Message ID | Yiz0cP7Ta5bSNKzG@tucnak |
---|---|
State | New |
Headers | show |
Series | i386: Fix up _mm_loadu_si{16,32} [PR99754] | expand |
On Sun, Mar 13, 2022 at 3:28 AM Jakub Jelinek <jakub@redhat.com> wrote: > > Hi! > > These intrinsics are supposed to do an unaligned may_alias load > of a 16-bit or 32-bit value and store it as the first element of > a 128-bit integer vector, with all other elements cleared. > > The current _mm_storeu_* implementation implements that correctly, uses > __*_u types to do the store and extracts the first element of a vector into > it. > But _mm_loadu_si{16,32} gets it all wrong. It performs an aligned > non-may_alias load and because _mm_set_epi{16,32} has the args reversed, > it also inserts it into the last vector element instead of first. > > The following patch fixes that, bootstrapped/regtested on x86_64-linux > and i686-linux, ok for trunk and affected release branches? LGTM, thanks for handling this. > > Note, while the Intrinsics guide for _mm_loadu_si32 says SSE2, > for _mm_loadu_si16 it says strangely SSE. But the intrinsics > returns __m128i, which is only defined in emmintrin.h, and > _mm_set_epi16 is also only SSE2 and later in emmintrin.h. > Even clang defines it in emmintrin.h and ends up with inlining > failure when calling _mm_loadu_si16 from sse,no-sse2 function. > So, isn't that a bug in the intrinsic guide instead? I think it's a bug, it's supposed to generate movzx + movd, and movd is under sse2, and have reported it to the colleague who maintains Intel intrinsic guide. Similar bug for _mm_loadu_si64 _mm_storeu_si16 _mm_storeu_si64 > > 2022-03-12 Jakub Jelinek <jakub@redhat.com> > > PR target/99754 > * config/i386/emmintrin.h (_mm_loadu_si32): Put loaded value into > first rather than last element of the vector, use __m32_u to do > a really unaligned load, use just 0 instead of (int)0. > (_mm_loadu_si16): Put loaded value into first rather than last > element of the vector, use __m16_u to do a really unaligned load, > use just 0 instead of (short)0. > > * gcc.target/i386/pr99754-1.c: New test. > * gcc.target/i386/pr99754-2.c: New test. > > --- gcc/config/i386/emmintrin.h.jj 2022-01-11 23:11:21.766298923 +0100 > +++ gcc/config/i386/emmintrin.h 2022-03-11 16:47:24.789884825 +0100 > @@ -718,14 +718,13 @@ _mm_loadu_si64 (void const *__P) > extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__)) > _mm_loadu_si32 (void const *__P) > { > - return _mm_set_epi32 (*(int *)__P, (int)0, (int)0, (int)0); > + return _mm_set_epi32 (0, 0, 0, (*(__m32_u *)__P)[0]); > } > > extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__)) > _mm_loadu_si16 (void const *__P) > { > - return _mm_set_epi16 (*(short *)__P, (short)0, (short)0, (short)0, > - (short)0, (short)0, (short)0, (short)0); > + return _mm_set_epi16 (0, 0, 0, 0, 0, 0, 0, (*(__m16_u *)__P)[0]); > } > > extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__)) > --- gcc/testsuite/gcc.target/i386/pr99754-1.c.jj 2022-03-11 16:43:30.621120896 +0100 > +++ gcc/testsuite/gcc.target/i386/pr99754-1.c 2022-03-11 16:43:18.250291856 +0100 > @@ -0,0 +1,20 @@ > +/* PR target/99754 */ > +/* { dg-do run } */ > +/* { dg-options "-O2 -msse2" } */ > +/* { dg-require-effective-target sse2 } */ > + > +#include "sse2-check.h" > +#include <emmintrin.h> > + > +static void > +sse2_test (void) > +{ > + union { unsigned char buf[32]; long long ll; } u; > + u.buf[1] = 0xfe; > + u.buf[2] = 0xca; > + u.buf[17] = 0xaa; > + u.buf[18] = 0x55; > + _mm_storeu_si16 (&u.buf[17], _mm_loadu_si16 (&u.buf[1])); > + if (u.buf[17] != 0xfe || u.buf[18] != 0xca) > + abort (); > +} > --- gcc/testsuite/gcc.target/i386/pr99754-2.c.jj 2022-03-11 16:43:41.701967763 +0100 > +++ gcc/testsuite/gcc.target/i386/pr99754-2.c 2022-03-11 16:45:16.391659211 +0100 > @@ -0,0 +1,24 @@ > +/* PR target/99754 */ > +/* { dg-do run } */ > +/* { dg-options "-O2 -msse2" } */ > +/* { dg-require-effective-target sse2 } */ > + > +#include "sse2-check.h" > +#include <emmintrin.h> > + > +static void > +sse2_test (void) > +{ > + union { unsigned char buf[32]; long long ll; } u; > + u.buf[1] = 0xbe; > + u.buf[2] = 0xba; > + u.buf[3] = 0xfe; > + u.buf[4] = 0xca; > + u.buf[17] = 0xaa; > + u.buf[18] = 0x55; > + u.buf[19] = 0xaa; > + u.buf[20] = 0x55; > + _mm_storeu_si32 (&u.buf[17], _mm_loadu_si32 (&u.buf[1])); > + if (u.buf[17] != 0xbe || u.buf[18] != 0xba || u.buf[19] != 0xfe || u.buf[20] != 0xca) > + abort (); > +} > > Jakub >
On Sun, Mar 13, 2022 at 09:34:10PM +0800, Hongtao Liu wrote: > LGTM, thanks for handling this. Thanks, committed. > > Note, while the Intrinsics guide for _mm_loadu_si32 says SSE2, > > for _mm_loadu_si16 it says strangely SSE. But the intrinsics > > returns __m128i, which is only defined in emmintrin.h, and > > _mm_set_epi16 is also only SSE2 and later in emmintrin.h. > > Even clang defines it in emmintrin.h and ends up with inlining > > failure when calling _mm_loadu_si16 from sse,no-sse2 function. > > So, isn't that a bug in the intrinsic guide instead? > I think it's a bug, it's supposed to generate movzx + movd, and movd > is under sse2, and have reported it to the colleague who maintains > Intel intrinsic guide. > > Similar bug for > _mm_loadu_si64 > _mm_storeu_si16 > _mm_storeu_si64 Currently it emits pxor + pinsrw, but even those are SSE2 instructions, unless they use a MMX register (then it is MMX and SSE). I agree that movzwl + movd seems better than pxor + pinsrw though. So, do we want to help it a little bit then? Like: 2022-03-14 Jakub Jelinek <jakub@redhat.com> * config/i386/eemintrin.h (_mm_loadu_si16): Use _mm_set_epi32 instead of _mm_set_epi16 and zero extend the memory load. * gcc.target/i386/pr95483-1.c: Use -msse2 instead of -msse in dg-options, allow movzwl+movd instead of pxor with pinsrw. --- gcc/config/i386/emmintrin.h.jj 2022-03-14 10:44:29.402617685 +0100 +++ gcc/config/i386/emmintrin.h 2022-03-14 11:58:18.062666257 +0100 @@ -724,7 +724,7 @@ _mm_loadu_si32 (void const *__P) extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__)) _mm_loadu_si16 (void const *__P) { - return _mm_set_epi16 (0, 0, 0, 0, 0, 0, 0, (*(__m16_u *)__P)[0]); + return _mm_set_epi32 (0, 0, 0, (unsigned short) ((*(__m16_u *)__P)[0])); } extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__)) --- gcc/testsuite/gcc.target/i386/pr95483-1.c.jj 2020-10-14 22:05:19.380856952 +0200 +++ gcc/testsuite/gcc.target/i386/pr95483-1.c 2022-03-14 