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

[X86] Add builtins for pshufd, pshuflw, and pshufhw to enable target feature and immediate range checking. 

llvm-svn: 334265
This commit is contained in:
Craig Topper 2018-06-08 06:13:16 +00:00
parent 573dab1553
commit 03de166ccd
13 changed files with 105 additions and 139 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
clang/include/clang/Basic/BuiltinsX86.def
View File

@ -321,6 +321,9 @@ TARGET_BUILTIN(__builtin_ia32_maskmovdqu, "vV16cV16cc*", "n", "sse2")
TARGET_BUILTIN(__builtin_ia32_movmskpd, "iV2d", "nc", "sse2")
TARGET_BUILTIN(__builtin_ia32_pmovmskb128, "iV16c", "nc", "sse2")
TARGET_BUILTIN(__builtin_ia32_movnti, "vi*i", "n", "sse2")
TARGET_BUILTIN(__builtin_ia32_pshufd, "V4iV4iIi", "nc", "sse2")
TARGET_BUILTIN(__builtin_ia32_pshuflw, "V8sV8sIi", "nc", "sse2")
TARGET_BUILTIN(__builtin_ia32_pshufhw, "V8sV8sIi", "nc", "sse2")
TARGET_BUILTIN(__builtin_ia32_psadbw128, "V2LLiV16cV16c", "nc", "sse2")
TARGET_BUILTIN(__builtin_ia32_sqrtpd, "V2dV2d", "nc", "sse2")
TARGET_BUILTIN(__builtin_ia32_sqrtsd, "V2dV2d", "nc", "sse2")
@ -598,6 +601,9 @@ TARGET_BUILTIN(__builtin_ia32_pmulhw256, "V16sV16sV16s", "nc", "avx2")
TARGET_BUILTIN(__builtin_ia32_pmuludq256, "V4LLiV8iV8i", "nc", "avx2")
TARGET_BUILTIN(__builtin_ia32_psadbw256, "V4LLiV32cV32c", "nc", "avx2")
TARGET_BUILTIN(__builtin_ia32_pshufb256, "V32cV32cV32c", "nc", "avx2")
TARGET_BUILTIN(__builtin_ia32_pshufd256, "V8iV8iIi", "nc", "avx2")
TARGET_BUILTIN(__builtin_ia32_pshuflw256, "V16sV16sIi", "nc", "avx2")
TARGET_BUILTIN(__builtin_ia32_pshufhw256, "V16sV16sIi", "nc", "avx2")
TARGET_BUILTIN(__builtin_ia32_psignb256, "V32cV32cV32c", "nc", "avx2")
TARGET_BUILTIN(__builtin_ia32_psignw256, "V16sV16sV16s", "nc", "avx2")
TARGET_BUILTIN(__builtin_ia32_psignd256, "V8iV8iV8i", "nc", "avx2")
@ -1363,6 +1369,8 @@ TARGET_BUILTIN(__builtin_ia32_prorvd128_mask, "V4iV4iV4iV4iUc", "nc", "avx512vl"
TARGET_BUILTIN(__builtin_ia32_prorvd256_mask, "V8iV8iV8iV8iUc", "nc", "avx512vl")
TARGET_BUILTIN(__builtin_ia32_prorvq128_mask, "V2LLiV2LLiV2LLiV2LLiUc", "nc", "avx512vl")
TARGET_BUILTIN(__builtin_ia32_prorvq256_mask, "V4LLiV4LLiV4LLiV4LLiUc", "nc", "avx512vl")
TARGET_BUILTIN(__builtin_ia32_pshufhw512, "V32sV32sIi", "nc ", "avx512bw")
TARGET_BUILTIN(__builtin_ia32_pshuflw512, "V32sV32sIi", "nc ", "avx512bw")
TARGET_BUILTIN(__builtin_ia32_psllv32hi, "V32sV32sV32s", "nc", "avx512bw")
TARGET_BUILTIN(__builtin_ia32_psllw512, "V32sV32sV8s", "nc", "avx512bw")
TARGET_BUILTIN(__builtin_ia32_psllwi512, "V32sV32si", "nc", "avx512bw")
@ -1737,6 +1745,7 @@ TARGET_BUILTIN(__builtin_ia32_compresssf512_mask, "V16fV16fV16fUs", "nc", "avx51
TARGET_BUILTIN(__builtin_ia32_compresssi512_mask, "V16iV16iV16iUs", "nc", "avx512f")
TARGET_BUILTIN(__builtin_ia32_cmpsd_mask, "UcV2dV2dIiUcIi", "nc", "avx512f")
TARGET_BUILTIN(__builtin_ia32_cmpss_mask, "UcV4fV4fIiUcIi", "nc", "avx512f")
TARGET_BUILTIN(__builtin_ia32_pshufd512, "V16iV16iIi", "nc", "avx512f")
TARGET_BUILTIN(__builtin_ia32_expanddf512_mask, "V8dV8dV8dUc", "nc", "avx512f")
TARGET_BUILTIN(__builtin_ia32_expanddi512_mask, "V8LLiV8LLiV8LLiUc", "nc", "avx512f")
TARGET_BUILTIN(__builtin_ia32_expandhi512_mask, "V32sV32sV32sUi", "nc", "avx512vbmi2")

