diff options
Diffstat (limited to 'llvm/test/CodeGen/X86/unaligned-32-byte-memops.ll')
-rw-r--r-- | llvm/test/CodeGen/X86/unaligned-32-byte-memops.ll | 60 |
1 files changed, 30 insertions, 30 deletions
diff --git a/llvm/test/CodeGen/X86/unaligned-32-byte-memops.ll b/llvm/test/CodeGen/X86/unaligned-32-byte-memops.ll index 391f7a38a37..c7825400910 100644 --- a/llvm/test/CodeGen/X86/unaligned-32-byte-memops.ll +++ b/llvm/test/CodeGen/X86/unaligned-32-byte-memops.ll @@ -7,18 +7,18 @@ define <8 x float> @load32bytes(<8 x float>* %Ap) { ; AVXSLOW-LABEL: load32bytes: -; AVXSLOW: # BB#0: +; AVXSLOW: # %bb.0: ; AVXSLOW-NEXT: vmovaps (%rdi), %xmm0 ; AVXSLOW-NEXT: vinsertf128 $1, 16(%rdi), %ymm0, %ymm0 ; AVXSLOW-NEXT: retq ; ; AVXFAST-LABEL: load32bytes: -; AVXFAST: # BB#0: +; AVXFAST: # %bb.0: ; AVXFAST-NEXT: vmovups (%rdi), %ymm0 ; AVXFAST-NEXT: retq ; ; AVX2-LABEL: load32bytes: -; AVX2: # BB#0: +; AVX2: # %bb.0: ; AVX2-NEXT: vmovups (%rdi), %ymm0 ; AVX2-NEXT: retq %A = load <8 x float>, <8 x float>* %Ap, align 16 @@ -29,20 +29,20 @@ define <8 x float> @load32bytes(<8 x float>* %Ap) { define void @store32bytes(<8 x float> %A, <8 x float>* %P) { ; AVXSLOW-LABEL: store32bytes: -; AVXSLOW: # BB#0: +; AVXSLOW: # %bb.0: ; AVXSLOW-NEXT: vextractf128 $1, %ymm0, 16(%rdi) ; AVXSLOW-NEXT: vmovaps %xmm0, (%rdi) ; AVXSLOW-NEXT: vzeroupper ; AVXSLOW-NEXT: retq ; ; AVXFAST-LABEL: store32bytes: -; AVXFAST: # BB#0: +; AVXFAST: # %bb.0: ; AVXFAST-NEXT: vmovups %ymm0, (%rdi) ; AVXFAST-NEXT: vzeroupper ; AVXFAST-NEXT: retq ; ; AVX2-LABEL: store32bytes: -; AVX2: # BB#0: +; AVX2: # %bb.0: ; AVX2-NEXT: vmovups %ymm0, (%rdi) ; AVX2-NEXT: vzeroupper ; AVX2-NEXT: retq @@ -54,18 +54,18 @@ define void @store32bytes(<8 x float> %A, <8 x float>* %P) { define <8 x float> @combine_16_byte_loads_no_intrinsic(<4 x float>* %ptr) { ; AVXSLOW-LABEL: combine_16_byte_loads_no_intrinsic: -; AVXSLOW: # BB#0: +; AVXSLOW: # %bb.0: ; AVXSLOW-NEXT: vmovups 48(%rdi), %xmm0 ; AVXSLOW-NEXT: vinsertf128 $1, 64(%rdi), %ymm0, %ymm0 ; AVXSLOW-NEXT: retq ; ; AVXFAST-LABEL: combine_16_byte_loads_no_intrinsic: -; AVXFAST: # BB#0: +; AVXFAST: # %bb.0: ; AVXFAST-NEXT: vmovups 48(%rdi), %ymm0 ; AVXFAST-NEXT: retq ; ; AVX2-LABEL: combine_16_byte_loads_no_intrinsic: -; AVX2: # BB#0: +; AVX2: # %bb.0: ; AVX2-NEXT: vmovups 48(%rdi), %ymm0 ; AVX2-NEXT: retq %ptr1 = getelementptr inbounds <4 x float>, <4 x float>* %ptr, i64 3 @@ -80,17 +80,17 @@ define <8 x float> @combine_16_byte_loads_no_intrinsic(<4 x float>* %ptr) { define <8 x float> @combine_16_byte_loads_aligned(<4 x