diff options
Diffstat (limited to 'test/CodeGen/X86/avx512-intrinsics-fast-isel.ll')
| -rw-r--r-- | test/CodeGen/X86/avx512-intrinsics-fast-isel.ll | 962 |
1 files changed, 724 insertions, 238 deletions
diff --git a/test/CodeGen/X86/avx512-intrinsics-fast-isel.ll b/test/CodeGen/X86/avx512-intrinsics-fast-isel.ll index 652f85d8833b6..50de773af0011 100644 --- a/test/CodeGen/X86/avx512-intrinsics-fast-isel.ll +++ b/test/CodeGen/X86/avx512-intrinsics-fast-isel.ll @@ -4,14 +4,552 @@ ; NOTE: This should use IR equivalent to what is generated by clang/test/CodeGen/avx512f-builtins.c + +define zeroext i16 @test_mm512_kunpackb(<8 x i64> %__A, <8 x i64> %__B, <8 x i64> %__C, <8 x i64> %__D, <8 x i64> %__E, <8 x i64> %__F) local_unnamed_addr #0 { +; X32-LABEL: test_mm512_kunpackb: +; X32: # %bb.0: # %entry +; X32-NEXT: pushl %ebp +; X32-NEXT: .cfi_def_cfa_offset 8 +; X32-NEXT: .cfi_offset %ebp, -8 +; X32-NEXT: movl %esp, %ebp +; X32-NEXT: .cfi_def_cfa_register %ebp +; X32-NEXT: andl $-64, %esp +; X32-NEXT: subl $64, %esp +; X32-NEXT: vmovdqa64 136(%ebp), %zmm3 +; X32-NEXT: vpcmpneqd %zmm1, %zmm0, %k0 +; X32-NEXT: vpcmpneqd 8(%ebp), %zmm2, %k1 +; X32-NEXT: kunpckbw %k0, %k1, %k1 +; X32-NEXT: vpcmpneqd 72(%ebp), %zmm3, %k0 {%k1} +; X32-NEXT: kmovw %k0, %eax +; X32-NEXT: movzwl %ax, %eax +; X32-NEXT: movl %ebp, %esp +; X32-NEXT: popl %ebp +; X32-NEXT: vzeroupper +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_kunpackb: +; X64: # %bb.0: # %entry +; X64-NEXT: vpcmpneqd %zmm1, %zmm0, %k0 +; X64-NEXT: vpcmpneqd %zmm3, %zmm2, %k1 +; X64-NEXT: kunpckbw %k0, %k1, %k1 +; X64-NEXT: vpcmpneqd %zmm5, %zmm4, %k0 {%k1} +; X64-NEXT: kmovw %k0, %eax +; X64-NEXT: movzwl %ax, %eax +; X64-NEXT: vzeroupper +; X64-NEXT: retq +entry: + %0 = bitcast <8 x i64> %__A to <16 x i32> + %1 = bitcast <8 x i64> %__B to <16 x i32> + %2 = icmp ne <16 x i32> %0, %1 + %3 = bitcast <16 x i1> %2 to i16 + %4 = bitcast <8 x i64> %__C to <16 x i32> + %5 = bitcast <8 x i64> %__D to <16 x i32> + %6 = icmp ne <16 x i32> %4, %5 + %7 = bitcast <16 x i1> %6 to i16 + %8 = and i16 %7, 255 + %shl.i = shl i16 %3, 8 + %or.i = or i16 %8, %shl.i + %9 = bitcast <8 x i64> %__E to <16 x i32> + %10 = bitcast <8 x i64> %__F to <16 x i32> + %11 = icmp ne <16 x i32> %9, %10 + %12 = bitcast i16 %or.i to <16 x i1> + %13 = and <16 x i1> %11, %12 + %14 = bitcast <16 x i1> %13 to i16 + ret i16 %14 +} + +define <16 x float> @test_mm512_shuffle_f32x4(<16 x float> %__A, <16 x float> %__B) { +; X32-LABEL: test_mm512_shuffle_f32x4: +; X32: # %bb.0: # %entry +; X32-NEXT: vshuff64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_shuffle_f32x4: +; X64: # %bb.0: # %entry +; X64-NEXT: vshuff64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <16 x float> %__A, <16 x float> %__B, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 16, i32 17, i32 18, i32 19> + ret <16 x float> %shuffle +} + + +define <16 x float> @test_mm512_mask_shuffle_f32x4(<16 x float> %__W, i16 zeroext %__U, <16 x float> %__A, <16 x float> %__B) { +; X32-LABEL: test_mm512_mask_shuffle_f32x4: +; X32: # %bb.0: # %entry +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 +; X32-NEXT: vshuff32x4 {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,3,4,5,6,7],zmm2[0,1,2,3,0,1,2,3] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_mask_shuffle_f32x4: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vshuff32x4 {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,3,4,5,6,7],zmm2[0,1,2,3,0,1,2,3] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <16 x float> %__A, <16 x float> %__B, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 16, i32 17, i32 18, i32 19> + %0 = bitcast i16 %__U to <16 x i1> + %1 = select <16 x i1> %0, <16 x float> %shuffle, <16 x float> %__W + ret <16 x float> %1 +} + +define <16 x float> @test_mm512_maskz_shuffle_f32x4(i16 zeroext %__U, <16 x float> %__A, <16 x float> %__B) { +; X32-LABEL: test_mm512_maskz_shuffle_f32x4: +; X32: # %bb.0: # %entry +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 +; X32-NEXT: vshuff32x4 {{.*#+}} zmm0 {%k1} {z} = zmm0[0,1,2,3,4,5,6,7],zmm1[0,1,2,3,0,1,2,3] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_maskz_shuffle_f32x4: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vshuff32x4 {{.*#+}} zmm0 {%k1} {z} = zmm0[0,1,2,3,4,5,6,7],zmm1[0,1,2,3,0,1,2,3] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <16 x float> %__A, <16 x float> %__B, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 16, i32 17, i32 18, i32 19> + %0 = bitcast i16 %__U to <16 x i1> + %1 = select <16 x i1> %0, <16 x float> %shuffle, <16 x float> zeroinitializer + ret <16 x float> %1 +} + +define <8 x double> @test_mm512_shuffle_f64x2(<8 x double> %__A, <8 x double> %__B) { +; X32-LABEL: test_mm512_shuffle_f64x2: +; X32: # %bb.0: # %entry +; X32-NEXT: vshuff64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_shuffle_f64x2: +; X64: # %bb.0: # %entry +; X64-NEXT: vshuff64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <8 x double> %__A, <8 x double> %__B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 8, i32 9> + ret <8 x double> %shuffle +} + +define <8 x double> @test_mm512_mask_shuffle_f64x2(<8 x double> %__W, i8 zeroext %__U, <8 x double> %__A, <8 x double> %__B) { +; X32-LABEL: test_mm512_mask_shuffle_f64x2: +; X32: # %bb.0: # %entry +; X32-NEXT: movb {{[0-9]+}}(%esp), %al +; X32-NEXT: kmovw %eax, %k1 +; X32-NEXT: vshuff64x2 {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,3],zmm2[0,1,0,1] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_mask_shuffle_f64x2: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vshuff64x2 {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,3],zmm2[0,1,0,1] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <8 x double> %__A, <8 x double> %__B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 8, i32 9> + %0 = bitcast i8 %__U to <8 x i1> + %1 = select <8 x i1> %0, <8 x double> %shuffle, <8 x double> %__W + ret <8 x double> %1 +} + +define <8 x double> @test_mm512_maskz_shuffle_f64x2(i8 zeroext %__U, <8 x double> %__A, <8 x double> %__B) { +; X32-LABEL: test_mm512_maskz_shuffle_f64x2: +; X32: # %bb.0: # %entry +; X32-NEXT: movb {{[0-9]+}}(%esp), %al +; X32-NEXT: kmovw %eax, %k1 +; X32-NEXT: vshuff64x2 {{.*#+}} zmm0 {%k1} {z} = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_maskz_shuffle_f64x2: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vshuff64x2 {{.*#+}} zmm0 {%k1} {z} = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <8 x double> %__A, <8 x double> %__B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 8, i32 9> + %0 = bitcast i8 %__U to <8 x i1> + %1 = select <8 x i1> %0, <8 x double> %shuffle, <8 x double> zeroinitializer + ret <8 x double> %1 +} + +define <8 x i64> @test_mm512_shuffle_i32x4(<8 x i64> %__A, <8 x i64> %__B) local_unnamed_addr #0 { +; X32-LABEL: test_mm512_shuffle_i32x4: +; X32: # %bb.0: # %entry +; X32-NEXT: vshufi64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_shuffle_i32x4: +; X64: # %bb.0: # %entry +; X64-NEXT: vshufi64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <8 x i64> %__A, <8 x i64> %__B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 8, i32 9> + ret <8 x i64> %shuffle +} + +define <8 x i64> @test_mm512_mask_shuffle_i32x4(<8 x i64> %__W, i16 zeroext %__U, <8 x i64> %__A, <8 x i64> %__B) local_unnamed_addr #0 { +; X32-LABEL: test_mm512_mask_shuffle_i32x4: +; X32: # %bb.0: # %entry +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 +; X32-NEXT: vshufi32x4 {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,3,4,5,6,7],zmm2[0,1,2,3,0,1,2,3] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_mask_shuffle_i32x4: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vshufi32x4 {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,3,4,5,6,7],zmm2[0,1,2,3,0,1,2,3] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <8 x i64> %__A, <8 x i64> %__B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 8, i32 9> + %0 = bitcast <8 x i64> %shuffle to <16 x i32> + %1 = bitcast <8 x i64> %__W to <16 x i32> + %2 = bitcast i16 %__U to <16 x i1> + %3 = select <16 x i1> %2, <16 x i32> %0, <16 x i32> %1 + %4 = bitcast <16 x i32> %3 to <8 x i64> + ret <8 x i64> %4 +} + +define <8 x i64> @test_mm512_maskz_shuffle_i32x4(i16 zeroext %__U, <8 x i64> %__A, <8 x i64> %__B) local_unnamed_addr #0 { +; X32-LABEL: test_mm512_maskz_shuffle_i32x4: +; X32: # %bb.0: # %entry +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 +; X32-NEXT: vshufi32x4 {{.