12:11:07.716891710 +0100 @@ -1,7 +1,7 @@ /* { dg-do compile } */ -/* { dg-options "-O2 -msse" } */ -/* { dg-final { scan-assembler-times "pxor\[ \\t\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */ -/* { dg-final { scan-assembler-times "pinsrw\[ \\t\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */ +/* { dg-options "-O2 -msse2" } */ +/* { dg-final { scan-assembler-times "(?:movzwl\[ \\t\]+\[^\n\]*|pxor\[ \\t\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+)(?:\n|\[ \\t\]+#)" 1 } } */ +/* { dg-final { scan-assembler-times "(?:movd|pinsrw)\[ \\t\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */ /* { dg-final { scan-assembler-times "pextrw\[ \\t\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*(?:\n|\[ \\t\]+#)" 1 } } */ Jakub
On Mon, Mar 14, 2022 at 7:25 PM Jakub Jelinek <jakub@redhat.com> wrote: > > On Sun, Mar 13, 2022 at 09:34:10PM +0800, Hongtao Liu wrote: > > LGTM, thanks for handling this. > > Thanks, committed. > > > > Note, while the Intrinsics guide for _mm_loadu_si32 says SSE2, > > > for _mm_loadu_si16 it says strangely SSE. But the intrinsics > > > returns __m128i, which is only defined in emmintrin.h, and > > > _mm_set_epi16 is also only SSE2 and later in emmintrin.h. > > > Even clang defines it in emmintrin.h and ends up with inlining > > > failure when calling _mm_loadu_si16 from sse,no-sse2 function. > > > So, isn't that a bug in the intrinsic guide instead? > > I think it's a bug, it's supposed to generate movzx + movd, and movd > > is under sse2, and have reported it to the colleague who maintains > > Intel intrinsic guide. > > > > Similar bug for > > _mm_loadu_si64 > > _mm_storeu_si16 > > _mm_storeu_si64 > > Currently it emits pxor + pinsrw, but even those are SSE2 instructions, > unless they use a MMX register (then it is MMX and SSE). > I agree that movzwl + movd seems better than pxor + pinsrw though. > So, do we want to help it a little bit then? Like: > > 2022-03-14 Jakub Jelinek <jakub@redhat.com> > > * config/i386/eemintrin.h (_mm_loadu_si16): Use _mm_set_epi32 instead > of _mm_set_epi16 and zero extend the memory load. > > * gcc.target/i386/pr95483-1.c: Use -msse2 instead of -msse in > dg-options, allow movzwl+movd instead of pxor with pinsrw. > > --- gcc/config/i386/emmintrin.h.jj 2022-03-14 10:44:29.402617685 +0100 > +++ gcc/config/i386/emmintrin.h 2022-03-14 11:58:18.062666257 +0100 > @@ -724,7 +724,7 @@ _mm_loadu_si32 (void const *__P) > extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__)) > _mm_loadu_si16 (void const *__P) > { > - return _mm_set_epi16 (0, 0, 0, 0, 0, 0, 0, (*(__m16_u *)__P)[0]); > + return _mm_set_epi32 (0, 0, 0, (unsigned short) ((*(__m16_u *)__P)[0])); > } Under avx512fp16, the former directly generates vmovw, but the latter still generates movzx + vmovd. There's still a miss optimization. Thus I prefer to optimize it in the backend pxor + pinsrw -> movzx + movd -> vmovw (under avx512fp16). I'll open a PR for that and optimize it in GCC13. > > extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__)) > --- gcc/testsuite/gcc.target/i386/pr95483-1.c.jj 2020-10-14 22:05:19.380856952 +0200 > +++ gcc/testsuite/gcc.target/i386/pr95483-1.c 2022-03-14 12:11:07.716891710 +0100 > @@ -1,7 +1,7 @@ > /* { dg-do compile } */ > -/* { dg-options "-O2 -msse" } */ > -/* { dg-final { scan-assembler-times "pxor\[ \\t\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */ > -/* { dg-final { scan-assembler-times "pinsrw\[ \\t\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */ > +/* { dg-options "-O2 -msse2" } */ > +/* { dg-final { scan-assembler-times "(?:movzwl\[ \\t\]+\[^\n\]*|pxor\[ \\t\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+)(?:\n|\[ \\t\]+#)" 1 } } */ > +/* { dg-final { scan-assembler-times "(?:movd|pinsrw)\[ \\t\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */ > /* { dg-final { scan-assembler-times "pextrw\[ \\t\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*(?:\n|\[ \\t\]+#)" 1 } } */ > > > > > Jakub >
On Mon, Mar 14, 2022 at 8:20 PM Hongtao Liu <crazylht@gmail.com> wrote: > > On Mon, Mar 14, 2022 at 7:25 PM Jakub Jelinek <jakub@redhat.com> wrote: > > > > On Sun, Mar 13, 2022 at 09:34:10PM +0800, Hongtao Liu wrote: > > > LGTM, thanks for handling this. > > > > Thanks, committed. > > > > > > Note, while the Intrinsics guide for _mm_loadu_si32 says SSE2, > > > > for _mm_loadu_si16 it says strangely SSE. But the intrinsics > > > > returns __m128i, which is only defined in emmintrin.h, and > > > > _mm_set_epi16 is also only SSE2 and later in emmintrin.h. > > > > Even clang defines it in emmintrin.h and ends up with inlining > > > > failure when calling _mm_loadu_si16 from sse,no-sse2 function. > > > > So, isn't that a bug in the intrinsic guide instead? > > > I think it's a bug, it's supposed to generate movzx + movd, and movd > > > is under sse2, and have reported it to the colleague who maintains > > > Intel intrinsic guide. > > > > > > Similar bug for > > > _mm_loadu_si64 > > > _mm_storeu_si16 > > > _mm_storeu_si64 > > > > Currently it emits pxor + pinsrw, but even those are SSE2 instructions, > > unless they use a MMX register (then it is MMX and SSE). > > I agree that movzwl + movd seems better than pxor + pinsrw though. > > So, do we want to help it a little bit then? Like: > > > > 2022-03-14 Jakub Jelinek <jakub@redhat.com> > > > > * config/i386/eemintrin.h (_mm_loadu_si16): Use _mm_set_epi32 instead > > of _mm_set_epi16 and zero extend the memory load. > > > > * gcc.target/i386/pr95483-1.c: Use -msse2 instead of -msse in > > dg-options, allow movzwl+movd instead of pxor with pinsrw. > > > > --- gcc/config/i386/emmintrin.h.jj 2022-03-14 10:44:29.402617685 +0100 > > +++ gcc/config/i386/emmintrin.h 2022-03-14 11:58:18.062666257 +0100 > > @@ -724,7 +724,7 @@ _mm_loadu_si32 (void const *__P) > > extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__)) > > _mm_loadu_si16 (void const *__P) > > { > > - return _mm_set_epi16 (0, 0, 0, 0, 0, 0, 0, (*(__m16_u *)__P)[0]); > > + return _mm_set_epi32 (0, 0, 0, (unsigned short) ((*(__m16_u *)__P)[0])); > > } > Under avx512fp16, the former directly generates vmovw, but the latter > still generates movzx + vmovd. There's still a miss optimization. > Thus I prefer to optimize it in the backend pxor + pinsrw -> movzx + > movd -> vmovw (under avx512fp16). > I'll open a PR for that and optimize it in