On Thu, Jul 05, 2018 at 11:57:26PM +0300, Grazvydas Ignotas wrote:
> I think it would be more efficient if you took care of it. I won't
> have time for at least a few days anyway.
Here is what I have ATM, but will still need to work on the testsuite side
for it and bootstrap/regtest it.
In addition to the checks I've posted I've also done:
echo `sed -n '/^_mm.*__mmask/,/^}/p' config/i386/*.h | sed 's/^}/@@@/'` | sed
's/@@@/}\n/g' > /tmp/11
echo `sed -n '/^#define[ \t]_mm/,/)$/p' config/i386/*.h | sed 's/)$/@@@/' | sed
's/\\$//'` | sed 's/@@@/)\n/g' | grep __mmask >> /tmp/11
for i in `grep '__builtin.*_UQI)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask8; done
for i in `grep '__builtin.*_UHI)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask16; done
for i in `grep '__builtin.*_USI)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask32; done
for i in `grep '__builtin.*_UDI)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask64; done
for i in `grep '__builtin.*_QI)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask8; done
for i in `grep '__builtin.*_HI)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask16; done
for i in `grep '__builtin.*_SI)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask32; done
for i in `grep '__builtin.*_DI)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask64; done
for i in `grep '__builtin.*_UQI_INT)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask8; done
for i in `grep '__builtin.*_UHI_INT)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask16; done
for i in `grep '__builtin.*_USI_INT)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask32; done
for i in `grep '__builtin.*_UDI_INT)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask64; done
for i in `grep '__builtin.*_QI_INT)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask8; done
for i in `grep '__builtin.*_HI_INT)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask16; done
for i in `grep '__builtin.*_SI_INT)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask32; done
for i in `grep '__builtin.*_DI_INT)' config/i386/i386-builtin.def | sed
's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[ \t(].*__mmask' /tmp/11 | grep
-v __mmask64; done
and finally manual checking (could be automated too) of:
for i in `grep '__builtin.*_INT)' config/i386/i386-builtin.def | grep -v
'_U\?[QHSD]I_INT)' | sed 's/^[^"]*"//;s/".*$//' | sort -u`; do grep $i'[
\t(].*__mmask' /tmp/11 | grep -v __mmask32; done
For this last one, it is about trying to verify what kind of
'__v\(2\|4\|8\|16\|32\|64\)[qhsd][if]'
is used with the different __mmask, 2/4/8 should be used with __mmask8,
16 with __mmask16, 32 with __mmask32 and 64 with __mmask64.
Some fixes in the patch are mostly for consistency and harmless for code
generation (e.g. when argument should have been __mmask8 but was __mmask16),
but several changes should fix wrong-code bugs.
--- gcc/config/i386/avx512bwintrin.h.jj 2018-01-03 10:20:06.699535804 +0100
+++ gcc/config/i386/avx512bwintrin.h 2018-07-06 09:53:44.657235040 +0200
@@ -3043,7 +3043,7 @@ _mm512_cmp_epi16_mask (__m512i __X, __m5
extern __inline __mmask64
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_cmp_epi8_mask (__mmask32 __U, __m512i __X, __m512i __Y,
+_mm512_mask_cmp_epi8_mask (__mmask64 __U, __m512i __X, __m512i __Y,
const int __P)
{
return (__mmask64) __builtin_ia32_cmpb512_mask ((__v64qi) __X,
@@ -3081,7 +3081,7 @@ _mm512_cmp_epu16_mask (__m512i __X, __m5
extern __inline __mmask64
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_cmp_epu8_mask (__mmask32 __U, __m512i __X, __m512i __Y,
+_mm512_mask_cmp_epu8_mask (__mmask64 __U, __m512i __X, __m512i __Y,
const int __P)
{
return (__mmask64) __builtin_ia32_ucmpb512_mask ((__v64qi) __X,
--- gcc/config/i386/avx512bitalgintrin.h.jj 2018-01-26 12:43:26.374922539
+0100
+++ gcc/config/i386/avx512bitalgintrin.h 2018-07-06 09:51:19.536082408
+0200
@@ -107,7 +107,7 @@ _mm512_bitshuffle_epi64_mask (__m512i __
extern __inline __mmask64