*#+}} zmm0 {%k1} {z} = zmm0[0,1,2,3,4,5,6,7],zmm1[0,1,2,3,0,1,2,3] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_maskz_shuffle_i32x4: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vshufi32x4 {{.*#+}} zmm0 {%k1} {z} = zmm0[0,1,2,3,4,5,6,7],zmm1[0,1,2,3,0,1,2,3] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <8 x i64> %__A, <8 x i64> %__B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 8, i32 9> + %0 = bitcast <8 x i64> %shuffle to <16 x i32> + %1 = bitcast i16 %__U to <16 x i1> + %2 = select <16 x i1> %1, <16 x i32> %0, <16 x i32> zeroinitializer + %3 = bitcast <16 x i32> %2 to <8 x i64> + ret <8 x i64> %3 +} + +define <8 x i64> @test_mm512_shuffle_i64x2(<8 x i64> %__A, <8 x i64> %__B) local_unnamed_addr #0 { +; X32-LABEL: test_mm512_shuffle_i64x2: +; X32: # %bb.0: # %entry +; X32-NEXT: vshufi64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_shuffle_i64x2: +; X64: # %bb.0: # %entry +; X64-NEXT: vshufi64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <8 x i64> %__A, <8 x i64> %__B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 8, i32 9> + ret <8 x i64> %shuffle +} + +define <8 x i64> @test_mm512_mask_shuffle_i64x2(<8 x i64> %__W, i8 zeroext %__U, <8 x i64> %__A, <8 x i64> %__B) local_unnamed_addr #0 { +; X32-LABEL: test_mm512_mask_shuffle_i64x2: +; X32: # %bb.0: # %entry +; X32-NEXT: movb {{[0-9]+}}(%esp), %al +; X32-NEXT: kmovw %eax, %k1 +; X32-NEXT: vshufi64x2 {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,3],zmm2[0,1,0,1] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_mask_shuffle_i64x2: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vshufi64x2 {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,3],zmm2[0,1,0,1] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <8 x i64> %__A, <8 x i64> %__B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 8, i32 9> + %0 = bitcast i8 %__U to <8 x i1> + %1 = select <8 x i1> %0, <8 x i64> %shuffle, <8 x i64> %__W + ret <8 x i64> %1 +} + +define <8 x i64> @test_mm512_maskz_shuffle_i64x2(i8 zeroext %__U, <8 x i64> %__A, <8 x i64> %__B) local_unnamed_addr #0 { +; X32-LABEL: test_mm512_maskz_shuffle_i64x2: +; X32: # %bb.0: # %entry +; X32-NEXT: movb {{[0-9]+}}(%esp), %al +; X32-NEXT: kmovw %eax, %k1 +; X32-NEXT: vshufi64x2 {{.*#+}} zmm0 {%k1} {z} = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_maskz_shuffle_i64x2: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vshufi64x2 {{.*#+}} zmm0 {%k1} {z} = zmm0[0,1,2,3],zmm1[0,1,0,1] +; X64-NEXT: retq +entry: + %shuffle = shufflevector <8 x i64> %__A, <8 x i64> %__B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 8, i32 9> + %0 = bitcast i8 %__U to <8 x i1> + %1 = select <8 x i1> %0, <8 x i64> %shuffle, <8 x i64> zeroinitializer + ret <8 x i64> %1 +} + + +define zeroext i16 @test_mm512_testn_epi32_mask(<8 x i64> %__A, <8 x i64> %__B) { +; X32-LABEL: test_mm512_testn_epi32_mask: +; X32: # %bb.0: # %entry +; X32-NEXT: vptestnmd %zmm0, %zmm1, %k0 +; X32-NEXT: kmovw %k0, %eax +; X32-NEXT: movzwl %ax, %eax +; X32-NEXT: vzeroupper +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_testn_epi32_mask: +; X64: # %bb.0: # %entry +; X64-NEXT: vptestnmd %zmm0, %zmm1, %k0 +; X64-NEXT: kmovw %k0, %eax +; X64-NEXT: movzwl %ax, %eax +; X64-NEXT: vzeroupper +; X64-NEXT: retq +entry: + %and1.i.i = and <8 x i64> %__B, %__A + %0 = bitcast <8 x i64> %and1.i.i to <16 x i32> + %1 = icmp eq <16 x i32> %0, zeroinitializer + %2 = bitcast <16 x i1> %1 to i16 + ret i16 %2 +} + +define zeroext i16 @test_mm512_mask_testn_epi32_mask(i16 zeroext %__U, <8 x i64> %__A, <8 x i64> %__B) { +; X32-LABEL: test_mm512_mask_testn_epi32_mask: +; X32: # %bb.0: # %entry +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 +; X32-NEXT: vptestnmd %zmm0, %zmm1, %k0 {%k1} +; X32-NEXT: kmovw %k0, %eax +; X32-NEXT: movzwl %ax, %eax +; X32-NEXT: vzeroupper +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_mask_testn_epi32_mask: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vptestnmd %zmm0, %zmm1, %k0 {%k1} +; X64-NEXT: kmovw %k0, %eax +; X64-NEXT: movzwl %ax, %eax +; X64-NEXT: vzeroupper +; X64-NEXT: retq +entry: + %and1.i.i = and <8 x i64> %__B, %__A + %0 = bitcast <8 x i64> %and1.i.i to <16 x i32> + %1 = icmp eq <16 x i32> %0, zeroinitializer + %2 = bitcast i16 %__U to <16 x i1> + %3 = and <16 x i1> %1, %2 + %4 = bitcast <16 x i1> %3 to i16 + ret i16 %4 +} + +define zeroext i8 @test_mm512_testn_epi64_mask(<8 x i64> %__A, <8 x i64> %__B) { +; X32-LABEL: test_mm512_testn_epi64_mask: +; X32: # %bb.0: # %entry +; X32-NEXT: vptestnmq %zmm0, %zmm1, %k0 +; X32-NEXT: kmovw %k0, %eax +; X32-NEXT: movzbl %al, %eax +; X32-NEXT: vzeroupper +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_testn_epi64_mask: +; X64: # %bb.0: # %entry +; X64-NEXT: vptestnmq %zmm0, %zmm1, %k0 +; X64-NEXT: kmovw %k0, %eax +; X64-NEXT: movzbl %al, %eax +; X64-NEXT: vzeroupper +; X64-NEXT: retq +entry: + %and1.i.i = and <8 x i64> %__B, %__A + %0 = icmp eq <8 x i64> %and1.i.i, zeroinitializer + %1 = bitcast <8 x i1> %0 to i8 + ret i8 %1 +} + +define zeroext i8 @test_mm512_mask_testn_epi64_mask(i8 zeroext %__U, <8 x i64> %__A, <8 x i64> %__B) { +; X32-LABEL: test_mm512_mask_testn_epi64_mask: +; X32: # %bb.0: # %entry +; X32-NEXT: movb {{[0-9]+}}(%esp), %al +; X32-NEXT: kmovw %eax, %k1 +; X32-NEXT: vptestnmq %zmm0, %zmm1, %k0 {%k1} +; X32-NEXT: kmovw %k0, %eax +; X32-NEXT: movzbl %al, %eax +; X32-NEXT: vzeroupper +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_mask_testn_epi64_mask: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vptestnmq %zmm0, %zmm1, %k0 {%k1} +; X64-NEXT: kmovw %k0, %eax +; X64-NEXT: movzbl %al, %eax +; X64-NEXT: vzeroupper +; X64-NEXT: retq +entry: + %and1.i.i = and <8 x i64> %__B, %__A + %0 = icmp eq <8 x i64> %and1.i.i, zeroinitializer + %1 = bitcast i8 %__U to <8 x i1> + %2 = and <8 x i1> %0, %1 + %3 = bitcast <8 x i1> %2 to i8 + ret i8 %3 +} + +define zeroext i16 @test_mm512_mask_test_epi32_mask(i16 zeroext %__U, <8 x i64> %__A, <8 x i64> %__B) { +; X32-LABEL: test_mm512_mask_test_epi32_mask: +; X32: # %bb.0: # %entry +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 +; X32-NEXT: vptestmd %zmm0, %zmm1, %k0 {%k1} +; X32-NEXT: kmovw %k0, %eax +; X32-NEXT: movzwl %ax, %eax +; X32-NEXT: vzeroupper +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_mask_test_epi32_mask: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vptestmd %zmm0, %zmm1, %k0 {%k1} +; X64-NEXT: kmovw %k0, %eax +; X64-NEXT: movzwl %ax, %eax +; X64-NEXT: vzeroupper +; X64-NEXT: retq +entry: + %and1.i.i = and <8 x i64> %__B, %__A + %0 = bitcast <8 x i64> %and1.i.i to <16 x i32> + %1 = icmp ne <16 x i32> %0, zeroinitializer + %2 = bitcast i16 %__U to <16 x i1> + %3 = and <16 x i1> %1, %2 + %4 = bitcast <16 x i1> %3 to i16 + ret i16 %4 +} + +define zeroext i8 @test_mm512_mask_test_epi64_mask(i8 zeroext %__U, <8 x i64> %__A, <8 x i64> %__B) { +; X32-LABEL: test_mm512_mask_test_epi64_mask: +; X32: # %bb.0: # %entry +; X32-NEXT: movb {{[0-9]+}}(%esp), %al +; X32-NEXT: kmovw %eax, %k1 +; X32-NEXT: vptestmq %zmm0, %zmm1, %k0 {%k1} +; X32-NEXT: kmovw %k0, %eax +; X32-NEXT: movzbl %al, %eax +; X32-NEXT: vzeroupper +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_mask_test_epi64_mask: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vptestmq %zmm0, %zmm1, %k0 {%k1} +; X64-NEXT: kmovw %k0, %eax +; X64-NEXT: movzbl %al, %eax +; X64-NEXT: vzeroupper +; X64-NEXT: retq +entry: + %and1.i.i = and <8 x i64> %__B, %__A + %0 = icmp ne <8 x i64> %and1.i.i, zeroinitializer + %1 = bitcast i8 %__U to <8 x i1> + %2 = and <8 x i1> %0, %1 + %3 = bitcast <8 x i1> %2 to i8 + ret i8 %3 +} + +define <8 x i64> @test_mm512_mask_set1_epi32(<8 x i64> %__O, i16 zeroext %__M, i32 %__A) { +; X32-LABEL: test_mm512_mask_set1_epi32: +; X32: # %bb.0: # %entry +; X32-NEXT: movl {{[0-9]+}}(%esp), %eax +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 +; X32-NEXT: vpbroadcastd %eax, %zmm0 {%k1} +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_mask_set1_epi32: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vpbroadcastd %esi, %zmm0 {%k1} +; X64-NEXT: retq +entry: + %vecinit.i.i = insertelement <16 x i32> undef, i32 %__A, i32 0 + %vecinit15.i.i = shufflevector <16 x i32> %vecinit.i.i, <16 x i32> undef, <16 x i32> zeroinitializer + %0 = bitcast <8 x i64> %__O to <16 x i32> + %1 = bitcast i16 %__M to <16 x i1> + %2 = select <16 x i1> %1, <16 x i32> %vecinit15.i.i, <16 x i32> %0 + %3 = bitcast <16 x i32> %2 to <8 x i64> + ret <8 x i64> %3 +} + +define <8 x i64> @test_mm512_maskz_set1_epi32(i16 zeroext %__M, i32 %__A) { +; X32-LABEL: test_mm512_maskz_set1_epi32: +; X32: # %bb.0: # %entry +; X32-NEXT: movl {{[0-9]+}}(%esp), %eax +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 +; X32-NEXT: vpbroadcastd %eax, %zmm0 {%k1} {z} +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_maskz_set1_epi32: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vpbroadcastd %esi, %zmm0 {%k1} {z} +; X64-NEXT: retq +entry: + %vecinit.i.i = insertelement <16 x i32> undef, i32 %__A, i32 0 + %vecinit15.i.i = shufflevector <16 x i32> %vecinit.i.i, <16 x i32> undef, <16 x i32> zeroinitializer + %0 = bitcast i16 %__M to <16 x i1> + %1 = select <16 x i1> %0, <16 x i32> %vecinit15.i.i, <16 x i32> zeroinitializer + %2 = bitcast <16 x i32> %1 to <8 x i64> + ret <8 x i64> %2 +} + +define <8 x i64> @test_mm512_mask_set1_epi64(<8 x i64> %__O, i8 zeroext %__M, i64 %__A) { +; X32-LABEL: test_mm512_mask_set1_epi64: +; X32: # %bb.0: # %entry +; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X32-NEXT: movl {{[0-9]+}}(%esp), %edx +; X32-NEXT: movb {{[0-9]+}}(%esp), %al +; X32-NEXT: vmovd %edx, %xmm1 +; X32-NEXT: vpinsrd $1, %ecx, %xmm1, %xmm1 +; X32-NEXT: vpinsrd $2, %edx, %xmm1, %xmm1 +; X32-NEXT: vpinsrd $3, %ecx, %xmm1, %xmm1 +; X32-NEXT: vinserti128 $1, %xmm1, %ymm1, %ymm1 +; X32-NEXT: kmovw %eax, %k1 +; X32-NEXT: vinserti64x4 $1, %ymm1, %zmm1, %zmm0 {%k1} +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_mask_set1_epi64: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vpbroadcastq %rsi, %zmm0 {%k1} +; X64-NEXT: retq +entry: + %vecinit.i.i = insertelement <8 x i64> undef, i64 %__A, i32 0 + %vecinit7.i.i = shufflevector <8 x i64> %vecinit.i.i, <8 x i64> undef, <8 x i32> zeroinitializer + %0 = bitcast i8 %__M to <8 x i1> + %1 = select <8 x i1> %0, <8 x i64> %vecinit7.i.i, <8 x i64> %__O + ret <8 x i64> %1 +} + +define <8 x i64> @test_mm512_maskz_set1_epi64(i8 zeroext %__M, i64 %__A) { +; X32-LABEL: test_mm512_maskz_set1_epi64: +; X32: # %bb.0: # %entry +; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X32-NEXT: movl {{[0-9]+}}(%esp), %edx +; X32-NEXT: movb {{[0-9]+}}(%esp), %al +; X32-NEXT: vmovd %edx, %xmm0 +; X32-NEXT: vpinsrd $1, %ecx, %xmm0, %xmm0 +; X32-NEXT: vpinsrd $2, %edx, %xmm0, %xmm0 +; X32-NEXT: vpinsrd $3, %ecx, %xmm0, %xmm0 +; X32-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm0 +; X32-NEXT: kmovw %eax, %k1 +; X32-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0 {%k1} {z} +; X32-NEXT: retl +; +; X64-LABEL: test_mm512_maskz_set1_epi64: +; X64: # %bb.0: # %entry +; X64-NEXT: kmovw %edi, %k1 +; X64-NEXT: vpbroadcastq %rsi, %zmm0 {%k1} {z} +; X64-NEXT: retq +entry: + %vecinit.i.i = insertelement <8 x i64> undef, i64 %__A, i32 0 + %vecinit7.i.i = shufflevector <8 x i64> %vecinit.i.i, <8 x i64> undef, <8 x i32> zeroinitializer + %0 = bitcast i8 %__M to <8 x i1> + %1 = select <8 x i1> %0, <8 x i64> %vecinit7.i.i, <8 x i64> zeroinitializer + ret <8 x i64> %1 +} + + define <8 x i64> @test_mm512_broadcastd_epi32(<2 x i64> %a0) { ; X32-LABEL: test_mm512_broadcastd_epi32: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vbroadcastss %xmm0, %zmm0 ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_broadcastd_epi32: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vbroadcastss %xmm0, %zmm0 ; X64-NEXT: retq %arg0 = bitcast <2 x i64> %a0 to <4 x i32> @@ -22,14 +560,13 @@ define <8 x i64> @test_mm512_broadcastd_epi32(<2 x i64> %a0) { define <8 x i64> @test_mm512_mask_broadcastd_epi32(<8 x i64> %a0, i16 %a1, <2 x i64> %a2) { ; X32-LABEL: test_mm512_mask_broadcastd_epi32: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vpbroadcastd %xmm1, %zmm0 {%k1} ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_broadcastd_epi32: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpbroadcastd %xmm1, %zmm0 {%k1} ; X64-NEXT: retq @@ -44,14 +581,13 @@ define <8 x i64> @test_mm512_mask_broadcastd_epi32(<8 x i64> %a0, i16 %a1, <2 x define <8 x i64> @test_mm512_maskz_broadcastd_epi32(i16 %a0, <2 x i64> %a1) { ; X32-LABEL: test_mm512_maskz_broadcastd_epi32: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vpbroadcastd %xmm0, %zmm0 {%k1} {z} ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_broadcastd_epi32: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpbroadcastd %xmm0, %zmm0 {%k1} {z} ; X64-NEXT: retq @@ -65,12 +601,12 @@ define <8 x i64> @test_mm512_maskz_broadcastd_epi32(i16 %a0, <2 x i64> %a1) { define <8 x i64> @test_mm512_broadcastq_epi64(<2 x i64> %a0) { ; X32-LABEL: test_mm512_broadcastq_epi64: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vbroadcastsd %xmm0, %zmm0 ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_broadcastq_epi64: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vbroadcastsd %xmm0, %zmm0 ; X64-NEXT: retq %res = shufflevector <2 x i64> %a0, <2 x i64> undef, <8 x i32> zeroinitializer @@ -79,14 +615,14 @@ define <8 x i64> @test_mm512_broadcastq_epi64(<2 x i64> %a0) { define <8 x i64> @test_mm512_mask_broadcastq_epi64(<8 x i64> %a0, i8 %a1, <2 x i64> %a2) { ; X32-LABEL: test_mm512_mask_broadcastq_epi64: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpbroadcastq %xmm1, %zmm0 {%k1} ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_broadcastq_epi64: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpbroadcastq %xmm1, %zmm0 {%k1} ; X64-NEXT: retq @@ -98,14 +634,14 @@ define <8 x i64> @test_mm512_mask_broadcastq_epi64(<8 x i64> %a0, i8 %a1, <2 x i define <8 x i64> @test_mm512_maskz_broadcastq_epi64(i8 %a0, <2 x i64> %a1) { ; X32-LABEL: test_mm512_maskz_broadcastq_epi64: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpbroadcastq %xmm0, %zmm0 {%k1} {z} ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_broadcastq_epi64: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpbroadcastq %xmm0, %zmm0 {%k1} {z} ; X64-NEXT: retq @@ -117,12 +653,12 @@ define <8 x i64> @test_mm512_maskz_broadcastq_epi64(i8 %a0, <2 x i64> %a1) { define <8 x double> @test_mm512_broadcastsd_pd(<2 x double> %a0) { ; X32-LABEL: test_mm512_broadcastsd_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vbroadcastsd %xmm0, %zmm0 ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_broadcastsd_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vbroadcastsd %xmm0, %zmm0 ; X64-NEXT: retq %res = shufflevector <2 x double> %a0, <2 x double> undef, <8 x i32> zeroinitializer @@ -131,14 +667,14 @@ define <8 x double> @test_mm512_broadcastsd_pd(<2 x double> %a0) { define <8 x double> @test_mm512_mask_broadcastsd_pd(<8 x double> %a0, i8 %a1, <2 x double> %a2) { ; X32-LABEL: test_mm512_mask_broadcastsd_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vbroadcastsd %xmm1, %zmm0 {%k1} ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_broadcastsd_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vbroadcastsd %xmm1, %zmm0 {%k1} ; X64-NEXT: retq @@ -150,14 +686,14 @@ define <8 x double> @test_mm512_mask_broadcastsd_pd(<8 x double> %a0, i8 %a1, <2 define <8 x double> @test_mm512_maskz_broadcastsd_pd(i8 %a0, <2 x double> %a1) { ; X32-LABEL: test_mm512_maskz_broadcastsd_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vbroadcastsd %xmm0, %zmm0 {%k1} {z} ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_broadcastsd_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vbroadcastsd %xmm0, %zmm0 {%k1} {z} ; X64-NEXT: retq @@ -169,12 +705,12 @@ define <8 x double> @test_mm512_maskz_broadcastsd_pd(i8 %a0, <2 x double> %a1) { define <16 x float> @test_mm512_broadcastss_ps(<4 x float> %a0) { ; X32-LABEL: test_mm512_broadcastss_ps: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vbroadcastss %xmm0, %zmm0 ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_broadcastss_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vbroadcastss %xmm0, %zmm0 ; X64-NEXT: retq %res = shufflevector <4 x float> %a0, <4 x float> undef, <16 x i32> zeroinitializer @@ -183,14 +719,13 @@ define <16 x float> @test_mm512_broadcastss_ps(<4 x float> %a0) { define <16 x float> @test_mm512_mask_broadcastss_ps(<16 x float> %a0, i16 %a1, <4 x float> %a2) { ; X32-LABEL: test_mm512_mask_broadcastss_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vbroadcastss %xmm1, %zmm0 {%k1} ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_broadcastss_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vbroadcastss %xmm1, %zmm0 {%k1} ; X64-NEXT: retq @@ -202,14 +737,13 @@ define <16 x float> @test_mm512_mask_broadcastss_ps(<16 x float> %a0, i16 %a1, < define <16 x float> @test_mm512_maskz_broadcastss_ps(i16 %a0, <4 x float> %a1) { ; X32-LABEL: test_mm512_maskz_broadcastss_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vbroadcastss %xmm0, %zmm0 {%k1} {z} ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_broadcastss_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vbroadcastss %xmm0, %zmm0 {%k1} {z} ; X64-NEXT: retq @@ -221,12 +755,12 @@ define <16 x float> @test_mm512_maskz_broadcastss_ps(i16 %a0, <4 x float> %a1) { define <8 x double> @test_mm512_movddup_pd(<8 x double> %a0) { ; X32-LABEL: test_mm512_movddup_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vmovddup {{.*#+}} zmm0 = zmm0[0,0,2,2,4,4,6,6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_movddup_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vmovddup {{.*#+}} zmm0 = zmm0[0,0,2,2,4,4,6,6] ; X64-NEXT: retq %res = shufflevector <8 x double> %a0, <8 x double> undef, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6> @@ -235,14 +769,14 @@ define <8 x double> @test_mm512_movddup_pd(<8 x double> %a0) { define <8 x double> @test_mm512_mask_movddup_pd(<8 x double> %a0, i8 %a1, <8 x double> %a2) { ; X32-LABEL: test_mm512_mask_movddup_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vmovddup {{.*#+}} zmm0 {%k1} = zmm1[0,0,2,2,4,4,6,6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_movddup_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vmovddup {{.*#+}} zmm0 {%k1} = zmm1[0,0,2,2,4,4,6,6] ; X64-NEXT: retq @@ -254,14 +788,14 @@ define <8 x double> @test_mm512_mask_movddup_pd(<8 x double> %a0, i8 %a1, <8 x d define <8 x double> @test_mm512_maskz_movddup_pd(i8 %a0, <8 x double> %a1) { ; X32-LABEL: test_mm512_maskz_movddup_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vmovddup {{.*#+}} zmm0 {%k1} {z} = zmm0[0,0,2,2,4,4,6,6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_movddup_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vmovddup {{.*#+}} zmm0 {%k1} {z} = zmm0[0,0,2,2,4,4,6,6] ; X64-NEXT: retq @@ -273,12 +807,12 @@ define <8 x double> @test_mm512_maskz_movddup_pd(i8 %a0, <8 x double> %a1) { define <16 x float> @test_mm512_movehdup_ps(<16 x float> %a0) { ; X32-LABEL: test_mm512_movehdup_ps: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vmovshdup {{.*#+}} zmm0 = zmm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_movehdup_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vmovshdup {{.*#+}} zmm0 = zmm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15] ; X64-NEXT: retq %res = shufflevector <16 x float> %a0, <16 x float> undef, <16 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7, i32 9, i32 9, i32 11, i32 11, i32 13, i32 13, i32 15, i32 15> @@ -287,14 +821,13 @@ define <16 x float> @test_mm512_movehdup_ps(<16 x float> %a0) { define <16 x float> @test_mm512_mask_movehdup_ps(<16 x float> %a0, i16 %a1, <16 x float> %a2) { ; X32-LABEL: test_mm512_mask_movehdup_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vmovshdup {{.*#+}} zmm0 {%k1} = zmm1[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_movehdup_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vmovshdup {{.*#+}} zmm0 {%k1} = zmm1[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15] ; X64-NEXT: retq @@ -306,14 +839,13 @@ define <16 x float> @test_mm512_mask_movehdup_ps(<16 x float> %a0, i16 %a1, <16 define <16 x float> @test_mm512_maskz_movehdup_ps(i16 %a0, <16 x float> %a1) { ; X32-LABEL: test_mm512_maskz_movehdup_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vmovshdup {{.*#+}} zmm0 {%k1} {z} = zmm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_movehdup_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vmovshdup {{.*#+}} zmm0 {%k1} {z} = zmm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15] ; X64-NEXT: retq @@ -325,12 +857,12 @@ define <16 x float> @test_mm512_maskz_movehdup_ps(i16 %a0, <16 x float> %a1) { define <16 x float> @test_mm512_moveldup_ps(<16 x float> %a0) { ; X32-LABEL: test_mm512_moveldup_ps: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vmovsldup {{.*#+}} zmm0 = zmm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_moveldup_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vmovsldup {{.*#+}} zmm0 = zmm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14] ; X64-NEXT: retq %res = shufflevector <16 x float> %a0, <16 x float> undef, <16 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6, i32 8, i32 8, i32 10, i32 10, i32 12, i32 12, i32 14, i32 14> @@ -339,14 +871,13 @@ define <16 x float> @test_mm512_moveldup_ps(<16 x float> %a0) { define <16 x float> @test_mm512_mask_moveldup_ps(<16 x float> %a0, i16 %a1, <16 x float> %a2) { ; X32-LABEL: test_mm512_mask_moveldup_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vmovsldup {{.*#+}} zmm0 {%k1} = zmm1[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_moveldup_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vmovsldup {{.*#+}} zmm0 {%k1} = zmm1[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14] ; X64-NEXT: retq @@ -358,14 +889,13 @@ define <16 x float> @test_mm512_mask_moveldup_ps(<16 x float> %a0, i16 %a1, <16 define <16 x float> @test_mm512_maskz_moveldup_ps(i16 %a0, <16 x float> %a1) { ; X32-LABEL: test_mm512_maskz_moveldup_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vmovsldup {{.*#+}} zmm0 {%k1} {z} = zmm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_moveldup_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vmovsldup {{.*#+}} zmm0 {%k1} {z} = zmm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14] ; X64-NEXT: retq @@ -377,12 +907,12 @@ define <16 x float> @test_mm512_maskz_moveldup_ps(i16 %a0, <16 x float> %a1) { define <8 x double> @test_mm512_permute_pd(<8 x double> %a0) { ; X32-LABEL: test_mm512_permute_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vpermilpd {{.*#+}} zmm0 = zmm0[0,1,2,2,4,4,6,6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_permute_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vpermilpd {{.