* [PATCH 1/3] s390: Refactor block operation cpymem
2023-05-15 7:17 [PATCH 0/3] Refactor memory block operations Stefan Schulze Frielinghaus
@ 2023-05-15 7:17 ` Stefan Schulze Frielinghaus
2023-05-15 7:17 ` [PATCH 2/3] s390: Add block operation movmem Stefan Schulze Frielinghaus
` (2 subsequent siblings)
3 siblings, 0 replies; 5+ messages in thread
From: Stefan Schulze Frielinghaus @ 2023-05-15 7:17 UTC (permalink / raw)
To: krebbel, gcc-patches; +Cc: Stefan Schulze Frielinghaus
Do not perform a libc function call into memcpy in case the size is not
a compile-time constant but bounded and the upper bound is less than or
equal to 256 bytes.
gcc/ChangeLog:
* config/s390/s390-protos.h (s390_expand_cpymem): Change
function signature.
* config/s390/s390.cc (s390_expand_cpymem): For memcpy's less
than or equal to 256 byte do not perform a libc call.
(s390_expand_insv): Adapt new function signature of
s390_expand_cpymem.
* config/s390/s390.md: Change expander into a version which
takes 8 operands.
---
gcc/config/s390/s390-protos.h | 2 +-
gcc/config/s390/s390.cc | 84 +++++++++++++++++++++++++++--------
gcc/config/s390/s390.md | 10 +++--
3 files changed, 74 insertions(+), 22 deletions(-)
diff --git a/gcc/config/s390/s390-protos.h b/gcc/config/s390/s390-protos.h
index 67fe09e732d..2c7495ca247 100644
--- a/gcc/config/s390/s390-protos.h
+++ b/gcc/config/s390/s390-protos.h
@@ -107,7 +107,7 @@ extern void s390_reload_symref_address (rtx , rtx , rtx , bool);
extern void s390_expand_plus_operand (rtx, rtx, rtx);
extern void emit_symbolic_move (rtx *);
extern void s390_load_address (rtx, rtx);
-extern bool s390_expand_cpymem (rtx, rtx, rtx);
+extern bool s390_expand_cpymem (rtx, rtx, rtx, rtx, rtx);
extern void s390_expand_setmem (rtx, rtx, rtx);
extern bool s390_expand_cmpmem (rtx, rtx, rtx, rtx);
extern void s390_expand_vec_strlen (rtx, rtx, rtx);
diff --git a/gcc/config/s390/s390.cc b/gcc/config/s390/s390.cc
index 505de995da8..95ea5e8d009 100644
--- a/gcc/config/s390/s390.cc
+++ b/gcc/config/s390/s390.cc
@@ -5650,27 +5650,27 @@ legitimize_reload_address (rtx ad, machine_mode mode ATTRIBUTE_UNUSED,
return NULL_RTX;
}
-/* Emit code to move LEN bytes from DST to SRC. */
+/* Emit code to move LEN bytes from SRC to DST. */
bool
-s390_expand_cpymem (rtx dst, rtx src, rtx len)
+s390_expand_cpymem (rtx dst, rtx src, rtx len, rtx min_len_rtx, rtx max_len_rtx)
{
- /* When tuning for z10 or higher we rely on the Glibc functions to
- do the right thing. Only for constant lengths below 64k we will
- generate inline code. */
- if (s390_tune >= PROCESSOR_2097_Z10
- && (GET_CODE (len) != CONST_INT || INTVAL (len) > (1<<16)))
- return false;
+ /* Exit early in case nothing has to be done. */
+ if (CONST_INT_P (len) && UINTVAL (len) == 0)
+ return true;
+
+ unsigned HOST_WIDE_INT min_len = UINTVAL (min_len_rtx);
+ unsigned HOST_WIDE_INT max_len
+ = max_len_rtx ? UINTVAL (max_len_rtx) : HOST_WIDE_INT_M1U;
/* Expand memcpy for constant length operands without a loop if it
is shorter that way.
