https://gcc.gnu.org/g:e5f8a39941f6f0f25dac88bd71fd368fb284a10f
commit r15-1678-ge5f8a39941f6f0f25dac88bd71fd368fb284a10f
Author: Hu, Lin1 <lin1...@intel.com>
Date: Wed Feb 28 18:11:55 2024 +0800
vect: Support v4hi -> v4qi.
gcc/ChangeLog:
PR target/107432
* config/i386/mmx.md
(VI2_32_64): New mode iterator.
(mmxhalfmode): New mode atter.
(mmxhalfmodelower): Ditto.
(truncv2hiv2qi2): Extend mode v4hi and change name from
truncv2hiv2qi to trunc<mode><mmxhalfmodelower>2.
gcc/testsuite/ChangeLog:
PR target/107432
* gcc.target/i386/pr107432-1.c: Modify test.
* gcc.target/i386/pr107432-6.c: Add test.
* gcc.target/i386/pr108938-3.c: This patch supports
truncv4hiv4qi affect bswap optimization, so I added
the -mno-avx option for now, and open a bugzilla.
Diff:
---
gcc/config/i386/mmx.md | 17 +++++++++++++----
gcc/testsuite/gcc.target/i386/pr107432-1.c | 13 ++++++++++++-
gcc/testsuite/gcc.target/i386/pr107432-6.c | 29 ++++++++++++++++++-----------
gcc/testsuite/gcc.target/i386/pr108938-3.c | 2 +-
4 files changed, 44 insertions(+), 17 deletions(-)
diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index ea53f516cbb..24c0516726c 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -67,6 +67,9 @@
;; 4-byte integer vector modes
(define_mode_iterator VI_32 [V4QI V2HI])
+;; 8-byte and 4-byte HImode vector modes
+(define_mode_iterator VI2_32_64 [(V4HI "TARGET_MMX_WITH_SSE") V2HI])
+
;; 4-byte and 2-byte integer vector modes
(define_mode_iterator VI_16_32 [V4QI V2QI V2HI])
@@ -106,6 +109,12 @@
(define_mode_attr mmxdoublemode
[(V8QI "V8HI") (V4HI "V4SI")])
+(define_mode_attr mmxhalfmode
+ [(V4HI "V4QI") (V2HI "V2QI")])
+
+(define_mode_attr mmxhalfmodelower
+ [(V4HI "v4qi") (V2HI "v2qi")])
+
;; Mapping of vector float modes to an integer mode of the same size
(define_mode_attr mmxintvecmode
[(V2SF "V2SI") (V2SI "V2SI") (V4HI "V4HI") (V8QI "V8QI")
@@ -4880,10 +4889,10 @@
DONE;
})
-(define_insn "truncv2hiv2qi2"
- [(set (match_operand:V2QI 0 "register_operand" "=v")
- (truncate:V2QI
- (match_operand:V2HI 1 "register_operand" "v")))]
+(define_insn "trunc<mode><mmxhalfmodelower>2"
+ [(set (match_operand:<mmxhalfmode> 0 "register_operand" "=v")
+ (truncate:<mmxhalfmode>
+ (match_operand:VI2_32_64 1 "register_operand" "v")))]
"TARGET_AVX512VL && TARGET_AVX512BW"
"vpmovwb\t{%1, %0|%0, %1}"
[(set_attr "type" "ssemov")
diff --git a/gcc/testsuite/gcc.target/i386/pr107432-1.c
b/gcc/testsuite/gcc.target/i386/pr107432-1.c
index a4f37447eb4..afdf367afe2 100644
--- a/gcc/testsuite/gcc.target/i386/pr107432-1.c
+++ b/gcc/testsuite/gcc.target/i386/pr107432-1.c
@@ -7,7 +7,8 @@
/* { dg-final { scan-assembler-times "vpmovdw" 8 { target { ! ia32 } } } } */
/* { dg-final { scan-assembler-times "vpmovdb" 6 { target { ia32 } } } } */
/* { dg-final { scan-assembler-times "vpmovdb" 8 { target { ! ia32 } } } } */
-/* { dg-final { scan-assembler-times "vpmovwb" 8 } } */
+/* { dg-final { scan-assembler-times "vpmovwb" 8 { target { ia32 } } } } */
+/* { dg-final { scan-assembler-times "vpmovwb" 10 { target { ! ia32 } } } } */
#include <x86intrin.h>
@@ -113,6 +114,11 @@ __v2qi mm32_cvtepi16_epi8_builtin_convertvector(__v2hi
a)
return __builtin_convertvector((__v2hi)a, __v2qi);
}
+__v4qi mm64_cvtepi16_epi8_builtin_convertvector(__v4hi a)
+{
+ return __builtin_convertvector((__v4hi)a, __v4qi);
+}
+
__v8qi mm_cvtepi16_epi8_builtin_convertvector(__m128i a)
{
return __builtin_convertvector((__v8hi)a, __v8qi);
@@ -218,6 +224,11 @@ __v2qu mm32_cvtepu16_epu8_builtin_convertvector(__v2hu
a)
return __builtin_convertvector((__v2hu)a, __v2qu);