*#+}} zmm0 = zmm0[0,1,2,2,4,4,6,6] ; X64-NEXT: retq %res = shufflevector <8 x double> %a0, <8 x double> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6> @@ -391,14 +921,14 @@ define <8 x double> @test_mm512_permute_pd(<8 x double> %a0) { define <8 x double> @test_mm512_mask_permute_pd(<8 x double> %a0, i8 %a1, <8 x double> %a2) { ; X32-LABEL: test_mm512_mask_permute_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpermilpd {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,2,4,4,6,6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_permute_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpermilpd {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,2,4,4,6,6] ; X64-NEXT: retq @@ -410,14 +940,14 @@ define <8 x double> @test_mm512_mask_permute_pd(<8 x double> %a0, i8 %a1, <8 x d define <8 x double> @test_mm512_maskz_permute_pd(i8 %a0, <8 x double> %a1) { ; X32-LABEL: test_mm512_maskz_permute_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpermilpd {{.*#+}} zmm0 {%k1} {z} = zmm0[0,1,2,2,4,4,6,6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_permute_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpermilpd {{.*#+}} zmm0 {%k1} {z} = zmm0[0,1,2,2,4,4,6,6] ; X64-NEXT: retq @@ -429,12 +959,12 @@ define <8 x double> @test_mm512_maskz_permute_pd(i8 %a0, <8 x double> %a1) { define <16 x float> @test_mm512_permute_ps(<16 x float> %a0) { ; X32-LABEL: test_mm512_permute_ps: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vpermilps {{.*#+}} zmm0 = zmm0[2,0,0,0,6,4,4,4,10,8,8,8,14,12,12,12] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_permute_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vpermilps {{.*#+}} zmm0 = zmm0[2,0,0,0,6,4,4,4,10,8,8,8,14,12,12,12] ; X64-NEXT: retq %res = shufflevector <16 x float> %a0, <16 x float> undef, <16 x i32> <i32 2, i32 0, i32 0, i32 0, i32 6, i32 4, i32 4, i32 4, i32 10, i32 8, i32 8, i32 8, i32 14, i32 12, i32 12, i32 12> @@ -443,14 +973,13 @@ define <16 x float> @test_mm512_permute_ps(<16 x float> %a0) { define <16 x float> @test_mm512_mask_permute_ps(<16 x float> %a0, i16 %a1, <16 x float> %a2) { ; X32-LABEL: test_mm512_mask_permute_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vpermilps {{.*#+}} zmm0 {%k1} = zmm1[2,0,0,0,6,4,4,4,10,8,8,8,14,12,12,12] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_permute_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpermilps {{.*#+}} zmm0 {%k1} = zmm1[2,0,0,0,6,4,4,4,10,8,8,8,14,12,12,12] ; X64-NEXT: retq @@ -462,14 +991,13 @@ define <16 x float> @test_mm512_mask_permute_ps(<16 x float> %a0, i16 %a1, <16 x define <16 x float> @test_mm512_maskz_permute_ps(i16 %a0, <16 x float> %a1) { ; X32-LABEL: test_mm512_maskz_permute_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vpermilps {{.*#+}} zmm0 {%k1} {z} = zmm0[2,0,0,0,6,4,4,4,10,8,8,8,14,12,12,12] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_permute_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpermilps {{.*#+}} zmm0 {%k1} {z} = zmm0[2,0,0,0,6,4,4,4,10,8,8,8,14,12,12,12] ; X64-NEXT: retq @@ -481,13 +1009,13 @@ define <16 x float> @test_mm512_maskz_permute_ps(i16 %a0, <16 x float> %a1) { define <8 x i64> @test_mm512_permutex_epi64(<8 x i64> %a0) { ; X32-LABEL: test_mm512_permutex_epi64: -; X32: # BB#0: -; X32-NEXT: vpermq {{.*#+}} zmm0 = zmm0[0,0,0,0,4,4,4,4] +; X32: # %bb.0: +; X32-NEXT: vpermpd {{.*#+}} zmm0 = zmm0[0,0,0,0,4,4,4,4] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_permutex_epi64: -; X64: # BB#0: -; X64-NEXT: vpermq {{.*#+}} zmm0 = zmm0[0,0,0,0,4,4,4,4] +; X64: # %bb.0: +; X64-NEXT: vpermpd {{.*#+}} zmm0 = zmm0[0,0,0,0,4,4,4,4] ; X64-NEXT: retq %res = shufflevector <8 x i64> %a0, <8 x i64> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4> ret <8 x i64> %res @@ -495,14 +1023,14 @@ define <8 x i64> @test_mm512_permutex_epi64(<8 x i64> %a0) { define <8 x i64> @test_mm512_mask_permutex_epi64(<8 x i64> %a0, i8 %a1, <8 x i64> %a2) { ; X32-LABEL: test_mm512_mask_permutex_epi64: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpermq {{.*#+}} zmm0 {%k1} = zmm1[0,0,0,0,4,4,4,4] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_permutex_epi64: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpermq {{.*#+}} zmm0 {%k1} = zmm1[0,0,0,0,4,4,4,4] ; X64-NEXT: retq @@ -514,14 +1042,14 @@ define <8 x i64> @test_mm512_mask_permutex_epi64(<8 x i64> %a0, i8 %a1, <8 x i64 define <8 x i64> @test_mm512_maskz_permutex_epi64(i8 %a0, <8 x i64> %a1) { ; X32-LABEL: test_mm512_maskz_permutex_epi64: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpermq {{.*#+}} zmm0 {%k1} {z} = zmm0[0,0,0,0,4,4,4,4] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_permutex_epi64: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpermq {{.*#+}} zmm0 {%k1} {z} = zmm0[0,0,0,0,4,4,4,4] ; X64-NEXT: retq @@ -533,12 +1061,12 @@ define <8 x i64> @test_mm512_maskz_permutex_epi64(i8 %a0, <8 x i64> %a1) { define <8 x double> @test_mm512_permutex_pd(<8 x double> %a0) { ; X32-LABEL: test_mm512_permutex_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vpermpd {{.*#+}} zmm0 = zmm0[0,0,0,0,4,4,4,4] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_permutex_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vpermpd {{.*#+}} zmm0 = zmm0[0,0,0,0,4,4,4,4] ; X64-NEXT: retq %res = shufflevector <8 x double> %a0, <8 x double> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4> @@ -547,14 +1075,14 @@ define <8 x double> @test_mm512_permutex_pd(<8 x double> %a0) { define <8 x double> @test_mm512_mask_permutex_pd(<8 x double> %a0, i8 %a1, <8 x double> %a2) { ; X32-LABEL: test_mm512_mask_permutex_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpermpd {{.*#+}} zmm0 {%k1} = zmm1[0,0,0,0,4,4,4,4] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_permutex_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpermpd {{.*#+}} zmm0 {%k1} = zmm1[0,0,0,0,4,4,4,4] ; X64-NEXT: retq @@ -566,14 +1094,14 @@ define <8 x double> @test_mm512_mask_permutex_pd(<8 x double> %a0, i8 %a1, <8 x define <8 x double> @test_mm512_maskz_permutex_pd(i8 %a0, <8 x double> %a1) { ; X32-LABEL: test_mm512_maskz_permutex_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpermpd {{.*#+}} zmm0 {%k1} {z} = zmm0[0,0,0,0,4,4,4,4] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_permutex_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpermpd {{.*#+}} zmm0 {%k1} {z} = zmm0[0,0,0,0,4,4,4,4] ; X64-NEXT: retq @@ -585,13 +1113,13 @@ define <8 x double> @test_mm512_maskz_permutex_pd(i8 %a0, <8 x double> %a1) { define <8 x i64> @test_mm512_shuffle_epi32(<8 x i64> %a0) { ; X32-LABEL: test_mm512_shuffle_epi32: -; X32: # BB#0: -; X32-NEXT: vpshufd {{.*#+}} zmm0 = zmm0[1,0,0,0,5,4,4,4,9,8,8,8,13,12,12,12] +; X32: # %bb.0: +; X32-NEXT: vpermilps {{.*#+}} zmm0 = zmm0[1,0,0,0,5,4,4,4,9,8,8,8,13,12,12,12] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_shuffle_epi32: -; X64: # BB#0: -; X64-NEXT: vpshufd {{.*#+}} zmm0 = zmm0[1,0,0,0,5,4,4,4,9,8,8,8,13,12,12,12] +; X64: # %bb.0: +; X64-NEXT: vpermilps {{.*#+}} zmm0 = zmm0[1,0,0,0,5,4,4,4,9,8,8,8,13,12,12,12] ; X64-NEXT: retq %arg0 = bitcast <8 x i64> %a0 to <16 x i32> %res0 = shufflevector <16 x i32> %arg0, <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> @@ -601,14 +1129,13 @@ define <8 x i64> @test_mm512_shuffle_epi32(<8 x i64> %a0) { define <8 x i64> @test_mm512_mask_shuffle_epi32(<8 x i64> %a0, i16 %a1, <8 x i64> %a2) { ; X32-LABEL: test_mm512_mask_shuffle_epi32: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vpshufd {{.*#+}} zmm0 {%k1} = zmm1[1,0,0,0,5,4,4,4,9,8,8,8,13,12,12,12] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_shuffle_epi32: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpshufd {{.*#+}} zmm0 {%k1} = zmm1[1,0,0,0,5,4,4,4,9,8,8,8,13,12,12,12] ; X64-NEXT: retq @@ -623,14 +1150,13 @@ define <8 x i64> @test_mm512_mask_shuffle_epi32(<8 x i64> %a0, i16 %a1, <8 x i64 define <8 x i64> @test_mm512_maskz_shuffle_epi32(i16 %a0, <8 x i64> %a1) { ; X32-LABEL: test_mm512_maskz_shuffle_epi32: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vpshufd {{.*#+}} zmm0 {%k1} {z} = zmm0[1,0,0,0,5,4,4,4,9,8,8,8,13,12,12,12] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_shuffle_epi32: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpshufd {{.