51
clang/lib/CodeGen/CGBuiltin.cpp
View File

@ -9325,6 +9325,57 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
makeArrayRef(Indices, NumElts),
"blend");
}
case X86::BI__builtin_ia32_pshuflw:
case X86::BI__builtin_ia32_pshuflw256:
case X86::BI__builtin_ia32_pshuflw512: {
uint32_t Imm = cast<llvm::ConstantInt>(Ops[1])->getZExtValue();
llvm::Type *Ty = Ops[0]->getType();
unsigned NumElts = Ty->getVectorNumElements();
// Splat the 8-bits of immediate 4 times to help the loop wrap around.
Imm = (Imm & 0xff) * 0x01010101;
uint32_t Indices[32];
for (unsigned l = 0; l != NumElts; l += 8) {
for (unsigned i = 0; i != 4; ++i) {
Indices[l + i] = l + (Imm & 3);
Imm >>= 2;
}
for (unsigned i = 4; i != 8; ++i)
Indices[l + i] = l + i;
}
return Builder.CreateShuffleVector(Ops[0], UndefValue::get(Ty),
makeArrayRef(Indices, NumElts),
"pshuflw");
}
case X86::BI__builtin_ia32_pshufhw:
case X86::BI__builtin_ia32_pshufhw256:
case X86::BI__builtin_ia32_pshufhw512: {
uint32_t Imm = cast<llvm::ConstantInt>(Ops[1])->getZExtValue();
llvm::Type *Ty = Ops[0]->getType();
unsigned NumElts = Ty->getVectorNumElements();
// Splat the 8-bits of immediate 4 times to help the loop wrap around.
Imm = (Imm & 0xff) * 0x01010101;
uint32_t Indices[32];
for (unsigned l = 0; l != NumElts; l += 8) {
for (unsigned i = 0; i != 4; ++i)
Indices[l + i] = l + i;
for (unsigned i = 4; i != 8; ++i) {
Indices[l + i] = l + 4 + (Imm & 3);
Imm >>= 2;
}
}
return Builder.CreateShuffleVector(Ops[0], UndefValue::get(Ty),
makeArrayRef(Indices, NumElts),
"pshufhw");
}
case X86::BI__builtin_ia32_pshufd:
case X86::BI__builtin_ia32_pshufd256:
case X86::BI__builtin_ia32_pshufd512:
case X86::BI__builtin_ia32_vpermilpd:
case X86::BI__builtin_ia32_vpermilps:
case X86::BI__builtin_ia32_vpermilpd256:

37
clang/lib/Headers/avx2intrin.h
View File

@ -488,44 +488,13 @@ _mm256_shuffle_epi8(__m256i __a, __m256i __b)
}
#define _mm256_shuffle_epi32(a, imm) \
(__m256i)__builtin_shufflevector((__v8si)(__m256i)(a), \
(__v8si)_mm256_undefined_si256(), \
0 + (((imm) >> 0) & 0x3), \
0 + (((imm) >> 2) & 0x3), \
0 + (((imm) >> 4) & 0x3), \
0 + (((imm) >> 6) & 0x3), \
4 + (((imm) >> 0) & 0x3), \
4 + (((imm) >> 2) & 0x3), \
4 + (((imm) >> 4) & 0x3), \
4 + (((imm) >> 6) & 0x3))
(__m256i)__builtin_ia32_pshufd256((__v8si)(__m256i)(a), (int)(imm))
#define _mm256_shufflehi_epi16(a, imm) \
(__m256i)__builtin_shufflevector((__v16hi)(__m256i)(a), \
(__v16hi)_mm256_undefined_si256(), \
0, 1, 2, 3, \
4 + (((imm) >> 0) & 0x3), \
4 + (((imm) >> 2) & 0x3), \
4 + (((imm) >> 4) & 0x3), \
4 + (((imm) >> 6) & 0x3), \
8, 9, 10, 11, \
12 + (((imm) >> 0) & 0x3), \
12 + (((imm) >> 2) & 0x3), \
12 + (((imm) >> 4) & 0x3), \
12 + (((imm) >> 6) & 0x3))
(__m256i)__builtin_ia32_pshufhw256((__v16hi)(__m256i)(a), (int)(imm))
#define _mm256_shufflelo_epi16(a, imm) \
(__m256i)__builtin_shufflevector((__v16hi)(__m256i)(a), \
(__v16hi)_mm256_undefined_si256(), \
0 + (((imm) >> 0) & 0x3), \
0 + (((imm) >> 2) & 0x3), \
0 + (((imm) >> 4) & 0x3), \
0 + (((imm) >> 6) & 0x3), \
4, 5, 6, 7, \
8 + (((imm) >> 0) & 0x3), \
8 + (((imm) >> 2) & 0x3), \
8 + (((imm) >> 4) & 0x3), \
8 + (((imm) >> 6) & 0x3), \
12, 13, 14, 15)
(__m256i)__builtin_ia32_pshuflw256((__v16hi)(__m256i)(a), (int)(imm))
static __inline__ __m256i __DEFAULT_FN_ATTRS
_mm256_sign_epi8(__m256i __a, __m256i __b)