With a constant length argument a
memcpy loop (without pfd) is 36 bytes -> 6 * mvc */
- if (GET_CODE (len) == CONST_INT
- && INTVAL (len) >= 0
- && INTVAL (len) <= 256 * 6
- && (!TARGET_MVCLE || INTVAL (len) <= 256))
+ if (CONST_INT_P (len)
+ && UINTVAL (len) <= 6 * 256
+ && (!TARGET_MVCLE || UINTVAL (len) <= 256))
{
HOST_WIDE_INT o, l;
@@ -5681,14 +5681,57 @@ s390_expand_cpymem (rtx dst, rtx src, rtx len)
emit_insn (gen_cpymem_short (newdst, newsrc,
GEN_INT (l > 256 ? 255 : l - 1)));
}
+
+ return true;
}
- else if (TARGET_MVCLE)
+ else if (TARGET_MVCLE
+ && (s390_tune < PROCESSOR_2097_Z10
+ || (CONST_INT_P (len) && UINTVAL (len) <= (1 << 16))))
{
emit_insn (gen_cpymem_long (dst, src, convert_to_mode (Pmode, len, 1)));
+ return true;
}
- else
+ /* Non-constant length and no loop required. */
+ else if (!CONST_INT_P (len) && max_len <= 256)
+ {
+ rtx_code_label *end_label;
+
+ if (min_len == 0)
+ {
+ end_label = gen_label_rtx ();
+ emit_cmp_and_jump_insns (len, const0_rtx, EQ, NULL_RTX,
+ GET_MODE (len), 1, end_label,
+ profile_probability::very_unlikely ());
+ }
+
+ rtx lenm1 = expand_binop (GET_MODE (len), add_optab, len, constm1_rtx,
+ NULL_RTX, 1, OPTAB_DIRECT);
+
+ /* Prefer a vectorized implementation over one which makes use of an
+ execute instruction since it is faster (although it increases register
+ pressure). */
+ if (max_len <= 16 && TARGET_VX)
+ {
+ rtx tmp = gen_reg_rtx (V16QImode);
+ lenm1 = convert_to_mode (SImode, lenm1, 1);
+ emit_insn (gen_vllv16qi (tmp, lenm1, src));
+ emit_insn (gen_vstlv16qi (tmp, lenm1, dst));
+ }
+ else if (TARGET_Z15)
+ emit_insn (gen_mvcrl (dst, src, convert_to_mode (SImode, lenm1, 1)));
+ else
+ emit_insn (
+ gen_cpymem_short (dst, src, convert_to_mode (Pmode, lenm1, 1)));
+
+ if (min_len == 0)
+ emit_label (end_label);
+
+ return true;
+ }
+
+ else if (s390_tune < PROCESSOR_2097_Z10 || (CONST_INT_P (len) && UINTVAL (len) <= (1 << 16)))
{
rtx dst_addr, src_addr, count, blocks, temp;
rtx_code_label *loop_start_label = gen_label_rtx ();
@@ -5706,8 +5749,9 @@ s390_expand_cpymem (rtx dst, rtx src, rtx len)
blocks = gen_reg_rtx (mode);
convert_move (count, len, 1);
- emit_cmp_and_jump_insns (count, const0_rtx,
- EQ, NULL_RTX, mode, 1, end_label);
+ if (min_len == 0)
+ emit_cmp_and_jump_insns (count, const0_rtx, EQ, NULL_RTX, mode, 1,
+ end_label);
emit_move_insn (dst_addr, force_operand (XEXP (dst, 0), NULL_RTX));
emit_move_insn (src_addr, force_operand (XEXP (src, 0), NULL_RTX));
@@ -5767,8 +5811,11 @@ s390_expand_cpymem (rtx dst, rtx src, rtx len)
emit_insn (gen_cpymem_short (dst, src,
convert_to_mode (Pmode, count, 1)));
emit_label (end_label);
+
+ return true;
}
- return true;
+
+ return false;
}
/* Emit code to set LEN bytes at DST to VAL.
