maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[Clang][Intrinsics][AVX512][BuiltIn] adding intrinsics for vrangesd instruction set 

Differential Revision: http://reviews.llvm.org/D21734

llvm-svn: 274218
This commit is contained in:
Michael Zuckerman 2016-06-30 08:05:46 +00:00
parent e775de8171
commit 3f316abdce
2 changed files with 48 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
clang/lib/Headers/avx512dqintrin.h
View File

@ -792,6 +792,8 @@ _mm512_maskz_cvtepu64_ps (__mmask8 __U, __m512i __A) {
(__mmask8) -1, (int)(C),\
(int)(R)); })
#define _mm_range_ss(A ,B , C) _mm_range_round_ss(A, B, C ,_MM_FROUND_CUR_DIRECTION)
#define _mm_mask_range_round_ss(W, U, A, B, C, R) __extension__ ({ \
(__m128)__builtin_ia32_rangess128_round_mask((__v4sf)(__m128)(A), \
(__v4sf)(__m128)(B), \
@ -799,6 +801,8 @@ _mm512_maskz_cvtepu64_ps (__mmask8 __U, __m512i __A) {
(__mmask8)(U), (int)(C),\
(int)(R)); })
#define _mm_mask_range_ss(W , U, A, B, C) _mm_mask_range_round_ss(W, U, A, B, C , _MM_FROUND_CUR_DIRECTION)
#define _mm_maskz_range_round_ss(U, A, B, C, R) __extension__ ({ \
(__m128)__builtin_ia32_rangess128_round_mask((__v4sf)(__m128)(A), \
(__v4sf)(__m128)(B), \
@ -806,6 +810,8 @@ _mm512_maskz_cvtepu64_ps (__mmask8 __U, __m512i __A) {
(__mmask8)(U), (int)(C),\
(int)(R)); })
#define _mm_maskz_range_ss(U, A ,B , C) _mm_maskz_range_round_ss(U, A, B, C ,_MM_FROUND_CUR_DIRECTION)
#define _mm_range_round_sd(A, B, C, R) __extension__ ({ \
(__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
(__v2df)(__m128d)(B), \
@ -813,6 +819,8 @@ _mm512_maskz_cvtepu64_ps (__mmask8 __U, __m512i __A) {
(__mmask8) -1, (int)(C),\
(int)(R)); })
#define _mm_range_sd(A ,B , C) _mm_range_round_sd(A, B, C ,_MM_FROUND_CUR_DIRECTION)
#define _mm_mask_range_round_sd(W, U, A, B, C, R) __extension__ ({ \
(__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
(__v2df)(__m128d)(B), \
@ -820,6 +828,8 @@ _mm512_maskz_cvtepu64_ps (__mmask8 __U, __m512i __A) {
(__mmask8)(U), (int)(C),\
(int)(R)); })
#define _mm_mask_range_sd(W, U, A, B, C) _mm_mask_range_round_sd(W, U, A, B, C ,_MM_FROUND_CUR_DIRECTION)
#define _mm_maskz_range_round_sd(U, A, B, C, R) __extension__ ({ \
(__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
(__v2df)(__m128d)(B), \
@ -827,6 +837,8 @@ _mm512_maskz_cvtepu64_ps (__mmask8 __U, __m512i __A) {
(__mmask8)(U), (int)(C),\
(int)(R)); })
#define _mm_maskz_range_sd(U, A, B, C) _mm_maskz_range_round_sd(U, A, B, C ,_MM_FROUND_CUR_DIRECTION)
#define _mm512_reduce_pd(A, B) __extension__ ({ \
(__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
(__v8df)_mm512_setzero_pd(), \

36
clang/test/CodeGen/avx512dq-builtins.c
View File

@ -671,6 +671,42 @@ __m128 test_mm512_maskz_range_round_ss(__mmask8 __U, __m128 __A, __m128 __B) {
return _mm_maskz_range_round_ss(__U, __A, __B, 4, 8);
}
__m128d test_mm_range_sd(__m128d __A, __m128d __B) {
// CHECK-LABEL: @test_mm_range_sd
// CHECK: @llvm.x86.avx512.mask.range.sd
return _mm_range_sd(__A, __B, 4);
}
__m128d test_mm_mask_range_sd(__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) {
// CHECK-LABEL: test_mm_mask_range_sd
// CHECK: @llvm.x86.avx512.mask.range.sd
return _mm_mask_range_sd(__W, __U, __A, __B, 4);
}
__m128d test_mm_maskz_range_sd(__mmask8 __U, __m128d __A, __m128d __B) {
// CHECK-LABEL: @test_mm_maskz_range_sd
// CHECK: @llvm.x86.avx512.mask.range.sd
return _mm_maskz_range_sd(__U, __A, __B, 4);
}
__m128d test_mm_range_ss(__m128d __A, __m128d __B) {
// CHECK-LABEL: @test_mm_range_ss
// CHECK: @llvm.x86.avx512.mask.range.ss
return _mm_range_ss(__A, __B, 4);
}
__m128d test_mm_mask_range_ss(__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) {
// CHECK-LABEL: @test_mm_mask_range_ss
// CHECK: @llvm.x86.avx512.mask.range.ss
return _mm_mask_range_ss(__W, __U, __A, __B, 4);
}
__m128 test_mm_maskz_range_ss(__mmask8 __U, __m128 __A, __m128 __B) {
// CHECK-LABEL: @test_mm_maskz_range_ss
// CHECK: @llvm.x86.avx512.mask.range.ss
return _mm_maskz_range_ss(__U, __A, __B, 4);
}
__m512 test_mm512_range_ps(__m512 __A, __m512 __B) {
// CHECK-LABEL: @test_mm512_range_ps
// CHECK: @llvm.x86.avx512.mask.range.ps.512