46
clang/lib/Headers/avx512bwintrin.h
View File

@ -1287,28 +1287,7 @@ _mm512_maskz_cvtepu8_epi16(__mmask32 __U, __m256i __A)
#define _mm512_shufflehi_epi16(A, imm) \
(__m512i)__builtin_shufflevector((__v32hi)(__m512i)(A), \
(__v32hi)_mm512_undefined_epi32(), \
0, 1, 2, 3, \
4 + (((imm) >> 0) & 0x3), \
4 + (((imm) >> 2) & 0x3), \
4 + (((imm) >> 4) & 0x3), \
4 + (((imm) >> 6) & 0x3), \
8, 9, 10, 11, \
12 + (((imm) >> 0) & 0x3), \
12 + (((imm) >> 2) & 0x3), \
12 + (((imm) >> 4) & 0x3), \
12 + (((imm) >> 6) & 0x3), \
16, 17, 18, 19, \
20 + (((imm) >> 0) & 0x3), \
20 + (((imm) >> 2) & 0x3), \
20 + (((imm) >> 4) & 0x3), \
20 + (((imm) >> 6) & 0x3), \
24, 25, 26, 27, \
28 + (((imm) >> 0) & 0x3), \
28 + (((imm) >> 2) & 0x3), \
28 + (((imm) >> 4) & 0x3), \
28 + (((imm) >> 6) & 0x3))
(__m512i)__builtin_ia32_pshufhw512((__v32hi)(__m512i)(A), (int)(imm))
#define _mm512_mask_shufflehi_epi16(W, U, A, imm) \
(__m512i)__builtin_ia32_selectw_512((__mmask32)(U), \
@ -1323,28 +1302,7 @@ _mm512_maskz_cvtepu8_epi16(__mmask32 __U, __m256i __A)
(__v32hi)_mm512_setzero_si512())
#define _mm512_shufflelo_epi16(A, imm) \
(__m512i)__builtin_shufflevector((__v32hi)(__m512i)(A), \
(__v32hi)_mm512_undefined_epi32(), \
0 + (((imm) >> 0) & 0x3), \
0 + (((imm) >> 2) & 0x3), \
0 + (((imm) >> 4) & 0x3), \
0 + (((imm) >> 6) & 0x3), \
4, 5, 6, 7, \
8 + (((imm) >> 0) & 0x3), \
8 + (((imm) >> 2) & 0x3), \
8 + (((imm) >> 4) & 0x3), \
8 + (((imm) >> 6) & 0x3), \
12, 13, 14, 15, \
16 + (((imm) >> 0) & 0x3), \
16 + (((imm) >> 2) & 0x3), \
16 + (((imm) >> 4) & 0x3), \
16 + (((imm) >> 6) & 0x3), \
20, 21, 22, 23, \
24 + (((imm) >> 0) & 0x3), \
24 + (((imm) >> 2) & 0x3), \
24 + (((imm) >> 4) & 0x3), \
24 + (((imm) >> 6) & 0x3), \
28, 29, 30, 31)
(__m512i)__builtin_ia32_pshuflw512((__v32hi)(__m512i)(A), (int)(imm))
#define _mm512_mask_shufflelo_epi16(W, U, A, imm) \

19
clang/lib/Headers/avx512fintrin.h
View File

@ -8849,24 +8849,7 @@ _mm_maskz_load_sd (__mmask8 __U, const double* __A)
}
#define _mm512_shuffle_epi32(A, I) \
(__m512i)__builtin_shufflevector((__v16si)(__m512i)(A), \
(__v16si)_mm512_undefined_epi32(), \
0 + (((I) >> 0) & 0x3), \
0 + (((I) >> 2) & 0x3), \
0 + (((I) >> 4) & 0x3), \
0 + (((I) >> 6) & 0x3), \
4 + (((I) >> 0) & 0x3), \
4 + (((I) >> 2) & 0x3), \
4 + (((I) >> 4) & 0x3), \
4 + (((I) >> 6) & 0x3), \
8 + (((I) >> 0) & 0x3), \
8 + (((I) >> 2) & 0x3), \
8 + (((I) >> 4) & 0x3), \
8 + (((I) >> 6) & 0x3), \
12 + (((I) >> 0) & 0x3), \
12 + (((I) >> 2) & 0x3), \
12 + (((I) >> 4) & 0x3), \
12 + (((I) >> 6) & 0x3))
(__m512i)__builtin_ia32_pshufd512((__v16si)(__m512i)(A), (int)(I))
#define _mm512_mask_shuffle_epi32(W, U, A, I) \
(__m512i)__builtin_ia32_selectd_512((__mmask16)(U), \