@@ -6599,7 +6646,8 @@ s390_expand_insv (rtx dest, rtx op1, rtx op2, rtx src)
dest = adjust_address (dest, BLKmode, 0);
set_mem_size (dest, size);
- s390_expand_cpymem (dest, src_mem, GEN_INT (size));
+ rtx size_rtx = GEN_INT (size);
+ s390_expand_cpymem (dest, src_mem, size_rtx, size_rtx, size_rtx);
return true;
}
diff --git a/gcc/config/s390/s390.md b/gcc/config/s390/s390.md
index 00d39608e1d..d9ce287ab85 100644
--- a/gcc/config/s390/s390.md
+++ b/gcc/config/s390/s390.md
@@ -3341,11 +3341,15 @@
(define_expand "cpymem<mode>"
[(set (match_operand:BLK 0 "memory_operand" "") ; destination
(match_operand:BLK 1 "memory_operand" "")) ; source
- (use (match_operand:GPR 2 "general_operand" "")) ; count
- (match_operand 3 "" "")]
+ (use (match_operand:GPR 2 "general_operand" "")) ; size
+ (match_operand 3 "") ; align
+ (match_operand 4 "") ; expected align
+ (match_operand 5 "") ; expected size
+ (match_operand 6 "") ; minimal size
+ (match_operand 7 "")] ; maximal size
""
{
- if (s390_expand_cpymem (operands[0], operands[1], operands[2]))
+ if (s390_expand_cpymem (operands[0], operands[1], operands[2], operands[6], operands[7]))
DONE;
else
FAIL;
--
2.39.2
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH 2/3] s390: Add block operation movmem
2023-05-15 7:17 [PATCH 0/3] Refactor memory block operations Stefan Schulze Frielinghaus
2023-05-15 7:17 ` [PATCH 1/3] s390: Refactor block operation cpymem Stefan Schulze Frielinghaus
@ 2023-05-15 7:17 ` Stefan Schulze Frielinghaus
2023-05-15 7:17 ` [PATCH 3/3] s390: Refactor block operation setmem Stefan Schulze Frielinghaus
2023-05-15 20:18 ` [PATCH 0/3] Refactor memory block operations Andreas Krebbel
3 siblings, 0 replies; 5+ messages in thread
From: Stefan Schulze Frielinghaus @ 2023-05-15 7:17 UTC (permalink / raw)
To: krebbel, gcc-patches; +Cc: Stefan Schulze Frielinghaus
gcc/ChangeLog:
* config/s390/s390-protos.h (s390_expand_movmem): New.
* config/s390/s390.cc (s390_expand_movmem): New.
* config/s390/s390.md (movmem<mode>): New.
(*mvcrl): New.
(mvcrl): New.
---
gcc/config/s390/s390-protos.h | 1 +
gcc/config/s390/s390.cc | 88 +++++++++++++++++++++++++++++++++++
gcc/config/s390/s390.md | 35 ++++++++++++++
3 files changed, 124 insertions(+)
diff --git a/gcc/config/s390/s390-protos.h b/gcc/config/s390/s390-protos.h
index 2c7495ca247..65e4f97b41e 100644
--- a/gcc/config/s390/s390-protos.h
+++ b/gcc/config/s390/s390-protos.h
@@ -108,6 +108,7 @@ extern void s390_expand_plus_operand (rtx, rtx, rtx);
extern void emit_symbolic_move (rtx *);
extern void s390_load_address (rtx, rtx);
extern bool s390_expand_cpymem (rtx, rtx, rtx, rtx, rtx);
+extern bool s390_expand_movmem (rtx, rtx, rtx, rtx, rtx);
extern void s390_expand_setmem (rtx, rtx, rtx);