*#+}} zmm0 {%k1} {z} = zmm0[1,0,0,0,5,4,4,4,9,8,8,8,13,12,12,12] ; X64-NEXT: retq @@ -644,12 +1170,12 @@ define <8 x i64> @test_mm512_maskz_shuffle_epi32(i16 %a0, <8 x i64> %a1) { define <8 x double> @test_mm512_shuffle_pd(<8 x double> %a0, <8 x double> %a1) { ; X32-LABEL: test_mm512_shuffle_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vshufpd {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[3],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_shuffle_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vshufpd {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[3],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X64-NEXT: retq %res = shufflevector <8 x double> %a0, <8 x double> %a1, <8 x i32> <i32 0, i32 8, i32 3, i32 10, i32 4, i32 12, i32 6, i32 14> @@ -658,14 +1184,14 @@ define <8 x double> @test_mm512_shuffle_pd(<8 x double> %a0, <8 x double> %a1) { define <8 x double> @test_mm512_mask_shuffle_pd(<8 x double> %a0, i8 %a1, <8 x double> %a2, <8 x double> %a3) { ; X32-LABEL: test_mm512_mask_shuffle_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vshufpd {{.*#+}} zmm0 {%k1} = zmm1[0],zmm2[0],zmm1[3],zmm2[2],zmm1[4],zmm2[4],zmm1[6],zmm2[6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_shuffle_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vshufpd {{.*#+}} zmm0 {%k1} = zmm1[0],zmm2[0],zmm1[3],zmm2[2],zmm1[4],zmm2[4],zmm1[6],zmm2[6] ; X64-NEXT: retq @@ -677,14 +1203,14 @@ define <8 x double> @test_mm512_mask_shuffle_pd(<8 x double> %a0, i8 %a1, <8 x d define <8 x double> @test_mm512_maskz_shuffle_pd(i8 %a0, <8 x double> %a1, <8 x double> %a2) { ; X32-LABEL: test_mm512_maskz_shuffle_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vshufpd {{.*#+}} zmm0 {%k1} {z} = zmm0[0],zmm1[0],zmm0[3],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_shuffle_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vshufpd {{.*#+}} zmm0 {%k1} {z} = zmm0[0],zmm1[0],zmm0[3],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X64-NEXT: retq @@ -696,13 +1222,13 @@ define <8 x double> @test_mm512_maskz_shuffle_pd(i8 %a0, <8 x double> %a1, <8 x define <8 x i64> @test_mm512_unpackhi_epi32(<8 x i64> %a0, <8 x i64> %a1) { ; X32-LABEL: test_mm512_unpackhi_epi32: -; X32: # BB#0: -; X32-NEXT: vpunpckhdq {{.*#+}} zmm0 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15] +; X32: # %bb.0: +; X32-NEXT: vunpckhps {{.*#+}} zmm0 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_unpackhi_epi32: -; X64: # BB#0: -; X64-NEXT: vpunpckhdq {{.*#+}} zmm0 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15] +; X64: # %bb.0: +; X64-NEXT: vunpckhps {{.*#+}} zmm0 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15] ; X64-NEXT: retq %arg0 = bitcast <8 x i64> %a0 to <16 x i32> %arg1 = bitcast <8 x i64> %a1 to <16 x i32> @@ -713,14 +1239,13 @@ define <8 x i64> @test_mm512_unpackhi_epi32(<8 x i64> %a0, <8 x i64> %a1) { define <8 x i64> @test_mm512_mask_unpackhi_epi32(<8 x i64> %a0, i16 %a1, <8 x i64> %a2, <8 x i64> %a3) { ; X32-LABEL: test_mm512_mask_unpackhi_epi32: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vpunpckhdq {{.*#+}} zmm0 {%k1} = zmm1[2],zmm2[2],zmm1[3],zmm2[3],zmm1[6],zmm2[6],zmm1[7],zmm2[7],zmm1[10],zmm2[10],zmm1[11],zmm2[11],zmm1[14],zmm2[14],zmm1[15],zmm2[15] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_unpackhi_epi32: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpunpckhdq {{.*#+}} zmm0 {%k1} = zmm1[2],zmm2[2],zmm1[3],zmm2[3],zmm1[6],zmm2[6],zmm1[7],zmm2[7],zmm1[10],zmm2[10],zmm1[11],zmm2[11],zmm1[14],zmm2[14],zmm1[15],zmm2[15] ; X64-NEXT: retq @@ -736,14 +1261,13 @@ define <8 x i64> @test_mm512_mask_unpackhi_epi32(<8 x i64> %a0, i16 %a1, <8 x i6 define <8 x i64> @test_mm512_maskz_unpackhi_epi32(i16 %a0, <8 x i64> %a1, <8 x i64> %a2) { ; X32-LABEL: test_mm512_maskz_unpackhi_epi32: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vpunpckhdq {{.*#+}} zmm0 {%k1} {z} = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_unpackhi_epi32: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpunpckhdq {{.*#+}} zmm0 {%k1} {z} = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15] ; X64-NEXT: retq @@ -758,13 +1282,13 @@ define <8 x i64> @test_mm512_maskz_unpackhi_epi32(i16 %a0, <8 x i64> %a1, <8 x i define <8 x i64> @test_mm512_unpackhi_epi64(<8 x i64> %a0, <8 x i64> %a1) { ; X32-LABEL: test_mm512_unpackhi_epi64: -; X32: # BB#0: -; X32-NEXT: vpunpckhqdq {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7] +; X32: # %bb.0: +; X32-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_unpackhi_epi64: -; X64: # BB#0: -; X64-NEXT: vpunpckhqdq {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7] +; X64: # %bb.0: +; X64-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7] ; X64-NEXT: retq %res = shufflevector <8 x i64> %a0, <8 x i64> %a1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15> ret <8 x i64> %res @@ -772,14 +1296,14 @@ define <8 x i64> @test_mm512_unpackhi_epi64(<8 x i64> %a0, <8 x i64> %a1) { define <8 x i64> @test_mm512_mask_unpackhi_epi64(<8 x i64> %a0, i8 %a1, <8 x i64> %a2, <8 x i64> %a3) { ; X32-LABEL: test_mm512_mask_unpackhi_epi64: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpunpckhqdq {{.*#+}} zmm0 = zmm1[1],zmm2[1],zmm1[3],zmm2[3],zmm1[5],zmm2[5],zmm1[7],zmm2[7] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_unpackhi_epi64: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpunpckhqdq {{.*#+}} zmm0 = zmm1[1],zmm2[1],zmm1[3],zmm2[3],zmm1[5],zmm2[5],zmm1[7],zmm2[7] ; X64-NEXT: retq @@ -791,14 +1315,14 @@ define <8 x i64> @test_mm512_mask_unpackhi_epi64(<8 x i64> %a0, i8 %a1, <8 x i64 define <8 x i64> @test_mm512_maskz_unpackhi_epi64(i8 %a0, <8 x i64> %a1, <8 x i64> %a2) { ; X32-LABEL: test_mm512_maskz_unpackhi_epi64: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpunpckhqdq {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_unpackhi_epi64: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpunpckhqdq {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7] ; X64-NEXT: retq @@ -810,12 +1334,12 @@ define <8 x i64> @test_mm512_maskz_unpackhi_epi64(i8 %a0, <8 x i64> %a1, <8 x i6 define <8 x double> @test_mm512_unpackhi_pd(<8 x double> %a0, <8 x double> %a1) { ; X32-LABEL: test_mm512_unpackhi_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_unpackhi_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7] ; X64-NEXT: retq %res = shufflevector <8 x double> %a0, <8 x double> %a1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15> @@ -824,14 +1348,14 @@ define <8 x double> @test_mm512_unpackhi_pd(<8 x double> %a0, <8 x double> %a1) define <8 x double> @test_mm512_mask_unpackhi_pd(<8 x double> %a0, i8 %a1, <8 x double> %a2, <8 x double> %a3) { ; X32-LABEL: test_mm512_mask_unpackhi_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vunpckhpd {{.*#+}} zmm0 {%k1} = zmm1[1],zmm2[1],zmm1[3],zmm2[3],zmm1[5],zmm2[5],zmm1[7],zmm2[7] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_unpackhi_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vunpckhpd {{.*#+}} zmm0 {%k1} = zmm1[1],zmm2[1],zmm1[3],zmm2[3],zmm1[5],zmm2[5],zmm1[7],zmm2[7] ; X64-NEXT: retq @@ -843,14 +1367,14 @@ define <8 x double> @test_mm512_mask_unpackhi_pd(<8 x double> %a0, i8 %a1, <8 x define <8 x double> @test_mm512_maskz_unpackhi_pd(i8 %a0, <8 x double> %a1, <8 x double> %a2) { ; X32-LABEL: test_mm512_maskz_unpackhi_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vunpckhpd {{.*#+}} zmm0 {%k1} {z} = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_unpackhi_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vunpckhpd {{.*#+}} zmm0 {%k1} {z} = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7] ; X64-NEXT: retq @@ -862,12 +1386,12 @@ define <8 x double> @test_mm512_maskz_unpackhi_pd(i8 %a0, <8 x double> %a1, <8 x define <16 x float> @test_mm512_unpackhi_ps(<16 x float> %a0, <16 x float> %a1) { ; X32-LABEL: test_mm512_unpackhi_ps: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vunpckhps {{.