19
clang/lib/Headers/emmintrin.h
View File

@ -4343,10 +4343,7 @@ _mm_movemask_epi8(__m128i __a)
/// 11: assign values from bits [127:96] of \a a.
/// \returns A 128-bit integer vector containing the shuffled values.
#define _mm_shuffle_epi32(a, imm) \
(__m128i)__builtin_shufflevector((__v4si)(__m128i)(a), \
(__v4si)_mm_undefined_si128(), \
((imm) >> 0) & 0x3, ((imm) >> 2) & 0x3, \
((imm) >> 4) & 0x3, ((imm) >> 6) & 0x3)
(__m128i)__builtin_ia32_pshufd((__v4si)(__m128i)(a), (int)(imm))
/// Constructs a 128-bit integer vector by shuffling four lower 16-bit
/// elements of a 128-bit integer vector of [8 x i16], using the immediate
@ -4376,11 +4373,7 @@ _mm_movemask_epi8(__m128i __a)
/// 11: assign values from bits [63:48] of \a a. \n
/// \returns A 128-bit integer vector containing the shuffled values.
#define _mm_shufflelo_epi16(a, imm) \
(__m128i)__builtin_shufflevector((__v8hi)(__m128i)(a), \
(__v8hi)_mm_undefined_si128(), \
((imm) >> 0) & 0x3, ((imm) >> 2) & 0x3, \
((imm) >> 4) & 0x3, ((imm) >> 6) & 0x3, \
4, 5, 6, 7)
(__m128i)__builtin_ia32_pshuflw((__v8hi)(__m128i)(a), (int)(imm))
/// Constructs a 128-bit integer vector by shuffling four upper 16-bit
/// elements of a 128-bit integer vector of [8 x i16], using the immediate
@ -4410,13 +4403,7 @@ _mm_movemask_epi8(__m128i __a)
/// 11: assign values from bits [127:112] of \a a. \n
/// \returns A 128-bit integer vector containing the shuffled values.
#define _mm_shufflehi_epi16(a, imm) \
(__m128i)__builtin_shufflevector((__v8hi)(__m128i)(a), \
(__v8hi)_mm_undefined_si128(), \
0, 1, 2, 3, \
4 + (((imm) >> 0) & 0x3), \
4 + (((imm) >> 2) & 0x3), \
4 + (((imm) >> 4) & 0x3), \
4 + (((imm) >> 6) & 0x3))
(__m128i)__builtin_ia32_pshufhw((__v8hi)(__m128i)(a), (int)(imm))
/// Unpacks the high-order (index 8-15) values from two 128-bit vectors
/// of [16 x i8] and interleaves them into a 128-bit vector of [16 x i8].

9
clang/lib/Sema/SemaChecking.cpp
View File

@ -2759,6 +2759,15 @@ bool Sema::CheckX86BuiltinFunctionCall(unsigned BuiltinID, CallExpr *TheCall) {
case X86::BI__builtin_ia32_vpermilps256:
case X86::BI__builtin_ia32_vpermilpd512:
case X86::BI__builtin_ia32_vpermilps512:
case X86::BI__builtin_ia32_pshufd:
case X86::BI__builtin_ia32_pshufd256:
case X86::BI__builtin_ia32_pshufd512:
case X86::BI__builtin_ia32_pshufhw:
case X86::BI__builtin_ia32_pshufhw256:
case X86::BI__builtin_ia32_pshufhw512:
case X86::BI__builtin_ia32_pshuflw:
case X86::BI__builtin_ia32_pshuflw256:
case X86::BI__builtin_ia32_pshuflw512:
case X86::BI__builtin_ia32_vcvtps2ph:
case X86::BI__builtin_ia32_vcvtps2ph_mask:
case X86::BI__builtin_ia32_vcvtps2ph256:

6
clang/test/CodeGen/avx2-builtins.c
View File

@ -955,19 +955,19 @@ __m256i test_mm256_shuffle_epi8(__m256i a, __m256i b) {
__m256i test_mm256_shuffle_epi32(__m256i a) {
// CHECK-LABEL: test_mm256_shuffle_epi32
// CHECK: shufflevector <8 x i32> %{{.*}}, <8 x i32> %{{.*}}, <8 x i32> <i32 3, i32 3, i32 0, i32 0, i32 7, i32 7, i32 4, i32 4>
// CHECK: shufflevector <8 x i32> %{{.*}}, <8 x i32> undef, <8 x i32> <i32 3, i32 3, i32 0, i32 0, i32 7, i32 7, i32 4, i32 4>
return _mm256_shuffle_epi32(a, 15);
}
__m256i test_mm256_shufflehi_epi16(__m256i a) {
// CHECK-LABEL: test_mm256_shufflehi_epi16
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> %{{.*}}, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 7, i32 6, i32 6, i32 5, i32 8, i32 9, i32 10, i32 11, i32 15, i32 14, i32 14, i32 13>
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 7, i32 6, i32 6, i32 5, i32 8, i32 9, i32 10, i32 11, i32 15, i32 14, i32 14, i32 13>
return _mm256_shufflehi_epi16(a, 107);
}
__m256i test_mm256_shufflelo_epi16(__m256i a) {
// CHECK-LABEL: test_mm256_shufflelo_epi16
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> %{{.*}}, <16 x i32> <i32 3, i32 0, i32 1, i32 1, i32 4, i32 5, i32 6, i32 7, i32 11, i32 8, i32 9, i32 9, i32 12, i32 13, i32 14, i32 15>
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> undef, <16 x i32> <i32 3, i32 0, i32 1, i32 1, i32 4, i32 5, i32 6, i32 7, i32 11, i32 8, i32 9, i32 9, i32 12, i32 13, i32 14, i32 15>
return _mm256_shufflelo_epi16(a, 83);
}

12
clang/test/CodeGen/avx512bw-builtins.c
View File

@ -1250,40 +1250,40 @@ __m512i test_mm512_maskz_cvtepu8_epi16(__mmask32 __U, __m256i __A) {
__m512i test_mm512_shufflehi_epi16(__m512i __A) {
// CHECK-LABEL: @test_mm512_shufflehi_epi16
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> %{{.*}}, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4, i32 8, i32 9, i32 10, i32 11, i32 13, i32 13, i32 12, i32 12, i32 16, i32 17, i32 18, i32 19, i32 21, i32 21, i32 20, i32 20, i32 24, i32 25, i32 26, i32 27, i32 29, i32 29, i32 28, i32 28>
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4, i32 8, i32 9, i32 10, i32 11, i32 13, i32 13, i32 12, i32 12, i32 16, i32 17, i32 18, i32 19, i32 21, i32 21, i32 20, i32 20, i32 24, i32 25, i32 26, i32 27, i32 29, i32 29, i32 28, i32 28>
return _mm512_shufflehi_epi16(__A, 5);
}
__m512i test_mm512_mask_shufflehi_epi16(__m512i __W, __mmask32 __U, __m512i __A) {
// CHECK-LABEL: @test_mm512_mask_shufflehi_epi16
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> %{{.*}}, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4, i32 8, i32 9, i32 10, i32 11, i32 13, i32 13, i32 12, i32 12, i32 16, i32 17, i32 18, i32 19, i32 21, i32 21, i32 20, i32 20, i32 24, i32 25, i32 26, i32 27, i32 29, i32 29, i32 28, i32 28>
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4, i32 8, i32 9, i32 10, i32 11, i32 13, i32 13, i32 12, i32 12, i32 16, i32 17, i32 18, i32 19, i32 21, i32 21, i32 20, i32 20, i32 24, i32 25, i32 26, i32 27, i32 29, i32 29, i32 28, i32 28>
// CHECK: select <32 x i1> %{{.*}}, <32 x i16> %{{.*}}, <32 x i16> %{{.*}}
return _mm512_mask_shufflehi_epi16(__W, __U, __A, 5);
}
__m512i test_mm512_maskz_shufflehi_epi16(__mmask32 __U, __m512i __A) {
// CHECK-LABEL: @test_mm512_maskz_shufflehi_epi16
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> %{{.*}}, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4, i32 8, i32 9, i32 10, i32 11, i32 13, i32 13, i32 12, i32 12, i32 16, i32 17, i32 18, i32 19, i32 21, i32 21, i32 20, i32 20, i32 24, i32 25, i32 26, i32 27, i32 29, i32 29, i32 28, i32 28>
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4, i32 8, i32 9, i32 10, i32 11, i32 13, i32 13, i32 12, i32 12, i32 16, i32 17, i32 18, i32 19, i32 21, i32 21, i32 20, i32 20, i32 24, i32 25, i32 26, i32 27, i32 29, i32 29, i32 28, i32 28>
// CHECK: select <32 x i1> %{{.*}}, <32 x i16> %{{.*}}, <32 x i16> %{{.*}}
return _mm512_maskz_shufflehi_epi16(__U, __A, 5);
}
__m512i test_mm512_shufflelo_epi16(__m512i __A) {
// CHECK-LABEL: @test_mm512_shufflelo_epi16
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> %{{.*}}, <32 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7, i32 9, i32 9, i32 8, i32 8, i32 12, i32 13, i32 14, i32 15, i32 17, i32 17, i32 16, i32 16, i32 20, i32 21, i32 22, i32 23, i32 25, i32 25, i32 24, i32 24, i32 28, i32 29, i32 30, i32 31>
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> undef, <32 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7, i32 9, i32 9, i32 8, i32 8, i32 12, i32 13, i32 14, i32 15, i32 17, i32 17, i32 16, i32 16, i32 20, i32 21, i32 22, i32 23, i32 25, i32 25, i32 24, i32 24, i32 28, i32 29, i32 30, i32 31>
return _mm512_shufflelo_epi16(__A, 5);
}
__m512i test_mm512_mask_shufflelo_epi16(__m512i __W, __mmask32 __U, __m512i __A) {
// CHECK-LABEL: @test_mm512_mask_shufflelo_epi16
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> %{{.*}}, <32 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7, i32 9, i32 9, i32 8, i32 8, i32 12, i32 13, i32 14, i32 15, i32 17, i32 17, i32 16, i32 16, i32 20, i32 21, i32 22, i32 23, i32 25, i32 25, i32 24, i32 24, i32 28, i32 29, i32 30, i32 31>
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> undef, <32 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7, i32 9, i32 9, i32 8, i32 8, i32 12, i32 13, i32 14, i32 15, i32 17, i32 17, i32 16, i32 16, i32 20, i32 21, i32 22, i32 23, i32 25, i32 25, i32 24, i32 24, i32 28, i32 29, i32 30, i32 31>
// CHECK: select <32 x i1> %{{.*}}, <32 x i16> %{{.*}}, <32 x i16> %{{.*}}
return _mm512_mask_shufflelo_epi16(__W, __U, __A, 5);
}
__m512i test_mm512_maskz_shufflelo_epi16(__mmask32 __U, __m512i __A) {
// CHECK-LABEL: @test_mm512_maskz_shufflelo_epi16
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> %{{.*}}, <32 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7, i32 9, i32 9, i32 8, i32 8, i32 12, i32 13, i32 14, i32 15, i32 17, i32 17, i32 16, i32 16, i32 20, i32 21, i32 22, i32 23, i32 25, i32 25, i32 24, i32 24, i32 28, i32 29, i32 30, i32 31>
// CHECK: shufflevector <32 x i16> %{{.*}}, <32 x i16> undef, <32 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7, i32 9, i32 9, i32 8, i32 8, i32 12, i32 13, i32 14, i32 15, i32 17, i32 17, i32 16, i32 16, i32 20, i32 21, i32 22, i32 23, i32 25, i32 25, i32 24, i32 24, i32 28, i32 29, i32 30, i32 31>
// CHECK: select <32 x i1> %{{.*}}, <32 x i16> %{{.*}}, <32 x i16> %{{.*}}
return _mm512_maskz_shufflelo_epi16(__U, __A, 5);
}

6
clang/test/CodeGen/avx512f-builtins.c
View File

@ -7234,20 +7234,20 @@ __m512 test_mm512_maskz_moveldup_ps(__mmask16 __U, __m512 __A) {
__m512i test_mm512_shuffle_epi32(__m512i __A) {
// CHECK-LABEL: @test_mm512_shuffle_epi32
// CHECK: shufflevector <16 x i32> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> <i32 1, i32 0, i32 0, i32 0, i32 5, i32 4, i32 4, i32 4, i32 9, i32 8, i32 8, i32 8, i32 13, i32 12, i32 12, i32 12>
// CHECK: shufflevector <16 x i32> %{{.*}}, <16 x i32> undef, <16 x i32> <i32 1, i32 0, i32 0, i32 0, i32 5, i32 4, i32 4, i32 4, i32 9, i32 8, i32 8, i32 8, i32 13, i32 12, i32 12, i32 12>
return _mm512_shuffle_epi32(__A, 1);
}
__m512i test_mm512_mask_shuffle_epi32(__m512i __W, __mmask16 __U, __m512i __A) {
// CHECK-LABEL: @test_mm512_mask_shuffle_epi32
// CHECK: shufflevector <16 x i32> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> <i32 1, i32 0, i32 0, i32 0, i32 5, i32 4, i32 4, i32 4, i32 9, i32 8, i32 8, i32 8, i32 13, i32 12, i32 12, i32 12>
// CHECK: shufflevector <16 x i32> %{{.*}}, <16 x i32> undef, <16 x i32> <i32 1, i32 0, i32 0, i32 0, i32 5, i32 4, i32 4, i32 4, i32 9, i32 8, i32 8, i32 8, i32 13, i32 12, i32 12, i32 12>
// CHECK: select <16 x i1> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> %{{.*}}
return _mm512_mask_shuffle_epi32(__W, __U, __A, 1);
}
__m512i test_mm512_maskz_shuffle_epi32(__mmask16 __U, __m512i __A) {
// CHECK-LABEL: @test_mm512_maskz_shuffle_epi32
// CHECK: shufflevector <16 x i32> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> <i32 1, i32 0, i32 0, i32 0, i32 5, i32 4, i32 4, i32 4, i32 9, i32 8, i32 8, i32 8, i32 13, i32 12, i32 12, i32 12>
// CHECK: shufflevector <16 x i32> %{{.*}}, <16 x i32> undef, <16 x i32> <i32 1, i32 0, i32 0, i32 0, i32 5, i32 4, i32 4, i32 4, i32 9, i32 8, i32 8, i32 8, i32 13, i32 12, i32 12, i32 12>
// CHECK: select <16 x i1> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> %{{.*}}
return _mm512_maskz_shuffle_epi32(__U, __A, 1);
}

