1. Add TARGET_AVX256_MOVE_BY_PIECES to perform move by-pieces operation
with 256-bit AVX instructions.
2. Add TARGET_AVX256_STORE_BY_PIECES to perform move and store by-pieces
operations with 256-bit AVX instructions.
They are enabled only for Intel Alder Lake and Intel processors with
AVX512.
gcc/
PR target/101935
* config/i386/i386.h (TARGET_AVX256_MOVE_BY_PIECES): New.
(TARGET_AVX256_STORE_BY_PIECES): Likewise.
(MOVE_MAX): Check TARGET_AVX256_MOVE_BY_PIECES and
TARGET_AVX256_STORE_BY_PIECES instead of
TARGET_AVX256_SPLIT_UNALIGNED_LOAD and
TARGET_AVX256_SPLIT_UNALIGNED_STORE.
(STORE_MAX_PIECES): Check TARGET_AVX256_STORE_BY_PIECES instead
of TARGET_AVX256_SPLIT_UNALIGNED_STORE.
* config/i386/x86-tune.def (X86_TUNE_AVX256_MOVE_BY_PIECES): New.
(X86_TUNE_AVX256_STORE_BY_PIECES): Likewise.
gcc/testsuite/
PR target/101935
* g++.target/i386/pr80566-1.C: Add
-mtune-ctrl=avx256_store_by_pieces.
* gcc.target/i386/pr100865-4a.c: Likewise.
* gcc.target/i386/pr100865-10a.c: Likewise.
* gcc.target/i386/pr90773-20.c: Likewise.
* gcc.target/i386/pr90773-21.c: Likewise.
* gcc.target/i386/pr90773-22.c: Likewise.
* gcc.target/i386/pr90773-23.c: Likewise.
* g++.target/i386/pr80566-2.C: Add
-mtune-ctrl=avx256_move_by_pieces.
* gcc.target/i386/eh_return-1.c: Likewise.
* gcc.target/i386/pr90773-26.c: Likewise.
* gcc.target/i386/pieces-memcpy-12.c: Replace -mtune=haswell
with -mtune-ctrl=avx256_move_by_pieces.
* gcc.target/i386/pieces-memcpy-15.c: Likewise.
* gcc.target/i386/pieces-memset-2.c: Replace -mtune=haswell
with -mtune-ctrl=avx256_store_by_pieces.
* gcc.target/i386/pieces-memset-5.c: Likewise.
* gcc.target/i386/pieces-memset-11.c: Likewise.
* gcc.target/i386/pieces-memset-14.c: Likewise.
* gcc.target/i386/pieces-memset-20.c: Likewise.
* gcc.target/i386/pieces-memset-23.c: Likewise.
* gcc.target/i386/pieces-memset-29.c: Likewise.
* gcc.target/i386/pieces-memset-30.c: Likewise.
* gcc.target/i386/pieces-memset-33.c: Likewise.
* gcc.target/i386/pieces-memset-34.c: Likewise.
* gcc.target/i386/pieces-memset-44.c: Likewise.
* gcc.target/i386/pieces-memset-37.c: Replace -mtune=generic
with -mtune-ctrl=avx256_store_by_pieces.
---
gcc/config/i386/i386.h | 10 +++++++---
gcc/config/i386/x86-tune.def | 11 +++++++++++
gcc/testsuite/g++.target/i386/pr80566-1.C | 2 +-
gcc/testsuite/g++.target/i386/pr80566-2.C | 2 +-
gcc/testsuite/gcc.target/i386/eh_return-1.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memcpy-12.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memcpy-15.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-11.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-14.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-2.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-20.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-23.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-29.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-30.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-33.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-34.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-37.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-44.c | 2 +-
gcc/testsuite/gcc.target/i386/pieces-memset-5.c | 2 +-
gcc/testsuite/gcc.target/i386/pr100865-10a.c | 2 +-
gcc/testsuite/gcc.target/i386/pr100865-4a.c | 2 +-
gcc/testsuite/gcc.target/i386/pr90773-20.c | 2 +-
gcc/testsuite/gcc.target/i386/pr90773-21.c | 2 +-
gcc/testsuite/gcc.target/i386/pr90773-22.c | 2 +-
gcc/testsuite/gcc.target/i386/pr90773-23.c | 2 +-
gcc/testsuite/gcc.target/i386/pr90773-26.c | 2 +-
26 files changed, 42 insertions(+), 27 deletions(-)
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index f671dae9236..9d45fe9611b 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -403,6 +403,10 @@ extern unsigned char ix86_tune_features[X86_TUNE_LAST];
ix86_tune_features[X86_TUNE_AVOID_LEA_FOR_ADDR]
#define TARGET_SOFTWARE_PREFETCHING_BENEFICIAL \
ix86_tune_features[X86_TUNE_SOFTWARE_PREFETCHING_BENEFICIAL]
+#define TARGET_AVX256_MOVE_BY_PIECES \
+ ix86_tune_features[X86_TUNE_AVX256_MOVE_BY_PIECES]
+#define TARGET_AVX256_STORE_BY_PIECES \
+ ix86_tune_features[X86_TUNE_AVX256_STORE_BY_PIECES]
#define TARGET_AVX256_SPLIT_REGS \
ix86_tune_features[X86_TUNE_AVX256_SPLIT_REGS]
#define TARGET_GENERAL_REGS_SSE_SPILL \
@@ -1781,8 +1785,8 @@ typedef struct ix86_args {
? 64 \
: ((TARGET_AVX \
&& !TARGET_PREFER_AVX128 \
- && !TARGET_AVX256_SPLIT_UNALIGNED_LOAD \
- && !TARGET_AVX256_SPLIT_UNALIGNED_STORE) \
+ && (TARGET_AVX256_MOVE_BY_PIECES \
+ || TARGET_AVX256_STORE_BY_PIECES)) \
? 32 \
: ((TARGET_SSE2 \
&& TARGET_SSE_UNALIGNED_LOAD_OPTIMAL \
@@ -1799,7 +1803,7 @@ typedef struct ix86_args {
? 64 \
: ((TARGET_AVX \
&& !TARGET_PREFER_AVX128 \
- && !TARGET_AVX256_SPLIT_UNALIGNED_STORE) \
