aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLili Cui <lili.cui@intel.com>2022-11-17 15:50:46 +0800
committerCui,Lili <lili.cui@intel.com>2022-11-17 16:27:34 +0800
commit156f523f9582f1e6bcce27ece03f2776960408c8 (patch)
treeb5c6f6263dfff3c0362563cdb6e4adb941c73bf1
parentcbe313060cdcf1d857d42a9e16a1a03e5ff89fff (diff)
downloadgcc-156f523f9582f1e6bcce27ece03f2776960408c8.zip
gcc-156f523f9582f1e6bcce27ece03f2776960408c8.tar.gz
gcc-156f523f9582f1e6bcce27ece03f2776960408c8.tar.bz2
x86: Enable 256 move by pieces for ALDERLAKE machine.
gcc/ChangeLog: * config/i386/x86-tune.def (X86_TUNE_AVX256_MOVE_BY_PIECES): Add alderlake. (X86_TUNE_AVX256_STORE_BY_PIECES): Ditto. gcc/testsuite/ChangeLog: * gcc.target/i386/pieces-memset-50.c: New test.
-rw-r--r--gcc/config/i386/x86-tune.def4
-rw-r--r--gcc/testsuite/gcc.target/i386/pieces-memset-50.c12
2 files changed, 14 insertions, 2 deletions
diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index 58e29e7..cd66f33 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -536,12 +536,12 @@ 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_CORE_AVX512)
+ m_ALDERLAKE | m_CORE_AVX2)
/* 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_CORE_AVX512)
+ m_ALDERLAKE | m_CORE_AVX2)
/* X86_TUNE_AVX512_MOVE_BY_PIECES: Optimize move_by_pieces with 512-bit
AVX instructions. */
diff --git a/gcc/testsuite/gcc.target/i386/pieces-memset-50.c b/gcc/testsuite/gcc.target/i386/pieces-memset-50.c
new file mode 100644
index 0000000..c09e7c3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pieces-memset-50.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=alderlake" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+ __builtin_memset (dst, x, 64);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */