diff options
Diffstat (limited to 'test/CodeGen/X86/avx512-intrinsics.ll')
| -rw-r--r-- | test/CodeGen/X86/avx512-intrinsics.ll | 123 |
1 files changed, 123 insertions, 0 deletions
diff --git a/test/CodeGen/X86/avx512-intrinsics.ll b/test/CodeGen/X86/avx512-intrinsics.ll index 764e13638485..5a17cdb29216 100644 --- a/test/CodeGen/X86/avx512-intrinsics.ll +++ b/test/CodeGen/X86/avx512-intrinsics.ll @@ -6419,3 +6419,126 @@ define <8 x i64>@test_int_x86_avx512_mask_broadcasti64x4_512(<4 x i64> %x0, <8 x ret <8 x i64> %res5 } +declare <8 x i64> @llvm.x86.avx512.mask.psrl.qi.512(<8 x i64>, i8, <8 x i64>, i8) + +define <8 x i64>@test_int_x86_avx512_mask_psrl_qi_512(<8 x i64> %x0, i8 %x1, <8 x i64> %x2, i8 %x3) { +; CHECK-LABEL: test_int_x86_avx512_mask_psrl_qi_512: +; CHECK: ## BB#0: +; CHECK-NEXT: movzbl %sil, %eax +; CHECK-NEXT: kmovw %eax, %k1 +; CHECK-NEXT: vpsrlq $255, %zmm0, %zmm1 {%k1} +; CHECK-NEXT: vpsrlq $255, %zmm0, %zmm2 {%k1} {z} +; CHECK-NEXT: vpsrlq $255, %zmm0, %zmm0 +; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0 +; CHECK-NEXT: vpaddq %zmm2, %zmm0, %zmm0 +; CHECK-NEXT: retq + %res = call <8 x i64> @llvm.x86.avx512.mask.psrl.qi.512(<8 x i64> %x0, i8 255, <8 x i64> %x2, i8 %x3) + %res1 = call <8 x i64> @llvm.x86.avx512.mask.psrl.qi.512(<8 x i64> %x0, i8 255, <8 x i64> %x2, i8 -1) + %res2 = call <8 x i64> @llvm.x86.avx512.mask.psrl.qi.512(<8 x i64> %x0, i8 255, <8 x i64> zeroinitializer, i8 %x3) + %res3 = add <8 x i64> %res, %res1 + %res4 = add <8 x i64> %res3, %res2 + ret <8 x i64> %res4 +} + +declare <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32>, i8, <16 x i32>, i16) + +define <16 x i32>@test_int_x86_avx512_mask_psrl_di_512(<16 x i32> %x0, i8 %x1, <16 x i32> %x2, i16 %x3) { +; CHECK-LABEL: test_int_x86_avx512_mask_psrl_di_512: +; CHECK: ## BB#0: +; CHECK-NEXT: kmovw %esi, %k1 +; CHECK-NEXT: vpsrld $255, %zmm0, %zmm1 {%k1} +; CHECK-NEXT: vpsrld $255, %zmm0, %zmm2 {%k1} {z} +; CHECK-NEXT: vpsrld $255, %zmm0, %zmm0 +; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0 +; CHECK-NEXT: vpaddd %zmm2, %zmm0, %zmm0 +; CHECK-NEXT: retq + %res = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i8 255, <16 x i32> %x2, i16 %x3) + %res1 = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i8 255, <16 x i32> %x2, i16 -1) + %res2 = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i8 255, <16 x i32> zeroinitializer, i16 %x3) + %res3 = add <16 x i32> %res, %res1 + %res4 = add <16 x i32> %res3, %res2 + ret <16 x i32> %res4 +} + +declare <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32>, i8, <16 x i32>, i16) + +define <16 x i32>@test_int_x86_avx512_mask_psra_di_512(<16 x i32> %x0, i8 %x1, <16 x i32> %x2, i16 %x3) { +; CHECK-LABEL: test_int_x86_avx512_mask_psra_di_512: +; CHECK: ## BB#0: +; CHECK-NEXT: kmovw %esi, %k1 +; CHECK-NEXT: vpsrad $3, %zmm0, %zmm1 {%k1} +; CHECK-NEXT: vpsrad $3, %zmm0, %zmm2 {%k1} {z} +; CHECK-NEXT: vpsrad $3, %zmm0, %zmm0 +; CHECK-NEXT: vpaddd %zmm2, %zmm1, %zmm1 +; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0 +; CHECK-NEXT: retq + %res = call <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32> %x0, i8 3, <16 x i32> %x2, i16 %x3) + %res1 = call <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32> %x0, i8 3, <16 x i32> zeroinitializer, i16 %x3) + %res2 = call <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32> %x0, i8 3, <16 x i32> %x2, i16 -1) + %res3 = add <16 x i32> %res, %res1 + %res4 = add <16 x i32> %res3, %res2 + ret <16 x i32> %res4 +} + +declare <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64>, i8, <8 x i64>, i8) + +define <8 x i64>@test_int_x86_avx512_mask_psra_qi_512(<8 x i64> %x0, i8 %x1, <8 x i64> %x2, i8 %x3) { +; CHECK-LABEL: test_int_x86_avx512_mask_psra_qi_512: +; CHECK: ## BB#0: +; CHECK-NEXT: movzbl %sil, %eax +; CHECK-NEXT: kmovw %eax, %k1 +; CHECK-NEXT: vpsraq $3, %zmm0, %zmm1 {%k1} +; CHECK-NEXT: vpsraq $3, %zmm0, %zmm2 {%k1} {z} +; CHECK-NEXT: vpsraq $3, %zmm0, %zmm0 +; CHECK-NEXT: vpaddq %zmm2, %zmm1, %zmm1 +; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0 +; CHECK-NEXT: retq + %res = call <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64> %x0, i8 3, <8 x i64> %x2, i8 %x3) + %res1 = call <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64> %x0, i8 3, <8 x i64> zeroinitializer, i8 %x3) + %res2 = call <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64> %x0, i8 3, <8 x i64> %x2, i8 -1) + %res3 = add <8 x i64> %res, %res1 + %res4 = add <8 x i64> %res3, %res2 + ret <8 x i64> %res4 +} + +declare <16 x i32> @llvm.x86.avx512.mask.psll.di.512(<16 x i32>, i8, <16 x i32>, i16) + +define <16 x i32>@test_int_x86_avx512_mask_psll_di_512(<16 x i32> %x0, i8 %x1, <16 x i32> %x2, i16 %x3) { +; CHECK-LABEL: test_int_x86_avx512_mask_psll_di_512: +; CHECK: ## BB#0: +; CHECK-NEXT: kmovw %esi, %k1 +; CHECK-NEXT: vpslld $3, %zmm0, %zmm1 {%k1} +; CHECK-NEXT: vpslld $3, %zmm0, %zmm2 {%k1} {z} +; CHECK-NEXT: vpslld $3, %zmm0, %zmm0 +; CHECK-NEXT: vpaddd %zmm2, %zmm1, %zmm1 +; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0 +; CHECK-NEXT: retq + %res = call <16 x i32> @llvm.x86.avx512.mask.psll.di.512(<16 x i32> %x0, i8 3, <16 x i32> %x2, i16 %x3) + %res1 = call <16 x i32> @llvm.x86.avx512.mask.psll.di.512(<16 x i32> %x0, i8 3, <16 x i32> zeroinitializer, i16 %x3) + %res2 = call <16 x i32> @llvm.x86.avx512.mask.psll.di.512(<16 x i32> %x0, i8 3, <16 x i32> %x2, i16 -1) + %res3 = add <16 x i32> %res, %res1 + %res4 = add <16 x i32> %res3, %res2 + ret <16 x i32> %res4 +} + +declare <8 x i64> @llvm.x86.avx512.mask.psll.qi.512(<8 x i64>, i8, <8 x i64>, i8) + +define <8 x i64>@test_int_x86_avx512_mask_psll_qi_512(<8 x i64> %x0, i8 %x1, <8 x i64> %x2, i8 %x3) { +; CHECK-LABEL: test_int_x86_avx512_mask_psll_qi_512: +; CHECK: ## BB#0: +; CHECK-NEXT: movzbl %sil, %eax +; CHECK-NEXT: kmovw %eax, %k1 +; CHECK-NEXT: vpsllq $3, %zmm0, %zmm1 {%k1} +; CHECK-NEXT: vpsllq $3, %zmm0, %zmm2 {%k1} {z} +; CHECK-NEXT: vpsllq $3, %zmm0, %zmm0 +; CHECK-NEXT: vpaddq %zmm2, %zmm1, %zmm1 +; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0 +; CHECK-NEXT: retq + %res = call <8 x i64> @llvm.x86.avx512.mask.psll.qi.512(<8 x i64> %x0, i8 3, <8 x i64> %x2, i8 %x3) + %res1 = call <8 x i64> @llvm.x86.avx512.mask.psll.qi.512(<8 x i64> %x0, i8 3, <8 x i64> zeroinitializer, i8 %x3) + %res2 = call <8 x i64> @llvm.x86.avx512.mask.psll.qi.512(<8 x i64> %x0, i8 3, <8 x i64> %x2, i8 -1) + %res3 = add <8 x i64> %res, %res1 + %res4 = add <8 x i64> %res3, %res2 + ret <8 x i64> %res4 +} + |