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_bitshuffle_epi64_mask (__mmask8 __M, __m512i __A, __m512i __B)
+_mm512_mask_bitshuffle_epi64_mask (__mmask64 __M, __m512i __A, __m512i __B)
{
return (__mmask64) __builtin_ia32_vpshufbitqmb512_mask ((__v64qi) __A,
(__v64qi) __B,
--- gcc/config/i386/avx512fintrin.h.jj 2018-05-21 13:15:43.494581775 +0200
+++ gcc/config/i386/avx512fintrin.h 2018-07-06 11:41:19.879801396 +0200
@@ -7377,7 +7377,7 @@ _mm512_xor_epi64 (__m512i __A, __m512i _
extern __inline __m512i
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_xor_epi64 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+_mm512_mask_xor_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
{
return (__m512i) __builtin_ia32_pxorq512_mask ((__v8di) __A,
(__v8di) __B,
@@ -7387,7 +7387,7 @@ _mm512_mask_xor_epi64 (__m512i __W, __mm
extern __inline __m512i
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_maskz_xor_epi64 (__mmask16 __U, __m512i __A, __m512i __B)
+_mm512_maskz_xor_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
{
return (__m512i) __builtin_ia32_pxorq512_mask ((__v8di) __A,
(__v8di) __B,
@@ -9615,7 +9615,7 @@ _mm512_cmpneq_epu32_mask (__m512i __X, _
extern __inline __mmask8
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm512_mask_cmpneq_epi64_mask (__mmask16 __M, __m512i __X, __m512i __Y)
+_mm512_mask_cmpneq_epi64_mask (__mmask8 __M, __m512i __X, __m512i __Y)
{
return (__mmask8) __builtin_ia32_cmpq512_mask ((__v8di) __X,
(__v8di) __Y, 4,
@@ -10877,22 +10877,22 @@ _mm512_mask_insertf32x4 (__m512 __A, __m
#define _mm512_maskz_insertf32x4(A, X, Y, C) \
((__m512) __builtin_ia32_insertf32x4_mask ((__v16sf)(__m512) (X), \
(__v4sf)(__m128) (Y), (int) (C), (__v16sf)_mm512_setzero_ps(), \
- (__mmask8)(A)))
+ (__mmask16)(A)))
#define _mm512_maskz_inserti32x4(A, X, Y, C) \
((__m512i) __builtin_ia32_inserti32x4_mask ((__v16si)(__m512i) (X), \
(__v4si)(__m128i) (Y), (int) (C), (__v16si)_mm512_setzero_si512 (), \
- (__mmask8)(A)))
+ (__mmask16)(A)))
#define _mm512_mask_insertf32x4(A, B, X, Y, C) \
((__m512) __builtin_ia32_insertf32x4_mask ((__v16sf)(__m512) (X), \
(__v4sf)(__m128) (Y), (int) (C), (__v16sf)(__m512) (A), \
- (__mmask8)(B)))
+ (__mmask16)(B)))
#define _mm512_mask_inserti32x4(A, B, X, Y, C) \
((__m512i) __builtin_ia32_inserti32x4_mask ((__v16si)(__m512i) (X), \
(__v4si)(__m128i) (Y), (int) (C), (__v16si)(__m512i) (A), \
- (__mmask8)(B)))
+ (__mmask16)(B)))
#endif
extern __inline __m512i
--- gcc/config/i386/avx512vlintrin.h.jj 2018-01-03 10:20:06.152535716 +0100
+++ gcc/config/i386/avx512vlintrin.h 2018-07-06 10:13:02.209506028 +0200
@@ -466,7 +466,7 @@ _mm256_maskz_add_pd (__mmask8 __U, __m25
extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_add_ps (__m128 __W, __mmask16 __U, __m128 __A, __m128 __B)
+_mm_mask_add_ps (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_addps128_mask ((__v4sf) __A,
(__v4sf) __B,
@@ -476,7 +476,7 @@ _mm_mask_add_ps (__m128 __W, __mmask16 _
extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maskz_add_ps (__mmask16 __U, __m128 __A, __m128 __B)
+_mm_maskz_add_ps (__mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_addps128_mask ((__v4sf) __A,
(__v4sf) __B,
@@ -487,7 +487,7 @@ _mm_maskz_add_ps (__mmask16 __U, __m128
extern __inline __m256
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_add_ps (__m256 __W, __mmask16 __U, __m256 __A, __m256 __B)
+_mm256_mask_add_ps (__m256 __W, __mmask8 __U, __m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_addps256_mask ((__v8sf) __A,
(__v8sf) __B,
@@ -497,7 +497,7 @@ _mm256_mask_add_ps (__m256 __W, __mmask1
extern __inline __m256
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_maskz_add_ps (__mmask16 __U, __m256 __A, __m256 __B)
+_mm256_maskz_add_ps (__mmask8 __U, __m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_addps256_mask ((__v8sf) __A,
(__v8sf) __B,
@@ -551,7 +551,7 @@ _mm256_maskz_sub_pd (__mmask8 __U, __m25
extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_sub_ps (__m128 __W, __mmask16 __U, __m128 __A, __m128 __B)
+_mm_mask_sub_ps (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_subps128_mask ((__v4sf) __A,