extern bool s390_expand_cmpmem (rtx, rtx, rtx, rtx);
extern void s390_expand_vec_strlen (rtx, rtx, rtx);
diff --git a/gcc/config/s390/s390.cc b/gcc/config/s390/s390.cc
index 95ea5e8d009..553273f23ff 100644
--- a/gcc/config/s390/s390.cc
+++ b/gcc/config/s390/s390.cc
@@ -5818,6 +5818,94 @@ s390_expand_cpymem (rtx dst, rtx src, rtx len, rtx min_len_rtx, rtx max_len_rtx)
return false;
}
+bool
+s390_expand_movmem (rtx dst, rtx src, rtx len, rtx min_len_rtx, rtx max_len_rtx)
+{
+ /* Exit early in case nothing has to be done. */
+ if (CONST_INT_P (len) && UINTVAL (len) == 0)
+ return true;
+ /* Exit early in case length is not upper bounded. */
+ else if (max_len_rtx == NULL)
+ return false;
+
+ unsigned HOST_WIDE_INT min_len = UINTVAL (min_len_rtx);
+ unsigned HOST_WIDE_INT max_len = UINTVAL (max_len_rtx);
+
+ /* At most 16 bytes. */
+ if (max_len <= 16 && TARGET_VX)
+ {
+ rtx_code_label *end_label;
+
+ if (min_len == 0)
+ {
+ end_label = gen_label_rtx ();
+ emit_cmp_and_jump_insns (len, const0_rtx, EQ, NULL_RTX,
+ GET_MODE (len), 1, end_label,
+ profile_probability::very_unlikely ());
+ }
+
+ rtx lenm1;
+ if (CONST_INT_P (len))
+ {
+ lenm1 = gen_reg_rtx (SImode);
+ emit_move_insn (lenm1, GEN_INT (UINTVAL (len) - 1));
+ }
+ else
+ lenm1
+ = expand_binop (SImode, add_optab, convert_to_mode (SImode, len, 1),
+ constm1_rtx, NULL_RTX, 1, OPTAB_DIRECT);
+
+ rtx tmp = gen_reg_rtx (V16QImode);
+ emit_insn (gen_vllv16qi (tmp, lenm1, src));
+ emit_insn (gen_vstlv16qi (tmp, lenm1, dst));
+
+ if (min_len == 0)
+ emit_label (end_label);
+
+ return true;
+ }
+
+ /* At most 256 bytes. */
+ else if (max_len <= 256 && TARGET_Z15)
+ {
+ rtx_code_label *end_label = gen_label_rtx ();
+
+ if (min_len == 0)
+ emit_cmp_and_jump_insns (len, const0_rtx, EQ, NULL_RTX, GET_MODE (len),
+ 1, end_label,
+ profile_probability::very_unlikely ());
+
+ rtx dst_addr = gen_reg_rtx (Pmode);
+ rtx src_addr = gen_reg_rtx (Pmode);
+ emit_move_insn (dst_addr, force_operand (XEXP (dst, 0), NULL_RTX));
+ emit_move_insn (src_addr, force_operand (XEXP (src, 0), NULL_RTX));
+
+ rtx lenm1 = CONST_INT_P (len)
+ ? GEN_INT (UINTVAL (len) - 1)
+ : expand_binop (GET_MODE (len), add_optab, len, constm1_rtx,
+ NULL_RTX, 1, OPTAB_DIRECT);
+
+ rtx_code_label *right_to_left_label = gen_label_rtx ();
+ emit_cmp_and_jump_insns (src_addr, dst_addr, LT, NULL_RTX, GET_MODE (len),
+ 1, right_to_left_label);
+
+ // MVC
+ emit_insn (
+ gen_cpymem_short (dst, src, convert_to_mode (Pmode, lenm1, 1)));
+ emit_jump (end_label);
+
+ // MVCRL
+ emit_label (right_to_left_label);
+ emit_insn (gen_mvcrl (dst, src, convert_to_mode (SImode, lenm1, 1)));
+
+ emit_label (end_label);
+
+ return true;
+ }
+
+ return false;
+}
+
/* Emit code to set LEN bytes at DST to VAL.
