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

[x86][AVX512] Lowering kunpack intrinsics to LLVM IR 

This patch, together with a matching llvm patch (https://reviews.llvm.org/D39720), implements the lowering of X86 kunpack intrinsics to IR.

Differential Revision: https://reviews.llvm.org/D39719

Change-Id: Id5d3cb394ad33b98be79a6783d1d15569e2b798d
llvm-svn: 319777
This commit is contained in:
Jina Nahias 2017-12-05 15:42:47 +00:00
parent cf333b8a56
commit eb0829155f
4 changed files with 29 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
clang/lib/Headers/avx512bwintrin.h
View File

@ -1854,15 +1854,13 @@ _mm512_maskz_set1_epi8 (__mmask64 __M, char __A)
static __inline__ __mmask64 __DEFAULT_FN_ATTRS
_mm512_kunpackd (__mmask64 __A, __mmask64 __B)
{
return (__mmask64) __builtin_ia32_kunpckdi ((__mmask64) __A,
(__mmask64) __B);
return (__mmask64) (( __A & 0xFFFFFFFF) | ( __B << 32));
}
static __inline__ __mmask32 __DEFAULT_FN_ATTRS
_mm512_kunpackw (__mmask32 __A, __mmask32 __B)
{
return (__mmask32) __builtin_ia32_kunpcksi ((__mmask32) __A,
(__mmask32) __B);
return (__mmask32) (( __A & 0xFFFF) | ( __B << 16));
}
static __inline__ __m512i __DEFAULT_FN_ATTRS

2
clang/lib/Headers/avx512fintrin.h
View File

@ -8787,7 +8787,7 @@ _mm512_kortestz (__mmask16 __A, __mmask16 __B)
static __inline__ __mmask16 __DEFAULT_FN_ATTRS
_mm512_kunpackb (__mmask16 __A, __mmask16 __B)
{
return (__mmask16) __builtin_ia32_kunpckhi ((__mmask16) __A, (__mmask16) __B);
return (__mmask16) (( __A & 0xFF) | ( __B << 8));
}
static __inline__ __mmask16 __DEFAULT_FN_ATTRS

22
clang/test/CodeGen/avx512bw-builtins.c
View File

@ -1626,16 +1626,26 @@ __m512i test_mm512_maskz_set1_epi8(__mmask64 __M, char __A) {
return _mm512_maskz_set1_epi8(__M, __A);
}
__mmask64 test_mm512_kunpackd(__mmask64 __A, __mmask64 __B) {
__mmask64 test_mm512_kunpackd(__m512i __A, __m512i __B, __m512i __C, __m512i __D, __m512i __E, __m512i __F) {
// CHECK-LABEL: @test_mm512_kunpackd
// CHECK: @llvm.x86.avx512.kunpck.dq
return _mm512_kunpackd(__A, __B);
// CHECK: bitcast <64 x i1> %{{.*}} to i64
// CHECK: bitcast <64 x i1> %{{.*}} to i64
// CHECK: and i64 %{{.*}}, 4294967295
// CHECK: shl i64 %{{.*}}, 32
// CHECK: or i64 %{{.*}}, %{{.*}}
// CHECK: bitcast i64 %{{.*}} to <64 x i1>
return _mm512_mask_cmpneq_epu8_mask(_mm512_kunpackd(_mm512_cmpneq_epu8_mask(__B, __A),_mm512_cmpneq_epu8_mask(__C, __D)), __E, __F);
}
__mmask32 test_mm512_kunpackw(__mmask32 __A, __mmask32 __B) {
__mmask32 test_mm512_kunpackw(__m512i __A, __m512i __B, __m512i __C, __m512i __D, __m512i __E, __m512i __F) {
// CHECK-LABEL: @test_mm512_kunpackw
// CHECK: @llvm.x86.avx512.kunpck.wd
return _mm512_kunpackw(__A, __B);
// CHECK: bitcast <32 x i1> %{{.*}} to i32
// CHECK: bitcast <32 x i1> %{{.*}} to i32
// CHECK: and i32 %{{.*}}, 65535
// CHECK: shl i32 %{{.*}}, 16
// CHECK: or i32 %{{.*}}, %{{.*}}
// CHECK: bitcast i32 %{{.*}} to <32 x i1>
return _mm512_mask_cmpneq_epu16_mask(_mm512_kunpackw(_mm512_cmpneq_epu16_mask(__B, __A),_mm512_cmpneq_epu16_mask(__C, __D)), __E, __F);
}
__m512i test_mm512_mask_loadu_epi16(__m512i __W, __mmask32 __U, void const *__P) {

13
clang/test/CodeGen/avx512f-builtins.c
View File

@ -6241,10 +6241,17 @@ int test_mm512_kortestz(__mmask16 __A, __mmask16 __B) {
return _mm512_kortestz(__A, __B);
}
__mmask16 test_mm512_kunpackb(__mmask16 __A, __mmask16 __B) {
__mmask16 test_mm512_kunpackb(__m512i __A, __m512i __B, __m512i __C, __m512i __D, __m512i __E, __m512i __F) {
// CHECK-LABEL: @test_mm512_kunpackb
// CHECK: @llvm.x86.avx512.kunpck.bw
return _mm512_kunpackb(__A, __B);
// CHECK: bitcast <16 x i1> %{{.*}} to i16
// CHECK: bitcast <16 x i1> %{{.*}} to i16
// CHECK: and i32 %{{.*}}, 255
// CHECK: shl i32 %{{.*}}, 8
// CHECK: or i32 %{{.*}}, %{{.*}}
// CHECK: bitcast i16 %{{.*}} to <16 x i1>
return _mm512_mask_cmpneq_epu32_mask(_mm512_kunpackb(_mm512_cmpneq_epu32_mask(__A, __B),
_mm512_cmpneq_epu32_mask(__C, __D)),
__E, __F);
}
__mmask16 test_mm512_kxnor(__mmask16 __A, __mmask16 __B) {