GCC13. PR104915. > > > > extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__)) > > --- gcc/testsuite/gcc.target/i386/pr95483-1.c.jj 2020-10-14 22:05:19.380856952 +0200 > > +++ gcc/testsuite/gcc.target/i386/pr95483-1.c 2022-03-14 12:11:07.716891710 +0100 > > @@ -1,7 +1,7 @@ > > /* { dg-do compile } */ > > -/* { dg-options "-O2 -msse" } */ > > -/* { dg-final { scan-assembler-times "pxor\[ \\t\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */ > > -/* { dg-final { scan-assembler-times "pinsrw\[ \\t\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */ > > +/* { dg-options "-O2 -msse2" } */ > > +/* { dg-final { scan-assembler-times "(?:movzwl\[ \\t\]+\[^\n\]*|pxor\[ \\t\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+)(?:\n|\[ \\t\]+#)" 1 } } */ > > +/* { dg-final { scan-assembler-times "(?:movd|pinsrw)\[ \\t\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */ > > /* { dg-final { scan-assembler-times "pextrw\[ \\t\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*(?:\n|\[ \\t\]+#)" 1 } } */ > > > > > > > > > > Jakub > > > > > -- > BR, > Hongtao
--- gcc/config/i386/emmintrin.h.jj 2022-01-11 23:11:21.766298923 +0100 +++ gcc/config/i386/emmintrin.h 2022-03-11 16:47:24.789884825 +0100 @@ -718,14 +718,13 @@ _mm_loadu_si64 (void const *__P) extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__)) _mm_loadu_si32 (void const *__P) { - return _mm_set_epi32 (*(int *)__P, (int)0, (int)0, (int)0); + return _mm_set_epi32 (0, 0, 0, (*(__m32_u *)__P)[0]); } extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__)) _mm_loadu_si16 (void const *__P) { - return _mm_set_epi16 (*(short *)__P, (short)0, (short)0, (short)0, - (short)0, (short)0, (short)0, (short)0); + return _mm_set_epi16 (0, 0, 0, 0, 0, 0, 0, (*(__m16_u *)__P)[0]); } extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__)) --- gcc/testsuite/gcc.target/i386/pr99754-1.c.jj 2022-03-11 16:43:30.621120896 +0100 +++ gcc/testsuite/gcc.target/i386/pr99754-1.c 2022-03-11 16:43:18.250291856 +0100 @@ -0,0 +1,20 @@ +/* PR target/99754 */ +/* { dg-do run } */ +/* { dg-options "-O2 -msse2" } */ +/* { dg-require-effective-target sse2 } */ + +#include "sse2-check.h" +#include <emmintrin.h> + +static void +sse2_test (void) +{ + union { unsigned char buf[32]; long long ll; } u; + u.buf[1] = 0xfe; + u.buf[2] = 0xca; + u.buf[17] = 0xaa; + u.buf[18] = 0x55; + _mm_storeu_si16 (&u.buf[17], _mm_loadu_si16 (&u.buf[1])); + if (u.buf[17] != 0xfe || u.buf[18] != 0xca) + abort (); +} --- gcc/testsuite/gcc.target/i386/pr99754-2.c.jj 2022-03-11 16:43:41.701967763 +0100 +++ gcc/testsuite/gcc.target/i386/pr99754-2.c 2022-03-11 16:45:16.391659211 +0100 @@ -0,0 +1,24 @@ +/* PR target/99754 */ +/* { dg-do run } */ +/* { dg-options "-O2 -msse2" } */ +/* { dg-require-effective-target sse2 } */ + +#include "sse2-check.h" +#include <emmintrin.h> + +static void +sse2_test (void) +{ + union { unsigned char buf[32]; long long ll; } u; + u.buf[1] = 0xbe; + u.buf[2] = 0xba; + u.buf[3] = 0xfe; + u.buf[4] = 0xca; + u.buf[17] = 0xaa; + u.buf[18] = 0x55; + u.buf[19] = 0xaa; + u.buf[20] = 0x55; + _mm_storeu_si32 (&u.buf[17], _mm_loadu_si32 (&u.buf[1])); + if (u.buf[17] != 0xbe || u.buf[18] != 0xba || u.buf[19] != 0xfe || u.buf[20] != 0xca) + abort (); +}