Make use of clrmem if VAL is zero. */
diff --git a/gcc/config/s390/s390.md b/gcc/config/s390/s390.md
index d9ce287ab85..abe3bbc5cd9 100644
--- a/gcc/config/s390/s390.md
+++ b/gcc/config/s390/s390.md
@@ -61,6 +61,7 @@
UNSPEC_ROUND
UNSPEC_ICM
UNSPEC_TIE
+ UNSPEC_MVCRL
; Convert CC into a str comparison result and copy it into an
; integer register
@@ -3496,6 +3497,40 @@
[(set_attr "length" "8")
(set_attr "type" "vs")])
+(define_expand "movmem<mode>"
+ [(set (match_operand:BLK 0 "memory_operand") ; destination
+ (match_operand:BLK 1 "memory_operand")) ; source
+ (use (match_operand:GPR 2 "general_operand")) ; size
+ (match_operand 3 "") ; align
+ (match_operand 4 "") ; expected align
+ (match_operand 5 "") ; expected size
+ (match_operand 6 "") ; minimal size
+ (match_operand 7 "")] ; maximal size
+ ""
+{
+ if (s390_expand_movmem (operands[0], operands[1], operands[2], operands[6], operands[7]))
+ DONE;
+ else
+ FAIL;
+})
+
+(define_insn "*mvcrl"
+ [(set (match_operand:BLK 0 "memory_operand" "=Q")
+ (unspec:BLK [(match_operand:BLK 1 "memory_operand" "Q")
+ (reg:SI GPR0_REGNUM)]
+ UNSPEC_MVCRL))]
+ "TARGET_Z15"
+ "mvcrl\t%0,%1"
+ [(set_attr "op_type" "SSE")])
+
+(define_expand "mvcrl"
+ [(set (reg:SI GPR0_REGNUM) (match_operand:SI 2 "general_operand"))
+ (set (match_operand:BLK 0 "memory_operand" "=Q")
+ (unspec:BLK [(match_operand:BLK 1 "memory_operand" "Q")
+ (reg:SI GPR0_REGNUM)]
+ UNSPEC_MVCRL))]
+ "TARGET_Z15"
+ "")
;
; Test data class.
--
2.39.2
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH 3/3] s390: Refactor block operation setmem
2023-05-15 7:17 [PATCH 0/3] Refactor memory block operations Stefan Schulze Frielinghaus
2023-05-15 7:17 ` [PATCH 1/3] s390: Refactor block operation cpymem Stefan Schulze Frielinghaus
2023-05-15 7:17 ` [PATCH 2/3] s390: Add block operation movmem Stefan Schulze Frielinghaus
@ 2023-05-15 7:17 ` Stefan Schulze Frielinghaus
2023-05-15 20:18 ` [PATCH 0/3] Refactor memory block operations Andreas Krebbel
3 siblings, 0 replies; 5+ messages in thread
From: Stefan Schulze Frielinghaus @ 2023-05-15 7:17 UTC (permalink / raw)
To: krebbel, gcc-patches; +Cc: Stefan Schulze Frielinghaus
Vectorize memset with a constant length of less than or equal to 64
bytes.
Do not perform a libc function call into memset in case the size is not
a compile-time constant but bounded and the upper bound is less than or
equal to 256 bytes.
gcc/ChangeLog:
* config/s390/s390-protos.h (s390_expand_setmem): Change
function signature.
* config/s390/s390.cc (s390_expand_setmem): For memset's less
than or equal to 256 byte do not perform a libc call.
* config/s390/s390.md: Change expander into a version which
takes 8 operands.
gcc/testsuite/ChangeLog:
* gcc.target/s390/memset-1.c: Test case memset1 makes use of
vst, now.