+ && TARGET_AVX256_STORE_BY_PIECES) \
? 32 \
: ((TARGET_SSE2 \
&& TARGET_SSE_UNALIGNED_STORE_OPTIMAL) \
diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index 8f55da89c92..2f221b1f8c9 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -484,6 +484,17 @@ DEF_TUNE (X86_TUNE_AVX128_OPTIMAL, "avx128_optimal",
m_BDVER | m_BTVER2
instructions in the auto-vectorizer. */
DEF_TUNE (X86_TUNE_AVX256_OPTIMAL, "avx256_optimal", m_CORE_AVX512)
+/* X86_TUNE_AVX256_MOVE_BY_PIECES: Optimize move_by_pieces with 256-bit
+ AVX instructions. */
+DEF_TUNE (X86_TUNE_AVX256_MOVE_BY_PIECES, "avx256_move_by_pieces",
+ m_ALDERLAKE | m_CORE_AVX512)
+
+/* X86_TUNE_AVX256_STORE_BY_PIECES: Optimize store_by_pieces with 256-bit
+ AVX instructions. */
+DEF_TUNE (X86_TUNE_AVX256_STORE_BY_PIECES, "avx256_store_by_pieces",
+ m_ALDERLAKE | m_CORE_AVX512)
+
+/*****************************************************************************/
/*****************************************************************************/
/* Historical relics: tuning flags that helps a specific old CPU designs */
/*****************************************************************************/
diff --git a/gcc/testsuite/g++.target/i386/pr80566-1.C
b/gcc/testsuite/g++.target/i386/pr80566-1.C
index 753f9740529..29da31d6bb6 100644
--- a/gcc/testsuite/g++.target/i386/pr80566-1.C
+++ b/gcc/testsuite/g++.target/i386/pr80566-1.C
@@ -1,5 +1,5 @@
// { dg-do compile }
-// { dg-options "-O2 -march=haswell" }
+// { dg-options "-O2 -march=haswell -mtune-ctrl=avx256_store_by_pieces" }
#include <cstring>
diff --git a/gcc/testsuite/g++.target/i386/pr80566-2.C
b/gcc/testsuite/g++.target/i386/pr80566-2.C
index 2a2e82d0a3a..9ffd2c8cadb 100644
--- a/gcc/testsuite/g++.target/i386/pr80566-2.C
+++ b/gcc/testsuite/g++.target/i386/pr80566-2.C
@@ -1,5 +1,5 @@
// { dg-do compile }
-// { dg-options "-O2 -march=haswell" }
+// { dg-options "-O2 -march=haswell -mtune-ctrl=avx256_move_by_pieces" }
#include <cstring>
diff --git a/gcc/testsuite/gcc.target/i386/eh_return-1.c
b/gcc/testsuite/gcc.target/i386/eh_return-1.c
index 671ba635e88..b21fd75fc93 100644
--- a/gcc/testsuite/gcc.target/i386/eh_return-1.c
+++ b/gcc/testsuite/gcc.target/i386/eh_return-1.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -march=haswell -mno-avx512f" } */
+/* { dg-options "-O2 -march=haswell -mno-avx512f
-mtune-ctrl=avx256_move_by_pieces" } */
struct _Unwind_Context
{
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memcpy-12.c
b/gcc/testsuite/gcc.target/i386/pieces-memcpy-12.c
index f1432ebe517..8a82baff5f1 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memcpy-12.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memcpy-12.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune-ctrl=avx256_move_by_pieces" } */
extern char *dst, *src;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memcpy-15.c
b/gcc/testsuite/gcc.target/i386/pieces-memcpy-15.c
index 695e8c3fa67..4fb94ce7bd5 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memcpy-15.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memcpy-15.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune-ctrl=avx256_move_by_pieces" } */
extern char *dst, *src;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-11.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-11.c
index 3fb9038b04f..3802eb7c147 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-11.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-11.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-14.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-14.c
index 45ece482464..10bc085f83b 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-14.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-14.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-2.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-2.c
index 649f344e8f6..4ebfc4df090 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-2.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-2.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-20.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-20.c
index b8747e669e8..1dc4db180d3 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-20.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-20.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-23.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-23.c
index a3b4ffc18e0..9232864024e 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-23.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-23.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-29.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-29.c
index 650e6fe66a5..3b07a64e3f6 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-29.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-29.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-30.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-30.c