8
clang/test/CodeGen/avx512vl-builtins.c
View File

@ -7598,28 +7598,28 @@ __m256 test_mm256_maskz_moveldup_ps(__mmask8 __U, __m256 __A) {
__m128i test_mm_mask_shuffle_epi32(__m128i __W, __mmask8 __U, __m128i __A) {
// CHECK-LABEL: @test_mm_mask_shuffle_epi32
// CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> %{{.*}}, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
// CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
// CHECK: select <4 x i1> %{{.*}}, <4 x i32> %{{.*}}, <4 x i32> %{{.*}}
return _mm_mask_shuffle_epi32(__W, __U, __A, 1);
}
__m128i test_mm_maskz_shuffle_epi32(__mmask8 __U, __m128i __A) {
// CHECK-LABEL: @test_mm_maskz_shuffle_epi32
// CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> %{{.*}}, <4 x i32> <i32 2, i32 0, i32 0, i32 0>
// CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 2, i32 0, i32 0, i32 0>
// CHECK: select <4 x i1> %{{.*}}, <4 x i32> %{{.*}}, <4 x i32> %{{.*}}
return _mm_maskz_shuffle_epi32(__U, __A, 2);
}
__m256i test_mm256_mask_shuffle_epi32(__m256i __W, __mmask8 __U, __m256i __A) {
// CHECK-LABEL: @test_mm256_mask_shuffle_epi32
// CHECK: shufflevector <8 x i32> %{{.*}}, <8 x i32> %{{.*}}, <8 x i32> <i32 2, i32 0, i32 0, i32 0, i32 6, i32 4, i32 4, i32 4>
// CHECK: shufflevector <8 x i32> %{{.*}}, <8 x i32> undef, <8 x i32> <i32 2, i32 0, i32 0, i32 0, i32 6, i32 4, i32 4, i32 4>
// CHECK: select <8 x i1> %{{.*}}, <8 x i32> %{{.*}}, <8 x i32> %{{.*}}
return _mm256_mask_shuffle_epi32(__W, __U, __A, 2);
}
__m256i test_mm256_maskz_shuffle_epi32(__mmask8 __U, __m256i __A) {
// CHECK-LABEL: @test_mm256_maskz_shuffle_epi32
// CHECK: shufflevector <8 x i32> %{{.*}}, <8 x i32> %{{.*}}, <8 x i32> <i32 2, i32 0, i32 0, i32 0, i32 6, i32 4, i32 4, i32 4>
// CHECK: shufflevector <8 x i32> %{{.*}}, <8 x i32> undef, <8 x i32> <i32 2, i32 0, i32 0, i32 0, i32 6, i32 4, i32 4, i32 4>
// CHECK: select <8 x i1> %{{.*}}, <8 x i32> %{{.*}}, <8 x i32> %{{.*}}
return _mm256_maskz_shuffle_epi32(__U, __A, 2);
}