*#+}} zmm0 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_unpackhi_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vunpckhps {{.*#+}} zmm0 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15] ; X64-NEXT: retq %res = shufflevector <16 x float> %a0, <16 x float> %a1, <16 x i32> <i32 2, i32 18, i32 3, i32 19, i32 6, i32 22, i32 7, i32 23, i32 10, i32 26, i32 11, i32 27, i32 14, i32 30, i32 15, i32 31> @@ -876,14 +1400,13 @@ define <16 x float> @test_mm512_unpackhi_ps(<16 x float> %a0, <16 x float> %a1) define <16 x float> @test_mm512_mask_unpackhi_ps(<16 x float> %a0, i16 %a1, <16 x float> %a2, <16 x float> %a3) { ; X32-LABEL: test_mm512_mask_unpackhi_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vunpckhps {{.*#+}} zmm0 {%k1} = zmm1[2],zmm2[2],zmm1[3],zmm2[3],zmm1[6],zmm2[6],zmm1[7],zmm2[7],zmm1[10],zmm2[10],zmm1[11],zmm2[11],zmm1[14],zmm2[14],zmm1[15],zmm2[15] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_unpackhi_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vunpckhps {{.*#+}} zmm0 {%k1} = zmm1[2],zmm2[2],zmm1[3],zmm2[3],zmm1[6],zmm2[6],zmm1[7],zmm2[7],zmm1[10],zmm2[10],zmm1[11],zmm2[11],zmm1[14],zmm2[14],zmm1[15],zmm2[15] ; X64-NEXT: retq @@ -895,14 +1418,13 @@ define <16 x float> @test_mm512_mask_unpackhi_ps(<16 x float> %a0, i16 %a1, <16 define <16 x float> @test_mm512_maskz_unpackhi_ps(i16 %a0, <16 x float> %a1, <16 x float> %a2) { ; X32-LABEL: test_mm512_maskz_unpackhi_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vunpckhps {{.*#+}} zmm0 {%k1} {z} = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_unpackhi_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vunpckhps {{.*#+}} zmm0 {%k1} {z} = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15] ; X64-NEXT: retq @@ -914,13 +1436,13 @@ define <16 x float> @test_mm512_maskz_unpackhi_ps(i16 %a0, <16 x float> %a1, <16 define <8 x i64> @test_mm512_unpacklo_epi32(<8 x i64> %a0, <8 x i64> %a1) { ; X32-LABEL: test_mm512_unpacklo_epi32: -; X32: # BB#0: -; X32-NEXT: vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13] +; X32: # %bb.0: +; X32-NEXT: vunpcklps {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_unpacklo_epi32: -; X64: # BB#0: -; X64-NEXT: vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13] +; X64: # %bb.0: +; X64-NEXT: vunpcklps {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13] ; X64-NEXT: retq %arg0 = bitcast <8 x i64> %a0 to <16 x i32> %arg1 = bitcast <8 x i64> %a1 to <16 x i32> @@ -931,14 +1453,13 @@ define <8 x i64> @test_mm512_unpacklo_epi32(<8 x i64> %a0, <8 x i64> %a1) { define <8 x i64> @test_mm512_mask_unpacklo_epi32(<8 x i64> %a0, i16 %a1, <8 x i64> %a2, <8 x i64> %a3) { ; X32-LABEL: test_mm512_mask_unpacklo_epi32: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vpunpckldq {{.*#+}} zmm0 {%k1} = zmm1[0],zmm2[0],zmm1[1],zmm2[1],zmm1[4],zmm2[4],zmm1[5],zmm2[5],zmm1[8],zmm2[8],zmm1[9],zmm2[9],zmm1[12],zmm2[12],zmm1[13],zmm2[13] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_unpacklo_epi32: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpunpckldq {{.*#+}} zmm0 {%k1} = zmm1[0],zmm2[0],zmm1[1],zmm2[1],zmm1[4],zmm2[4],zmm1[5],zmm2[5],zmm1[8],zmm2[8],zmm1[9],zmm2[9],zmm1[12],zmm2[12],zmm1[13],zmm2[13] ; X64-NEXT: retq @@ -954,14 +1475,13 @@ define <8 x i64> @test_mm512_mask_unpacklo_epi32(<8 x i64> %a0, i16 %a1, <8 x i6 define <8 x i64> @test_mm512_maskz_unpacklo_epi32(i16 %a0, <8 x i64> %a1, <8 x i64> %a2) { ; X32-LABEL: test_mm512_maskz_unpacklo_epi32: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vpunpckldq {{.*#+}} zmm0 {%k1} {z} = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_unpacklo_epi32: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpunpckldq {{.*#+}} zmm0 {%k1} {z} = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13] ; X64-NEXT: retq @@ -976,13 +1496,13 @@ define <8 x i64> @test_mm512_maskz_unpacklo_epi32(i16 %a0, <8 x i64> %a1, <8 x i define <8 x i64> @test_mm512_unpacklo_epi64(<8 x i64> %a0, <8 x i64> %a1) { ; X32-LABEL: test_mm512_unpacklo_epi64: -; X32: # BB#0: -; X32-NEXT: vpunpcklqdq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] +; X32: # %bb.0: +; X32-NEXT: vunpcklpd {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_unpacklo_epi64: -; X64: # BB#0: -; X64-NEXT: vpunpcklqdq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] +; X64: # %bb.0: +; X64-NEXT: vunpcklpd {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X64-NEXT: retq %res = shufflevector <8 x i64> %a0, <8 x i64> %a1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14> ret <8 x i64> %res @@ -990,14 +1510,14 @@ define <8 x i64> @test_mm512_unpacklo_epi64(<8 x i64> %a0, <8 x i64> %a1) { define <8 x i64> @test_mm512_mask_unpacklo_epi64(<8 x i64> %a0, i8 %a1, <8 x i64> %a2, <8 x i64> %a3) { ; X32-LABEL: test_mm512_mask_unpacklo_epi64: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpunpcklqdq {{.*#+}} zmm0 = zmm1[0],zmm2[0],zmm1[2],zmm2[2],zmm1[4],zmm2[4],zmm1[6],zmm2[6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_unpacklo_epi64: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpunpcklqdq {{.*#+}} zmm0 = zmm1[0],zmm2[0],zmm1[2],zmm2[2],zmm1[4],zmm2[4],zmm1[6],zmm2[6] ; X64-NEXT: retq @@ -1009,14 +1529,14 @@ define <8 x i64> @test_mm512_mask_unpacklo_epi64(<8 x i64> %a0, i8 %a1, <8 x i64 define <8 x i64> @test_mm512_maskz_unpacklo_epi64(i8 %a0, <8 x i64> %a1, <8 x i64> %a2) { ; X32-LABEL: test_mm512_maskz_unpacklo_epi64: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vpunpcklqdq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_unpacklo_epi64: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vpunpcklqdq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X64-NEXT: retq @@ -1028,12 +1548,12 @@ define <8 x i64> @test_mm512_maskz_unpacklo_epi64(i8 %a0, <8 x i64> %a1, <8 x i6 define <8 x double> @test_mm512_unpacklo_pd(<8 x double> %a0, <8 x double> %a1) { ; X32-LABEL: test_mm512_unpacklo_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vunpcklpd {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_unpacklo_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vunpcklpd {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X64-NEXT: retq %res = shufflevector <8 x double> %a0, <8 x double> %a1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14> @@ -1042,14 +1562,14 @@ define <8 x double> @test_mm512_unpacklo_pd(<8 x double> %a0, <8 x double> %a1) define <8 x double> @test_mm512_mask_unpacklo_pd(<8 x double> %a0, i8 %a1, <8 x double> %a2, <8 x double> %a3) { ; X32-LABEL: test_mm512_mask_unpacklo_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vunpcklpd {{.*#+}} zmm0 {%k1} = zmm1[0],zmm2[0],zmm1[2],zmm2[2],zmm1[4],zmm2[4],zmm1[6],zmm2[6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_unpacklo_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vunpcklpd {{.*#+}} zmm0 {%k1} = zmm1[0],zmm2[0],zmm1[2],zmm2[2],zmm1[4],zmm2[4],zmm1[6],zmm2[6] ; X64-NEXT: retq @@ -1061,14 +1581,14 @@ define <8 x double> @test_mm512_mask_unpacklo_pd(<8 x double> %a0, i8 %a1, <8 x define <8 x double> @test_mm512_maskz_unpacklo_pd(i8 %a0, <8 x double> %a1, <8 x double> %a2) { ; X32-LABEL: test_mm512_maskz_unpacklo_pd: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: movb {{[0-9]+}}(%esp), %al ; X32-NEXT: kmovw %eax, %k1 ; X32-NEXT: vunpcklpd {{.*#+}} zmm0 {%k1} {z} = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_unpacklo_pd: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vunpcklpd {{.*#+}} zmm0 {%k1} {z} = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6] ; X64-NEXT: retq @@ -1080,12 +1600,12 @@ define <8 x double> @test_mm512_maskz_unpacklo_pd(i8 %a0, <8 x double> %a1, <8 x define <16 x float> @test_mm512_unpacklo_ps(<16 x float> %a0, <16 x float> %a1) { ; X32-LABEL: test_mm512_unpacklo_ps: -; X32: # BB#0: +; X32: # %bb.0: ; X32-NEXT: vunpcklps {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_unpacklo_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: vunpcklps {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13] ; X64-NEXT: retq %res = shufflevector <16 x float> %a0, <16 x float> %a1, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 4, i32 20, i32 5, i32 21, i32 8, i32 24, i32 9, i32 25, i32 12, i32 28, i32 13, i32 29> @@ -1094,14 +1614,13 @@ define <16 x float> @test_mm512_unpacklo_ps(<16 x float> %a0, <16 x float> %a1) define <16 x float> @test_mm512_mask_unpacklo_ps(<16 x float> %a0, i16 %a1, <16 x float> %a2, <16 x float> %a3) { ; X32-LABEL: test_mm512_mask_unpacklo_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vunpcklps {{.