index dcec2c700fc..59595e6d3c4 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-30.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-30.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune-ctrl=avx256_store_by_pieces" }
*/
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-33.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-33.c
index a87d1b80ae6..68646223b0e 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-33.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-33.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-34.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-34.c
index 0c2f1ee6049..52a16a0292d 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-34.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-34.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune-ctrl=avx256_store_by_pieces" }
*/
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-37.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-37.c
index ec59497b116..fd09bd153ce 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-37.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-37.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune=generic" } */
+/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune-ctrl=avx256_store_by_pieces" }
*/
void
foo (int a1, int a2, int a3, int a4, int a5, int a6, int x, char *dst)
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-44.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-44.c
index ecc31be1a34..5986f8e8b23 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-44.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-44.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-5.c
b/gcc/testsuite/gcc.target/i386/pieces-memset-5.c
index 3e95db5efef..e2379df71aa 100644
--- a/gcc/testsuite/gcc.target/i386/pieces-memset-5.c
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-5.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pr100865-10a.c
b/gcc/testsuite/gcc.target/i386/pr100865-10a.c
index 98b6dfb16f3..1d849a381c0 100644
--- a/gcc/testsuite/gcc.target/i386/pr100865-10a.c
+++ b/gcc/testsuite/gcc.target/i386/pr100865-10a.c
@@ -1,5 +1,5 @@
/* { dg-do compile { target int128 } } */
-/* { dg-options "-O3 -march=skylake" } */
+/* { dg-options "-O3 -march=skylake -mtune-ctrl=avx256_store_by_pieces" } */
extern __int128 array[16];
diff --git a/gcc/testsuite/gcc.target/i386/pr100865-4a.c
b/gcc/testsuite/gcc.target/i386/pr100865-4a.c
index 365487337ae..8609d1128b8 100644
--- a/gcc/testsuite/gcc.target/i386/pr100865-4a.c
+++ b/gcc/testsuite/gcc.target/i386/pr100865-4a.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -march=skylake" } */
+/* { dg-options "-O2 -march=skylake -mtune-ctrl=avx256_store_by_pieces" } */
extern char array[64];
diff --git a/gcc/testsuite/gcc.target/i386/pr90773-20.c
b/gcc/testsuite/gcc.target/i386/pr90773-20.c
index e61e405f2b6..884a5502b59 100644
--- a/gcc/testsuite/gcc.target/i386/pr90773-20.c
+++ b/gcc/testsuite/gcc.target/i386/pr90773-20.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -march=skylake" } */
+/* { dg-options "-O2 -march=skylake -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pr90773-21.c
b/gcc/testsuite/gcc.target/i386/pr90773-21.c
index 16ad17f3cbb..5bbb387a3ea 100644
--- a/gcc/testsuite/gcc.target/i386/pr90773-21.c
+++ b/gcc/testsuite/gcc.target/i386/pr90773-21.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -march=skylake" } */
+/* { dg-options "-O2 -march=skylake -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pr90773-22.c
b/gcc/testsuite/gcc.target/i386/pr90773-22.c
index 45a8ff65a84..245a436b7eb 100644
--- a/gcc/testsuite/gcc.target/i386/pr90773-22.c
+++ b/gcc/testsuite/gcc.target/i386/pr90773-22.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -march=skylake" } */
+/* { dg-options "-O2 -march=skylake -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pr90773-23.c
b/gcc/testsuite/gcc.target/i386/pr90773-23.c
index 9256ce10ff0..ca4a86f30b8 100644
--- a/gcc/testsuite/gcc.target/i386/pr90773-23.c
+++ b/gcc/testsuite/gcc.target/i386/pr90773-23.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -march=skylake" } */
+/* { dg-options "-O2 -march=skylake -mtune-ctrl=avx256_store_by_pieces" } */
extern char *dst;
diff --git a/gcc/testsuite/gcc.target/i386/pr90773-26.c
b/gcc/testsuite/gcc.target/i386/pr90773-26.c
index b2513c3a9c8..76fb79f2e20 100644
--- a/gcc/testsuite/gcc.target/i386/pr90773-26.c
+++ b/gcc/testsuite/gcc.target/i386/pr90773-26.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -march=skylake" } */
+/* { dg-options "-O2 -march=skylake -mtune-ctrl=avx256_move_by_pieces" } */
struct S
{
--
2.31.1