16
clang/test/CodeGen/avx512vlbw-builtins.c
View File

@ -3013,56 +3013,56 @@ __mmask16 test_mm256_movepi16_mask(__m256i __A) {
__m128i test_mm_mask_shufflehi_epi16(__m128i __W, __mmask32 __U, __m128i __A) {
// CHECK-LABEL: @test_mm_mask_shufflehi_epi16
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4>
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4>
// CHECK: select <8 x i1> %{{.*}}, <8 x i16> %{{.*}}, <8 x i16> %{{.*}}
return _mm_mask_shufflehi_epi16(__W, __U, __A, 5);
}
__m128i test_mm_maskz_shufflehi_epi16(__mmask32 __U, __m128i __A) {
// CHECK-LABEL: @test_mm_maskz_shufflehi_epi16
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4>
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4>
// CHECK: select <8 x i1> %{{.*}}, <8 x i16> %{{.*}}, <8 x i16> %{{.*}}
return _mm_maskz_shufflehi_epi16(__U, __A, 5);
}
__m128i test_mm_mask_shufflelo_epi16(__m128i __W, __mmask32 __U, __m128i __A) {
// CHECK-LABEL: @test_mm_mask_shufflelo_epi16
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> %{{.*}}, <8 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7>
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> undef, <8 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7>
// CHECK: select <8 x i1> %{{.*}}, <8 x i16> %{{.*}}, <8 x i16> %{{.*}}
return _mm_mask_shufflelo_epi16(__W, __U, __A, 5);
}
__m128i test_mm_maskz_shufflelo_epi16(__mmask32 __U, __m128i __A) {
// CHECK-LABEL: @test_mm_maskz_shufflelo_epi16
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> %{{.*}}, <8 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7>
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> undef, <8 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7>
// CHECK: select <8 x i1> %{{.*}}, <8 x i16> %{{.*}}, <8 x i16> %{{.*}}
return _mm_maskz_shufflelo_epi16(__U, __A, 5);
}
__m256i test_mm256_mask_shufflehi_epi16(__m256i __W, __mmask32 __U, __m256i __A) {
// CHECK-LABEL: @test_mm256_mask_shufflehi_epi16
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> %{{.*}}, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4, i32 8, i32 9, i32 10, i32 11, i32 13, i32 13, i32 12, i32 12>
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4, i32 8, i32 9, i32 10, i32 11, i32 13, i32 13, i32 12, i32 12>
// CHECK: select <16 x i1> %{{.*}}, <16 x i16> %{{.*}}, <16 x i16> %{{.*}}
return _mm256_mask_shufflehi_epi16(__W, __U, __A, 5);
}
__m256i test_mm256_maskz_shufflehi_epi16(__mmask32 __U, __m256i __A) {
// CHECK-LABEL: @test_mm256_maskz_shufflehi_epi16
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> %{{.*}}, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4, i32 8, i32 9, i32 10, i32 11, i32 13, i32 13, i32 12, i32 12>
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 5, i32 4, i32 4, i32 8, i32 9, i32 10, i32 11, i32 13, i32 13, i32 12, i32 12>
// CHECK: select <16 x i1> %{{.*}}, <16 x i16> %{{.*}}, <16 x i16> %{{.*}}
return _mm256_maskz_shufflehi_epi16(__U, __A, 5);
}
__m256i test_mm256_mask_shufflelo_epi16(__m256i __W, __mmask32 __U, __m256i __A) {
// CHECK-LABEL: @test_mm256_mask_shufflelo_epi16
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> %{{.*}}, <16 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7, i32 9, i32 9, i32 8, i32 8, i32 12, i32 13, i32 14, i32 15>
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> undef, <16 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7, i32 9, i32 9, i32 8, i32 8, i32 12, i32 13, i32 14, i32 15>
// CHECK: select <16 x i1> %{{.*}}, <16 x i16> %{{.*}}, <16 x i16> %{{.*}}
return _mm256_mask_shufflelo_epi16(__W, __U, __A, 5);
}
__m256i test_mm256_maskz_shufflelo_epi16(__mmask32 __U, __m256i __A) {
// CHECK-LABEL: @test_mm256_maskz_shufflelo_epi16
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> %{{.*}}, <16 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7, i32 9, i32 9, i32 8, i32 8, i32 12, i32 13, i32 14, i32 15>
// CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> undef, <16 x i32> <i32 1, i32 1, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7, i32 9, i32 9, i32 8, i32 8, i32 12, i32 13, i32 14, i32 15>
// CHECK: select <16 x i1> %{{.*}}, <16 x i16> %{{.*}}, <16 x i16> %{{.*}}
return _mm256_maskz_shufflelo_epi16(__U, __A, 5);
}

6
clang/test/CodeGen/sse2-builtins.c
View File

@ -1116,7 +1116,7 @@ __m128i test_mm_setzero_si128() {
__m128i test_mm_shuffle_epi32(__m128i A) {
// CHECK-LABEL: test_mm_shuffle_epi32
// CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> %{{.*}}, <4 x i32> zeroinitializer
// CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> zeroinitializer
return _mm_shuffle_epi32(A, 0);
}
@ -1128,13 +1128,13 @@ __m128d test_mm_shuffle_pd(__m128d A, __m128d B) {
__m128i test_mm_shufflehi_epi16(__m128i A) {
// CHECK-LABEL: test_mm_shufflehi_epi16
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 4, i32 4, i32 4>
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 4, i32 4, i32 4>
return _mm_shufflehi_epi16(A, 0);
}
__m128i test_mm_shufflelo_epi16(__m128i A) {
// CHECK-LABEL: test_mm_shufflelo_epi16
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> %{{.*}}, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7>
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7>
return _mm_shufflelo_epi16(A, 0);
}