*#+}} zmm0 {%k1} = zmm1[0],zmm2[0],zmm1[1],zmm2[1],zmm1[4],zmm2[4],zmm1[5],zmm2[5],zmm1[8],zmm2[8],zmm1[9],zmm2[9],zmm1[12],zmm2[12],zmm1[13],zmm2[13] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_mask_unpacklo_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vunpcklps {{.*#+}} zmm0 {%k1} = zmm1[0],zmm2[0],zmm1[1],zmm2[1],zmm1[4],zmm2[4],zmm1[5],zmm2[5],zmm1[8],zmm2[8],zmm1[9],zmm2[9],zmm1[12],zmm2[12],zmm1[13],zmm2[13] ; X64-NEXT: retq @@ -1113,14 +1632,13 @@ define <16 x float> @test_mm512_mask_unpacklo_ps(<16 x float> %a0, i16 %a1, <16 define <16 x float> @test_mm512_maskz_unpacklo_ps(i16 %a0, <16 x float> %a1, <16 x float> %a2) { ; X32-LABEL: test_mm512_maskz_unpacklo_ps: -; X32: # BB#0: -; X32-NEXT: movw {{[0-9]+}}(%esp), %ax -; X32-NEXT: kmovw %eax, %k1 +; X32: # %bb.0: +; X32-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ; X32-NEXT: vunpcklps {{.*#+}} zmm0 {%k1} {z} = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13] ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_maskz_unpacklo_ps: -; X64: # BB#0: +; X64: # %bb.0: ; X64-NEXT: kmovw %edi, %k1 ; X64-NEXT: vunpcklps {{.*#+}} zmm0 {%k1} {z} = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13] ; X64-NEXT: retq @@ -1132,21 +1650,13 @@ define <16 x float> @test_mm512_maskz_unpacklo_ps(i16 %a0, <16 x float> %a1, <16 define <8 x double> @test_mm512_zextpd128_pd512(<2 x double> %a0) nounwind { ; X32-LABEL: test_mm512_zextpd128_pd512: -; X32: # BB#0: -; X32-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<def> -; X32-NEXT: vxorpd %xmm1, %xmm1, %xmm1 -; X32-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm2 -; X32-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 -; X32-NEXT: vinsertf64x4 $1, %ymm2, %zmm0, %zmm0 +; X32: # %bb.0: +; X32-NEXT: vmovaps %xmm0, %xmm0 ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_zextpd128_pd512: -; X64: # BB#0: -; X64-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<def> -; X64-NEXT: vxorpd %xmm1, %xmm1, %xmm1 -; X64-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm2 -; X64-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 -; X64-NEXT: vinsertf64x4 $1, %ymm2, %zmm0, %zmm0 +; X64: # %bb.0: +; X64-NEXT: vmovaps %xmm0, %xmm0 ; X64-NEXT: retq %res = shufflevector <2 x double> %a0, <2 x double> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 2, i32 3, i32 2, i32 3> ret <8 x double> %res @@ -1154,17 +1664,13 @@ define <8 x double> @test_mm512_zextpd128_pd512(<2 x double> %a0) nounwind { define <8 x double> @test_mm512_zextpd256_pd512(<4 x double> %a0) nounwind { ; X32-LABEL: test_mm512_zextpd256_pd512: -; X32: # BB#0: -; X32-NEXT: # kill: %YMM0<def> %YMM0<kill> %ZMM0<def> -; X32-NEXT: vxorpd %ymm1, %ymm1, %ymm1 -; X32-NEXT: vinsertf64x4 $1, %ymm1, %zmm0, %zmm0 +; X32: # %bb.0: +; X32-NEXT: vmovaps %ymm0, %ymm0 ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_zextpd256_pd512: -; X64: # BB#0: -; X64-NEXT: # kill: %YMM0<def> %YMM0<kill> %ZMM0<def> -; X64-NEXT: vxorpd %ymm1, %ymm1, %ymm1 -; X64-NEXT: vinsertf64x4 $1, %ymm1, %zmm0, %zmm0 +; X64: # %bb.0: +; X64-NEXT: vmovaps %ymm0, %ymm0 ; X64-NEXT: retq %res = shufflevector <4 x double> %a0, <4 x double> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> ret <8 x double> %res @@ -1172,21 +1678,17 @@ define <8 x double> @test_mm512_zextpd256_pd512(<4 x double> %a0) nounwind { define <16 x float> @test_mm512_zextps128_ps512(<4 x float> %a0) nounwind { ; X32-LABEL: test_mm512_zextps128_ps512: -; X32: # BB#0: -; X32-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<def> -; X32-NEXT: vxorpd %xmm1, %xmm1, %xmm1 -; X32-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm2 -; X32-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 -; X32-NEXT: vinsertf64x4 $1, %ymm2, %zmm0, %zmm0 +; X32: # %bb.0: +; X32-NEXT: vmovaps %xmm0, %xmm0 +; X32-NEXT: vxorps %xmm1, %xmm1, %xmm1 +; X32-NEXT: vinsertf64x4 $1, %ymm1, %zmm0, %zmm0 ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_zextps128_ps512: -; X64: # BB#0: -; X64-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<def> -; X64-NEXT: vxorpd %xmm1, %xmm1, %xmm1 -; X64-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm2 -; X64-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 -; X64-NEXT: vinsertf64x4 $1, %ymm2, %zmm0, %zmm0 +; X64: # %bb.0: +; X64-NEXT: vmovaps %xmm0, %xmm0 +; X64-NEXT: vxorps %xmm1, %xmm1, %xmm1 +; X64-NEXT: vinsertf64x4 $1, %ymm1, %zmm0, %zmm0 ; X64-NEXT: retq %res = shufflevector <4 x float> %a0, <4 x float> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7> ret <16 x float> %res @@ -1194,17 +1696,13 @@ define <16 x float> @test_mm512_zextps128_ps512(<4 x float> %a0) nounwind { define <16 x float> @test_mm512_zextps256_ps512(<8 x float> %a0) nounwind { ; X32-LABEL: test_mm512_zextps256_ps512: -; X32: # BB#0: -; X32-NEXT: # kill: %YMM0<def> %YMM0<kill> %ZMM0<def> -; X32-NEXT: vxorpd %ymm1, %ymm1, %ymm1 -; X32-NEXT: vinsertf64x4 $1, %ymm1, %zmm0, %zmm0 +; X32: # %bb.0: +; X32-NEXT: vmovaps %ymm0, %ymm0 ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_zextps256_ps512: -; X64: # BB#0: -; X64-NEXT: # kill: %YMM0<def> %YMM0<kill> %ZMM0<def> -; X64-NEXT: vxorpd %ymm1, %ymm1, %ymm1 -; X64-NEXT: vinsertf64x4 $1, %ymm1, %zmm0, %zmm0 +; X64: # %bb.0: +; X64-NEXT: vmovaps %ymm0, %ymm0 ; X64-NEXT: retq %res = shufflevector <8 x float> %a0, <8 x float> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15> ret <16 x float> %res @@ -1212,21 +1710,13 @@ define <16 x float> @test_mm512_zextps256_ps512(<8 x float> %a0) nounwind { define <8 x i64> @test_mm512_zextsi128_si512(<2 x i64> %a0) nounwind { ; X32-LABEL: test_mm512_zextsi128_si512: -; X32: # BB#0: -; X32-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<def> -; X32-NEXT: vpxor %xmm1, %xmm1, %xmm1 -; X32-NEXT: vinserti128 $1, %xmm1, %ymm1, %ymm2 -; X32-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 -; X32-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0 +; X32: # %bb.0: +; X32-NEXT: vmovaps %xmm0, %xmm0 ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_zextsi128_si512: -; X64: # BB#0: -; X64-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<def> -; X64-NEXT: vpxor %xmm1, %xmm1, %xmm1 -; X64-NEXT: vinserti128 $1, %xmm1, %ymm1, %ymm2 -; X64-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 -; X64-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0 +; X64: # %bb.0: +; X64-NEXT: vmovaps %xmm0, %xmm0 ; X64-NEXT: retq %res = shufflevector <2 x i64> %a0, <2 x i64> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 2, i32 3, i32 2, i32 3> ret <8 x i64> %res @@ -1234,17 +1724,13 @@ define <8 x i64> @test_mm512_zextsi128_si512(<2 x i64> %a0) nounwind { define <8 x i64> @test_mm512_zextsi256_si512(<4 x i64> %a0) nounwind { ; X32-LABEL: test_mm512_zextsi256_si512: -; X32: # BB#0: -; X32-NEXT: # kill: %YMM0<def> %YMM0<kill> %ZMM0<def> -; X32-NEXT: vpxor %ymm1, %ymm1, %ymm1 -; X32-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0 +; X32: # %bb.0: +; X32-NEXT: vmovaps %ymm0, %ymm0 ; X32-NEXT: retl ; ; X64-LABEL: test_mm512_zextsi256_si512: -; X64: # BB#0: -; X64-NEXT: # kill: %YMM0<def> %YMM0<kill> %ZMM0<def> -; X64-NEXT: vpxor %ymm1, %ymm1, %ymm1 -; X64-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0 +; X64: # %bb.0: +; X64-NEXT: vmovaps %ymm0, %ymm0 ; X64-NEXT: retq %res = shufflevector <4 x i64> %a0, <4 x i64> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> ret <8 x i64> %res |