---
gcc/config/s390/s390-protos.h | 2 +-
gcc/config/s390/s390.cc | 129 +++++++++++++++++++++--
gcc/config/s390/s390.md | 14 ++-
gcc/testsuite/gcc.target/s390/memset-1.c | 7 +-
4 files changed, 132 insertions(+), 20 deletions(-)
diff --git a/gcc/config/s390/s390-protos.h b/gcc/config/s390/s390-protos.h
index 65e4f97b41e..4a5263fccec 100644
--- a/gcc/config/s390/s390-protos.h
+++ b/gcc/config/s390/s390-protos.h
@@ -109,7 +109,7 @@ extern void emit_symbolic_move (rtx *);
extern void s390_load_address (rtx, rtx);
extern bool s390_expand_cpymem (rtx, rtx, rtx, rtx, rtx);
extern bool s390_expand_movmem (rtx, rtx, rtx, rtx, rtx);
-extern void s390_expand_setmem (rtx, rtx, rtx);
+extern void s390_expand_setmem (rtx, rtx, rtx, rtx, rtx);
extern bool s390_expand_cmpmem (rtx, rtx, rtx, rtx);
extern void s390_expand_vec_strlen (rtx, rtx, rtx);
extern void s390_expand_vec_movstr (rtx, rtx, rtx);
diff --git a/gcc/config/s390/s390.cc b/gcc/config/s390/s390.cc
index 553273f23ff..b1cb54612b8 100644
--- a/gcc/config/s390/s390.cc
+++ b/gcc/config/s390/s390.cc
@@ -5910,20 +5910,62 @@ s390_expand_movmem (rtx dst, rtx src, rtx len, rtx min_len_rtx, rtx max_len_rtx)
Make use of clrmem if VAL is zero. */
void
-s390_expand_setmem (rtx dst, rtx len, rtx val)
+s390_expand_setmem (rtx dst, rtx len, rtx val, rtx min_len_rtx, rtx max_len_rtx)
{
- if (GET_CODE (len) == CONST_INT && INTVAL (len) <= 0)
+ /* Exit early in case nothing has to be done. */
+ if (CONST_INT_P (len) && UINTVAL (len) == 0)
return;
gcc_assert (GET_CODE (val) == CONST_INT || GET_MODE (val) == QImode);
+ unsigned HOST_WIDE_INT min_len = UINTVAL (min_len_rtx);
+ unsigned HOST_WIDE_INT max_len
+ = max_len_rtx ? UINTVAL (max_len_rtx) : HOST_WIDE_INT_M1U;
+
+ /* Vectorize memset with a constant length
+ - if 0 < LEN < 16, then emit a vstl based solution;
+ - if 16 <= LEN <= 64, then emit a vst based solution
+ where the last two vector stores may overlap in case LEN%16!=0. Paying
+ the price for an overlap is negligible compared to an extra GPR which is
+ required for vstl. */
+ if (CONST_INT_P (len) && UINTVAL (len) <= 64 && val != const0_rtx
+ && TARGET_VX)
+ {
+ rtx val_vec = gen_reg_rtx (V16QImode);
+ emit_move_insn (val_vec, gen_rtx_VEC_DUPLICATE (V16QImode, val));
+
+ if (UINTVAL (len) < 16)
+ {
+ rtx len_reg = gen_reg_rtx (SImode);
+ emit_move_insn (len_reg, GEN_INT (UINTVAL (len) - 1));
+ emit_insn (gen_vstlv16qi (val_vec, len_reg, dst));
+ }
+ else
+ {
+ unsigned HOST_WIDE_INT l = UINTVAL (len) / 16;
+ unsigned HOST_WIDE_INT r = UINTVAL (len) % 16;
+ unsigned HOST_WIDE_INT o = 0;
+ for (unsigned HOST_WIDE_INT i = 0; i < l; ++i)
+ {
+ rtx newdst = adjust_address (dst, V16QImode, o);
+ emit_move_insn (newdst, val_vec);
+ o += 16;
+ }
+ if (r != 0)
+ {
+ rtx newdst = adjust_address (dst, V16QImode, (o - 16) + r);
+ emit_move_insn (newdst, val_vec);
+ }
+ }
+ }
+
/* Expand setmem/clrmem for a constant length operand without a
loop if it will be shorter that way.