}
+__v4qu mm64_cvtepu16_epu8_builtin_convertvector(__v4hu a)
+{
+ return __builtin_convertvector((__v4hu)a, __v4qu);
+}
+
__v8qu mm_cvtepu16_epu8_builtin_convertvector(__m128i a)
{
return __builtin_convertvector((__v8hu)a, __v8qu);
diff --git a/gcc/testsuite/gcc.target/i386/pr107432-6.c
b/gcc/testsuite/gcc.target/i386/pr107432-6.c
index 4a68a10b089..dd585b2a351 100644
--- a/gcc/testsuite/gcc.target/i386/pr107432-6.c
+++ b/gcc/testsuite/gcc.target/i386/pr107432-6.c
@@ -1,18 +1,15 @@
/* { dg-do compile } */
/* { dg-options "-mavx512fp16 -mavx512vl -mavx512bw -O2 -mavx512dq
-fno-trapping-math" } */
-/* { dg-final { scan-assembler-times "vcvttpd2dq" 2 { target { ia32 } } } } */
-/* { dg-final { scan-assembler-times "vcvttpd2dq" 3 { target { ! ia32 } } } }
*/
-/* { dg-final { scan-assembler-times "vcvttpd2udq" 2 { target { ia32 } } } } */
-/* { dg-final { scan-assembler-times "vcvttpd2udq" 3 { target { ! ia32 } } } }
*/
-/* { dg-final { scan-assembler-times "vcvttps2dq" 3 { target { ia32 } } } } */
-/* { dg-final { scan-assembler-times "vcvttps2dq" 4 { target { ! ia32 } } } }
*/
-/* { dg-final { scan-assembler-times "vcvttps2udq" 3 { target { ia32 } } } } */
-/* { dg-final { scan-assembler-times "vcvttps2udq" 4 { target { ! ia32 } } } }
*/
-/* { dg-final { scan-assembler-times "vcvttph2w" 4 } } */
-/* { dg-final { scan-assembler-times "vcvttph2uw" 4 } } */
+/* { dg-final { scan-assembler-times "vcvttpd2dq" 4 { target { ia32 } } } } */
+/* { dg-final { scan-assembler-times "vcvttpd2dq" 6 { target { ! ia32 } } } }
*/
+/* { dg-final { scan-assembler-times "vcvttps2dq" 6 { target { ia32 } } } } */
+/* { dg-final { scan-assembler-times "vcvttps2dq" 8 { target { ! ia32 } } } }
*/
+/* { dg-final { scan-assembler-times "vcvttph2w" 8 { target { ia32 } } } } */
+/* { dg-final { scan-assembler-times "vcvttph2w" 10 { target { ! ia32 } } } }
*/
/* { dg-final { scan-assembler-times "vpmovdb" 10 { target { ia32 } } } } */
/* { dg-final { scan-assembler-times "vpmovdb" 14 { target { ! ia32 } } } } */
-/* { dg-final { scan-assembler-times "vpmovwb" 8 } } */
+/* { dg-final { scan-assembler-times "vpmovwb" 8 { target { ia32 } } } } */
+/* { dg-final { scan-assembler-times "vpmovwb" 10 { target { ! ia32 } } } } */
#include <x86intrin.h>
@@ -103,6 +100,11 @@ __v2qi mm32_cvtph_epi8_builtin_convertvector(__v2hf a)
return __builtin_convertvector((__v2hf)a, __v2qi);
}
+__v4qi mm64_cvtph_epi8_builtin_convertvector(__v4hf a)
+{
+ return __builtin_convertvector((__v4hf)a, __v4qi);
+}
+
__v8qi mm128_cvtph_epi8_builtin_convertvector(__v8hf a)
{
return __builtin_convertvector((__v8hf)a, __v8qi);
@@ -123,6 +125,11 @@ __v2qu mm32_cvtph_epu8_builtin_convertvector(__v2hf a)
return __builtin_convertvector((__v2hf)a, __v2qu);
}
+__v4qu mm64_cvtph_epu8_builtin_convertvector(__v4hf a)
+{
+ return __builtin_convertvector((__v4hf)a, __v4qu);
+}
+
__v8qu mm128_cvtph_epu8_builtin_convertvector(__v8hf a)
{
return __builtin_convertvector((__v8hf)a, __v8qu);
diff --git a/gcc/testsuite/gcc.target/i386/pr108938-3.c
b/gcc/testsuite/gcc.target/i386/pr108938-3.c
index 32ac544c7ed..757a0c456bc 100644
--- a/gcc/testsuite/gcc.target/i386/pr108938-3.c
+++ b/gcc/testsuite/gcc.target/i386/pr108938-3.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -ftree-vectorize -mno-movbe" } */
+/* { dg-options "-O2 -ftree-vectorize -mno-movbe -mno-avx" } */
/* { dg-final { scan-assembler-times "bswap\[\t ]+" 2 { target { ! ia32 } } }
} */
/* { dg-final { scan-assembler-times "bswap\[\t ]+" 3 { target ia32 } } } */
