op1));
+
+ if (GET_CODE (operands[6]) == SCRATCH)
+ operands[6] = gen_reg_rtx (V2DImode);
+
+ operands[7] = CONSTM1_RTX (V2DImode);
+ operands[8] = CONST0_RTX (V2DImode);
+
+ operands[9] = gen_rtx_fmt_ee (cond, CCFPmode, operands[2], operands[3]);
+}
+ [(set_attr "length" "8")
+ (set_attr "type" "vecperm")])
+
+(define_insn "*fpmask<mode>"
+ [(set (match_operand:V2DI 0 "altivec_register_operand" "=v")
+ (if_then_else:V2DI
+ (match_operator:CCFP 1 "fpmask_comparison_operator"
+ [(match_operand:IEEE128 2 "altivec_register_operand" "v")
+ (match_operand:IEEE128 3 "altivec_register_operand" "v")])
+ (match_operand:V2DI 4 "all_ones_constant" "")
+ (match_operand:V2DI 5 "zero_constant" "")))]
+ "TARGET_FLOAT128_HW && TARGET_POWER10 && FLOAT128_IEEE_P (<MODE>mode)"
+ "xscmp%V1qp %0,%2,%3"
+ [(set_attr "type" "fpcompare")
+ (set_attr "size" "128")])
+
+(define_insn "*xxsel<mode>"
+ [(set (match_operand:IEEE128 0 "vsx_register_operand" "=wa")
+ (if_then_else:IEEE128
+ (ne (match_operand:V2DI 1 "vsx_register_operand" "wa")
+ (match_operand:V2DI 2 "zero_constant" ""))
+ (match_operand:IEEE128 3 "vsx_register_operand" "wa")
+ (match_operand:IEEE128 4 "vsx_register_operand" "wa")))]
+ "TARGET_FLOAT128_HW && TARGET_POWER10 && FLOAT128_IEEE_P (<MODE>mode)"
+ "xxsel %x0,%x4,%x3,%x1"
+ [(set_attr "type" "vecmove")
+ (set_attr "size" "128")])
\f
;; Miscellaneous ISA 3.0 (power9) instructions
diff --git a/gcc/testsuite/gcc.target/powerpc/float128-minmax-2.c b/gcc/testsuite/gcc.target/powerpc/float128-minmax-2.c
new file mode 100644
index 0000000..e689678
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/float128-minmax-2.c
@@ -0,0 +1,70 @@
+/* { dg-do compile { target { powerpc*-*-* && lp64 } } } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2 -ffast-math" } */
+/* { dg-final { scan-assembler-not "xscmpuqp" } } */
+/* { dg-final { scan-assembler "xscmpeqqp" } } */
+/* { dg-final { scan-assembler "xscmpgtqp" } } */
+/* { dg-final { scan-assembler "xscmpgeqp" } } */
+/* { dg-final { scan-assembler "xsmaxcqp" } } */
+/* { dg-final { scan-assembler "xsmincqp" } } */
+/* { dg-final { scan-assembler "xxsel" } } */
+
+__float128
+f128_max1 (__float128 a, __float128 b)
+{
+ return (a >= b) ? a : b;
+}
+
+__float128
+f128_max2 (__float128 a, __float128 b)
+{
+ return (a > b) ? a : b;
+}
+
+__float128
+f128_min1 (__float128 a, __float128 b)
+{
+ return (a < b) ? a : b;
+}
+
+__float128
+f128_min2 (__float128 a, __float128 b)
+{
+ return (a <= b) ? a : b;
+}
+
+__float128
+f128_cmp_eq (__float128 a, __float128 b, __float128 c, __float128 d)
+{
+ return (a == b) ? c : d;
+}
+
+__float128
+f128_cmp_ne (__float128 a, __float128 b, __float128 c, __float128 d)
+{
+ return (a != b) ? c : d;
+}
+
+__float128
+f128_cmp_gt (__float128 a, __float128 b, __float128 c, __float128 d)
+{
+ return (a > b) ? c : d;
+}
+
+__float128
+f128_cmp_ge (__float128 a, __float128 b, __float128 c, __float128 d)
+{
+ return (a >= b) ? c : d;
+}
+
+__float128
+f128_cmp_lt (__float128 a, __float128 b, __float128 c, __float128 d)
+{
+ return (a < b) ? c : d;
+}
+
+__float128
+f128_cmp_le (__float128 a, __float128 b, __float128 c, __float128 d)
+{
+ return (a <= b) ? c : d;
+}
--
1.8.3.1
^ permalink raw reply [flat|nested] 5+ messages in thread