clrmem loop (with PFD) is 30 bytes -> 5 * xc
clrmem loop (without PFD) is 24 bytes -> 4 * xc
setmem loop (with PFD) is 38 bytes -> ~4 * (mvi/stc + mvc)
setmem loop (without PFD) is 32 bytes -> ~4 * (mvi/stc + mvc) */
- if (GET_CODE (len) == CONST_INT
+ else if (GET_CODE (len) == CONST_INT
&& ((val == const0_rtx
&& (INTVAL (len) <= 256 * 4
|| (INTVAL (len) <= 256 * 5 && TARGET_SETMEM_PFD(val,len))))
@@ -5968,6 +6010,70 @@ s390_expand_setmem (rtx dst, rtx len, rtx val)
val));
}
+ /* Non-constant length and no loop required. */
+ else if (!CONST_INT_P (len) && max_len <= 256)
+ {
+ rtx_code_label *end_label;
+
+ if (min_len == 0)
+ {
+ end_label = gen_label_rtx ();
+ emit_cmp_and_jump_insns (len, const0_rtx, EQ, NULL_RTX,
+ GET_MODE (len), 1, end_label,
+ profile_probability::very_unlikely ());
+ }
+
+ rtx lenm1 = expand_binop (GET_MODE (len), add_optab, len, constm1_rtx,
+ NULL_RTX, 1, OPTAB_DIRECT);
+
+ /* Prefer a vectorized implementation over one which makes use of an
+ execute instruction since it is faster (although it increases register
+ pressure). */
+ if (max_len <= 16 && TARGET_VX)
+ {
+ rtx val_vec = gen_reg_rtx (V16QImode);
+ if (val == const0_rtx)
+ emit_move_insn (val_vec, CONST0_RTX (V16QImode));
+ else
+ emit_move_insn (val_vec, gen_rtx_VEC_DUPLICATE (V16QImode, val));
+
+ lenm1 = convert_to_mode (SImode, lenm1, 1);
+ emit_insn (gen_vstlv16qi (val_vec, lenm1, dst));
+ }
+ else
+ {
+ if (val == const0_rtx)
+ emit_insn (
+ gen_clrmem_short (dst, convert_to_mode (Pmode, lenm1, 1)));
+ else
+ {
+ emit_move_insn (adjust_address (dst, QImode, 0), val);
+
+ rtx_code_label *onebyte_end_label;
+ if (min_len <= 1)
+ {
+ onebyte_end_label = gen_label_rtx ();
+ emit_cmp_and_jump_insns (
+ len, const1_rtx, EQ, NULL_RTX, GET_MODE (len), 1,
+ onebyte_end_label, profile_probability::very_unlikely ());
+ }
+
+ rtx dstp1 = adjust_address (dst, VOIDmode, 1);
+ rtx lenm2
+ = expand_binop (GET_MODE (len), add_optab, len, GEN_INT (-2),
+ NULL_RTX, 1, OPTAB_DIRECT);
+ lenm2 = convert_to_mode (Pmode, lenm2, 1);
+ emit_insn (gen_cpymem_short (dstp1, dst, lenm2));
+
+ if (min_len <= 1)
+ emit_label (onebyte_end_label);
+ }
+ }
+
+ if (min_len == 0)
+ emit_label (end_label);
+ }
+
else
{
rtx dst_addr, count, blocks, temp, dstp1 = NULL_RTX;
@@ -5986,9 +6092,10 @@ s390_expand_setmem (rtx dst, rtx len, rtx val)
blocks = gen_reg_rtx (mode);
convert_move (count, len, 1);
- emit_cmp_and_jump_insns (count, const0_rtx,
- EQ, NULL_RTX, mode, 1, zerobyte_end_label,
- profile_probability::very_unlikely ());
+ if (min_len == 0)
+ emit_cmp_and_jump_insns (count, const0_rtx, EQ, NULL_RTX, mode, 1,
+ zerobyte_end_label,
+ profile_probability::very_unlikely ());
/* We need to make a copy of the target address since memset is
supposed to return it unmodified. We have to make it here
@@ -6003,10 +6110,10 @@ s390_expand_setmem (rtx dst, rtx len, rtx val)
the mvc reading this value). */
set_mem_size (dst, 1);
dstp1 = adjust_address (dst, VOIDmode, 1);
- emit_cmp_and_jump_insns (count,
- const1_rtx, EQ, NULL_RTX, mode, 1,
- onebyte_end_label,
- profile_probability::very_unlikely ());
+ if (min_len <= 1)
+ emit_cmp_and_jump_insns (count, const1_rtx, EQ, NULL_RTX, mode, 1,
+ onebyte_end_label,
+ profile_probability::very_unlikely ());
}
/* There is one unconditional (mvi+mvc)/xc after the loop
@@ -6029,7 +6136,7 @@ s390_expand_setmem (rtx dst, rtx len, rtx val)
emit_jump (loop_start_label);
- if (val != const0_rtx)
+ if (val != const0_rtx && min_len <= 1)
{
/* The 1 byte != 0 special case. Not handled efficiently
since we require two jumps for that. However, this
diff --git a/gcc/config/s390/s390.md b/gcc/config/s390/s390.md
index abe3bbc5cd9..9631b2a8c60 100644
--- a/gcc/config/s390/s390.md
+++ b/gcc/config/s390/s390.md
@@ -3595,12 +3595,16 @@
;
(define_expand "setmem<mode>"
- [(set (match_operand:BLK 0 "memory_operand" "")
- (match_operand:QI 2 "general_operand" ""))
- (use (match_operand:GPR 1 "general_operand" ""))
- (match_operand 3 "" "")]
+ [(set (match_operand:BLK 0 "memory_operand" "") ; destination
+ (match_operand:QI 2 "general_operand" "")) ; value
+ (use (match_operand:GPR 1 "general_operand" "")) ; size
+ (match_operand 3 "") ; align
+ (match_operand 4 "") ; expected align
+ (match_operand 5 "") ; expected size
+ (match_operand 6 "") ; minimal size
+ (match_operand 7 "")] ; maximal size
""
- "s390_expand_setmem (operands[0], operands[1], operands[2]); DONE;")
+ "s390_expand_setmem (operands[0], operands[1], operands[2], operands[6], operands[7]); DONE;")
; Clear a block that is up to 256 bytes in length.
; The block length is taken as (operands[1] % 256) + 1.
diff --git a/gcc/testsuite/gcc.target/s390/memset-1.c b/gcc/testsuite/gcc.target/s390/memset-1.c
index 9463a77208b..5eb96112f13 100644
--- a/gcc/testsuite/gcc.target/s390/memset-1.c
+++ b/gcc/testsuite/gcc.target/s390/memset-1.c
@@ -11,7 +11,7 @@ void
return __builtin_memset (s, c, 1);
}
-/* 1 stc 1 mvc */
+/* 3 vst */
void
*memset1(void *s, int c)
{
@@ -170,8 +170,9 @@ void
}
/* { dg-final { scan-assembler-times "mvi\\s" 1 } } */
-/* { dg-final { scan-assembler-times "mvc\\s" 20 } } */
+/* { dg-final { scan-assembler-times "mvc\\s" 19 } } */
/* { dg-final { scan-assembler-times "xc\\s" 28 } } */
-/* { dg-final { scan-assembler-times "stc\\s" 22 } } */
+/* { dg-final { scan-assembler-times "stc\\s" 21 } } */
/* { dg-final { scan-assembler-times "stcy\\s" 0 } } */
/* { dg-final { scan-assembler-times "pfd\\s" 2 } } */
+/* { dg-final { scan-assembler-times "vst\\s" 3 } } */
--
2.39.2
^ permalink raw reply [flat|nested] 5+ messages in thread* Re: [PATCH 0/3] Refactor memory block operations
2023-05-15 7:17 [PATCH 0/3] Refactor memory block operations Stefan Schulze Frielinghaus
` (2 preceding siblings ...)
2023-05-15 7:17 ` [PATCH 3/3] s390: Refactor block operation setmem Stefan Schulze Frielinghaus
@ 2023-05-15 20:18 ` Andreas Krebbel
3 siblings, 0 replies; 5+ messages in thread
From: Andreas Krebbel @ 2023-05-15 20:18 UTC (permalink / raw)
To: Stefan Schulze Frielinghaus, gcc-patches
On 5/15/23 09:17, Stefan Schulze Frielinghaus wrote:
> Bootstrapped and regtested. Ok for mainline?
>
> Stefan Schulze Frielinghaus (3):
> s390: Refactor block operation cpymem
> s390: Add block operation movmem
> s390: Refactor block operation setmem
>
> gcc/config/s390/s390-protos.h | 5 +-
> gcc/config/s390/s390.cc | 301 ++++++++++++++++++++---
> gcc/config/s390/s390.md | 61 ++++-
> gcc/testsuite/gcc.target/s390/memset-1.c | 7 +-
> 4 files changed, 331 insertions(+), 43 deletions(-)
>
Ok. Thanks!
Andreas
^ permalink raw reply [flat|nested] 5+ messages in thread