(__v4sf) __B,
@@ -561,7 +561,7 @@ _mm_mask_sub_ps (__m128 __W, __mmask16 _
extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maskz_sub_ps (__mmask16 __U, __m128 __A, __m128 __B)
+_mm_maskz_sub_ps (__mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_subps128_mask ((__v4sf) __A,
(__v4sf) __B,
@@ -572,7 +572,7 @@ _mm_maskz_sub_ps (__mmask16 __U, __m128
extern __inline __m256
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_sub_ps (__m256 __W, __mmask16 __U, __m256 __A, __m256 __B)
+_mm256_mask_sub_ps (__m256 __W, __mmask8 __U, __m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_subps256_mask ((__v8sf) __A,
(__v8sf) __B,
@@ -582,7 +582,7 @@ _mm256_mask_sub_ps (__m256 __W, __mmask1
extern __inline __m256
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_maskz_sub_ps (__mmask16 __U, __m256 __A, __m256 __B)
+_mm256_maskz_sub_ps (__mmask8 __U, __m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_subps256_mask ((__v8sf) __A,
(__v8sf) __B,
@@ -1320,7 +1320,7 @@ _mm256_mask_cvtepi32_ps (__m256 __W, __m
extern __inline __m256
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_maskz_cvtepi32_ps (__mmask16 __U, __m256i __A)
+_mm256_maskz_cvtepi32_ps (__mmask8 __U, __m256i __A)
{
return (__m256) __builtin_ia32_cvtdq2ps256_mask ((__v8si) __A,
(__v8sf)
@@ -1339,7 +1339,7 @@ _mm_mask_cvtepi32_ps (__m128 __W, __mmas
extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_maskz_cvtepi32_ps (__mmask16 __U, __m128i __A)
+_mm_maskz_cvtepi32_ps (__mmask8 __U, __m128i __A)
{
return (__m128) __builtin_ia32_cvtdq2ps128_mask ((__v4si) __A,
(__v4sf)
--- gcc/config/i386/avx512vlbwintrin.h.jj 2018-01-03 10:20:06.598535787
+0100
+++ gcc/config/i386/avx512vlbwintrin.h 2018-07-06 12:16:56.109933815 +0200
@@ -1467,7 +1467,7 @@ _mm256_cmp_epi16_mask (__m256i __X, __m2
extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_cmp_epi8_mask (__mmask8 __U, __m128i __X, __m128i __Y,
+_mm_mask_cmp_epi8_mask (__mmask16 __U, __m128i __X, __m128i __Y,
const int __P)
{
return (__mmask16) __builtin_ia32_cmpb128_mask ((__v16qi) __X,
@@ -1486,7 +1486,7 @@ _mm_cmp_epi8_mask (__m128i __X, __m128i
extern __inline __mmask32
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmp_epi8_mask (__mmask16 __U, __m256i __X, __m256i __Y,
+_mm256_mask_cmp_epi8_mask (__mmask32 __U, __m256i __X, __m256i __Y,
const int __P)
{
return (__mmask32) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
@@ -1543,7 +1543,7 @@ _mm256_cmp_epu16_mask (__m256i __X, __m2
extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_cmp_epu8_mask (__mmask8 __U, __m128i __X, __m128i __Y,
+_mm_mask_cmp_epu8_mask (__mmask16 __U, __m128i __X, __m128i __Y,
const int __P)
{
return (__mmask16) __builtin_ia32_ucmpb128_mask ((__v16qi) __X,
@@ -1562,7 +1562,7 @@ _mm_cmp_epu8_mask (__m128i __X, __m128i
extern __inline __mmask32
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmp_epu8_mask (__mmask16 __U, __m256i __X, __m256i __Y,
+_mm256_mask_cmp_epu8_mask (__mmask32 __U, __m256i __X, __m256i __Y,
const int __P)
{
return (__mmask32) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
@@ -1998,7 +1998,7 @@ _mm_maskz_slli_epi16 (__mmask8 __U, __m1
#define _mm_mask_cmp_epi16_mask(M, X, Y, P) \
((__mmask8) __builtin_ia32_cmpw128_mask ((__v8hi)(__m128i)(X), \
(__v8hi)(__m128i)(Y), (int)(P),\
- (__mmask16)(M)))
+ (__mmask8)(M)))
#define _mm_mask_cmp_epi8_mask(M, X, Y, P) \
((__mmask16) __builtin_ia32_cmpb128_mask ((__v16qi)(__m128i)(X), \
@@ -2430,7 +2430,7 @@ _mm_maskz_mullo_epi16 (__mmask8 __U, __m
extern __inline __m256i
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cvtepi8_epi16 (__m256i __W, __mmask32 __U, __m128i __A)
+_mm256_mask_cvtepi8_epi16 (__m256i __W, __mmask16 __U, __m128i __A)
{
return (__m256i) __builtin_ia32_pmovsxbw256_mask ((__v16qi) __A,
(__v16hi) __W,
@@ -2449,7 +2449,7 @@ _mm256_maskz_cvtepi8_epi16 (__mmask16 __
extern __inline __m128i
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_cvtepi8_epi16 (__m128i __W, __mmask32 __U, __m128i __A)
+_mm_mask_cvtepi8_epi16 (__m128i __W, __mmask8 __U, __m128i __A)
{
return (__m128i) __builtin_ia32_pmovsxbw128_mask ((__v16qi) __A,
(__v8hi) __W,
@@ -2468,7 +2468,7 @@ _mm_maskz_cvtepi8_epi16 (__mmask8 __U, _
extern __inline __m256i
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cvtepu8_epi16 (__m256i __W, __mmask32 __U, __m128i __A)
+_mm256_mask_cvtepu8_epi16 (__m256i __W, __mmask16 __U, __m128i __A)
{
return (__m256i) __builtin_ia32_pmovzxbw256_mask ((__v16qi) __A,
(__v16hi) __W,
@@ -2487,7 +2487,7 @@ _mm256_maskz_cvtepu8_epi16 (__mmask16 __
extern __inline __m128i
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_cvtepu8_epi16 (__m128i __W, __mmask32 __U, __m128i __A)
+_mm_mask_cvtepu8_epi16 (__m128i __W, __mmask8 __U, __m128i __A)
{
return (__m128i) __builtin_ia32_pmovzxbw128_mask ((__v16qi) __A,
(__v8hi) __W,
@@ -4541,148 +4541,148 @@ _mm_mask_cmple_epi16_mask (__mmask8 __M,
(__mmask8) __M);
}
-extern __inline __mmask8
+extern __inline __mmask32
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpneq_epu8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpneq_epu8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
- (__v32qi) __Y, 4,
- (__mmask8) __M);
+ return (__mmask32) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
+ (__v32qi) __Y, 4,
+ (__mmask32) __M);
}
-extern __inline __mmask8
+extern __inline __mmask32
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmplt_epu8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmplt_epu8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
- (__v32qi) __Y, 1,
- (__mmask8) __M);
+ return (__mmask32) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
+ (__v32qi) __Y, 1,
+ (__mmask32) __M);
}
-extern __inline __mmask8
+extern __inline __mmask32
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpge_epu8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpge_epu8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
- (__v32qi) __Y, 5,
- (__mmask8) __M);
+ return (__mmask32) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
+ (__v32qi) __Y, 5,
+ (__mmask32) __M);
}
-extern __inline __mmask8
+extern __inline __mmask32
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmple_epu8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmple_epu8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
- (__v32qi) __Y, 2,
- (__mmask8) __M);
+ return (__mmask32) __builtin_ia32_ucmpb256_mask ((__v32qi) __X,
+ (__v32qi) __Y, 2,
+ (__mmask32) __M);
}
-extern __inline __mmask8
+extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpneq_epu16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpneq_epu16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
- (__v16hi) __Y, 4,
- (__mmask8) __M);
+ return (__mmask16) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
+ (__v16hi) __Y, 4,
+ (__mmask16) __M);
}
-extern __inline __mmask8
+extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmplt_epu16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmplt_epu16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
- (__v16hi) __Y, 1,
- (__mmask8) __M);
+ return (__mmask16) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
+ (__v16hi) __Y, 1,
+ (__mmask16) __M);
}
-extern __inline __mmask8
+extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpge_epu16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpge_epu16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
- (__v16hi) __Y, 5,
- (__mmask8) __M);
+ return (__mmask16) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
+ (__v16hi) __Y, 5,
+ (__mmask16) __M);
}
-extern __inline __mmask8
+extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmple_epu16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmple_epu16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
- (__v16hi) __Y, 2,
- (__mmask8) __M);
+ return (__mmask16) __builtin_ia32_ucmpw256_mask ((__v16hi) __X,
+ (__v16hi) __Y, 2,
+ (__mmask16) __M);
}
-extern __inline __mmask8
+extern __inline __mmask32
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpneq_epi8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpneq_epi8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
- (__v32qi) __Y, 4,
- (__mmask8) __M);
+ return (__mmask32) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
+ (__v32qi) __Y, 4,
+ (__mmask32) __M);
}
-extern __inline __mmask8
+extern __inline __mmask32
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmplt_epi8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmplt_epi8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
- (__v32qi) __Y, 1,
- (__mmask8) __M);
+ return (__mmask32) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
+ (__v32qi) __Y, 1,
+ (__mmask32) __M);
}
-extern __inline __mmask8
+extern __inline __mmask32
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpge_epi8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpge_epi8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
- (__v32qi) __Y, 5,
- (__mmask8) __M);
+ return (__mmask32) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
+ (__v32qi) __Y, 5,
+ (__mmask32) __M);
}
-extern __inline __mmask8
+extern __inline __mmask32
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmple_epi8_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmple_epi8_mask (__mmask32 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
- (__v32qi) __Y, 2,
- (__mmask8) __M);
+ return (__mmask32) __builtin_ia32_cmpb256_mask ((__v32qi) __X,
+ (__v32qi) __Y, 2,
+ (__mmask32) __M);
}
-extern __inline __mmask8
+extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpneq_epi16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpneq_epi16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
- (__v16hi) __Y, 4,
- (__mmask8) __M);
+ return (__mmask16) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
+ (__v16hi) __Y, 4,
+ (__mmask16) __M);
}
-extern __inline __mmask8
+extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmplt_epi16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmplt_epi16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
- (__v16hi) __Y, 1,
- (__mmask8) __M);
+ return (__mmask16) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
+ (__v16hi) __Y, 1,
+ (__mmask16) __M);
}
-extern __inline __mmask8
+extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmpge_epi16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmpge_epi16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
- (__v16hi) __Y, 5,
- (__mmask8) __M);
+ return (__mmask16) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
+ (__v16hi) __Y, 5,
+ (__mmask16) __M);
}
-extern __inline __mmask8
+extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm256_mask_cmple_epi16_mask (__mmask8 __M, __m256i __X, __m256i __Y)
+_mm256_mask_cmple_epi16_mask (__mmask16 __M, __m256i __X, __m256i __Y)
{
- return (__mmask8) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
- (__v16hi) __Y, 2,
- (__mmask8) __M);
+ return (__mmask16) __builtin_ia32_cmpw256_mask ((__v16hi) __X,
+ (__v16hi) __Y, 2,
+ (__mmask16) __M);
}
#ifdef __DISABLE_AVX512VLBW__
--- gcc/config/i386/avx512vbmi2vlintrin.h.jj 2018-01-03 10:20:06.085535705
+0100
+++ gcc/config/i386/avx512vbmi2vlintrin.h 2018-07-06 12:09:13.797471324
+0200
@@ -541,7 +541,7 @@ _mm_shldi_epi64 (__m128i __A, __m128i __
(__v4si)(__m128i)(B),(int)(C))
#define _mm_mask_shrdi_epi32(A, B, C, D, E) \
((__m128i) __builtin_ia32_vpshrd_v4si_mask ((__v4si)(__m128i)(C), \
- (__v4si)(__m128i)(D), (int)(E), (__v4si)(__m128i)(A),(__mmask16)(B))
+ (__v4si)(__m128i)(D), (int)(E), (__v4si)(__m128i)(A),(__mmask8)(B))
#define _mm_maskz_shrdi_epi32(A, B, C, D) \
((__m128i) __builtin_ia32_vpshrd_v4si_mask ((__v4si)(__m128i)(B), \
(__v4si)(__m128i)(C),(int)(D), \
@@ -601,7 +601,7 @@ _mm_shldi_epi64 (__m128i __A, __m128i __
(__v4si)(__m128i)(B),(int)(C))
#define _mm_mask_shldi_epi32(A, B, C, D, E) \
((__m128i) __builtin_ia32_vpshld_v4si_mask ((__v4si)(__m128i)(C), \
- (__v4si)(__m128i)(D), (int)(E), (__v4si)(__m128i)(A),(__mmask16)(B))
+ (__v4si)(__m128i)(D), (int)(E), (__v4si)(__m128i)(A),(__mmask8)(B))
#define _mm_maskz_shldi_epi32(A, B, C, D) \
((__m128i) __builtin_ia32_vpshld_v4si_mask ((__v4si)(__m128i)(B), \
(__v4si)(__m128i)(C),(int)(D), \
Jakub