float>* %ptr) { ; AVXSLOW-LABEL: combine_16_byte_loads_aligned: -; AVXSLOW: # BB#0: +; AVXSLOW: # %bb.0: ; AVXSLOW-NEXT: vmovaps 48(%rdi), %ymm0 ; AVXSLOW-NEXT: retq ; ; AVXFAST-LABEL: combine_16_byte_loads_aligned: -; AVXFAST: # BB#0: +; AVXFAST: # %bb.0: ; AVXFAST-NEXT: vmovaps 48(%rdi), %ymm0 ; AVXFAST-NEXT: retq ; ; AVX2-LABEL: combine_16_byte_loads_aligned: -; AVX2: # BB#0: +; AVX2: # %bb.0: ; AVX2-NEXT: vmovaps 48(%rdi), %ymm0 ; AVX2-NEXT: retq %ptr1 = getelementptr inbounds <4 x float>, <4 x float>* %ptr, i64 3 @@ -105,18 +105,18 @@ define <8 x float> @combine_16_byte_loads_aligned(<4 x float>* %ptr) { define <8 x float> @combine_16_byte_loads_no_intrinsic_swap(<4 x float>* %ptr) { ; AVXSLOW-LABEL: combine_16_byte_loads_no_intrinsic_swap: -; AVXSLOW: # BB#0: +; AVXSLOW: # %bb.0: ; AVXSLOW-NEXT: vmovups 64(%rdi), %xmm0 ; AVXSLOW-NEXT: vinsertf128 $1, 80(%rdi), %ymm0, %ymm0 ; AVXSLOW-NEXT: retq ; ; AVXFAST-LABEL: combine_16_byte_loads_no_intrinsic_swap: -; AVXFAST: # BB#0: +; AVXFAST: # %bb.0: ; AVXFAST-NEXT: vmovups 64(%rdi), %ymm0 ; AVXFAST-NEXT: retq ; ; AVX2-LABEL: combine_16_byte_loads_no_intrinsic_swap: -; AVX2: # BB#0: +; AVX2: # %bb.0: ; AVX2-NEXT: vmovups 64(%rdi), %ymm0 ; AVX2-NEXT: retq %ptr1 = getelementptr inbounds <4 x float>, <4 x float>* %ptr, i64 4 @@ -133,7 +133,7 @@ define <8 x float> @combine_16_byte_loads_no_intrinsic_swap(<4 x float>* %ptr) { define <4 x i64> @combine_16_byte_loads_i64(<2 x i64>* %ptr, <4 x i64> %x) { ; AVXSLOW-LABEL: combine_16_byte_loads_i64: -; AVXSLOW: # BB#0: +; AVXSLOW: # %bb.0: ; AVXSLOW-NEXT: vextractf128 $1, %ymm0, %xmm1 ; AVXSLOW-NEXT: vpaddq 96(%rdi), %xmm1, %xmm1 ; AVXSLOW-NEXT: vpaddq 80(%rdi), %xmm0, %xmm0 @@ -141,7 +141,7 @@ define <4 x i64> @combine_16_byte_loads_i64(<2 x i64>* %ptr, <4 x i64> %x) { ; AVXSLOW-NEXT: retq ; ; AVXFAST-LABEL: combine_16_byte_loads_i64: -; AVXFAST: # BB#0: +; AVXFAST: # %bb.0: ; AVXFAST-NEXT: vextractf128 $1, %ymm0, %xmm1 ; AVXFAST-NEXT: vpaddq 96(%rdi), %xmm1, %xmm1 ; AVXFAST-NEXT: vpaddq 80(%rdi), %xmm0, %xmm0 @@ -149,7 +149,7 @@ define <4 x i64> @combine_16_byte_loads_i64(<2 x i64>* %ptr, <4 x i64> %x) { ; AVXFAST-NEXT: retq ; ; AVX2-LABEL: combine_16_byte_loads_i64: -; AVX2: # BB#0: +; AVX2: # %bb.0: ; AVX2-NEXT: vpaddq 80(%rdi), %ymm0, %ymm0 ; AVX2-NEXT: retq %ptr1 = getelementptr inbounds <2 x i64>, <2 x i64>* %ptr, i64 5 @@ -163,7 +163,7 @@ define <4 x i64> @combine_16_byte_loads_i64(<2 x i64>* %ptr, <4 x i64> %x) { define <8 x i32> @combine_16_byte_loads_i32(<4 x i32>* %ptr, <8 x i32> %x) { ; AVXSLOW-LABEL: combine_16_byte_loads_i32: -; AVXSLOW: # BB#0: +; AVXSLOW: # %bb.0: ; AVXSLOW-NEXT: vextractf128 $1, %ymm0, %xmm1 ; AVXSLOW-NEXT: vpaddd 112(%rdi), %xmm1, %xmm1 ; AVXSLOW-NEXT: vpaddd 96(%rdi), %xmm0, %xmm0 @@ -171,7 +171,7 @@ define <8 x i32> @combine_16_byte_loads_i32(<4 x i32>* %ptr, <8 x i32> %x) { ; AVXSLOW-NEXT: retq ; ; AVXFAST-LABEL: combine_16_byte_loads_i32: -; AVXFAST: # BB#0: +; AVXFAST: # %bb.0: ; AVXFAST-NEXT: vextractf128 $1, %ymm0, %xmm1 ; AVXFAST-NEXT: vpaddd 112(%rdi), %xmm1, %xmm1 ; AVXFAST-NEXT: vpaddd 96(%rdi), %xmm0, %xmm0 @@ -179,7 +179,7 @@ define <8 x i32> @combine_16_byte_loads_i32(<4 x i32>* %ptr, <8 x i32> %x) { ; AVXFAST-NEXT: retq ; ; AVX2-LABEL: combine_16_byte_loads_i32: -; AVX2: # BB#0: +; AVX2: # %bb.0: ; AVX2-NEXT: vpaddd 96(%rdi), %ymm0, %ymm0 ; AVX2-NEXT: retq %ptr1 = getelementptr inbounds <4 x i32>, <4 x i32>* %ptr, i64 6 @@ -193,7 +193,7 @@ define <8 x i32> @combine_16_byte_loads_i32(<4 x i32>* %ptr, <8 x i32> %x) { define <16 x i16> @combine_16_byte_loads_i16(<8 x i16>* %ptr, <16 x i16> %x) { ; AVXSLOW-LABEL: combine_16_byte_loads_i16: -; AVXSLOW: # BB#0: +; AVXSLOW: # %bb.0: ; AVXSLOW-NEXT: vextractf128 $1, %ymm0, %xmm1 ; AVXSLOW-NEXT: vpaddw 128(%rdi), %xmm1, %xmm1 ; AVXSLOW-NEXT: vpaddw 112(%rdi), %xmm0, %xmm0 @@ -201,7 +201,7 @@ define <16 x i16> @combine_16_byte_loads_i16(<8 x i16>* %ptr, <16 x i16> %x) { ; AVXSLOW-NEXT: retq ; ; AVXFAST-LABEL: combine_16_byte_loads_i16: -; AVXFAST: # BB#0: +; AVXFAST: # %bb.0: ; AVXFAST-NEXT: vextractf128 $1, %ymm0, %xmm1 ; AVXFAST-NEXT: vpaddw 128(%rdi), %xmm1, %xmm1 ; AVXFAST-NEXT: vpaddw 112(%rdi), %xmm0, %xmm0 @@ -209,7 +209,7 @@ define <16 x i16> @combine_16_byte_loads_i16(<8 x i16>* %ptr, <16 x i16> %x) { ; AVXFAST-NEXT: retq ; ; AVX2-LABEL: combine_16_byte_loads_i16: -; AVX2: # BB#0: +; AVX2: # %bb.0: ; AVX2-NEXT: vpaddw 112(%rdi), %ymm0, %ymm0 ; AVX2-NEXT: retq %ptr1 = getelementptr inbounds <8 x i16>, <8 x i16>* %ptr, i64 7 @@ -223,7 +223,7 @@ define <16 x i16> @combine_16_byte_loads_i16(<8 x i16>* %ptr, <16 x i16> %x) { define <32 x i8> @combine_16_byte_loads_i8(<16 x i8>* %ptr, <32 x i8> %x) { ; AVXSLOW-LABEL: combine_16_byte_loads_i8: -; AVXSLOW: # BB#0: +; AVXSLOW: # %bb.0: ; AVXSLOW-NEXT: vextractf128 $1, %ymm0, %xmm1 ; AVXSLOW-NEXT: vpaddb 144(%rdi), %xmm1, %xmm1 ; AVXSLOW-NEXT: vpaddb 128(%rdi), %xmm0, %xmm0 @@ -231,7 +231,7 @@ define <32 x i8> @combine_16_byte_loads_i8(<16 x i8>* %ptr, <32 x i8> %x) { ; AVXSLOW-NEXT: retq ; ; AVXFAST-LABEL: combine_16_byte_loads_i8: -; AVXFAST: # BB#0: +; AVXFAST: # %bb.0: ; AVXFAST-NEXT: vextractf128 $1, %ymm0, %xmm1 ; AVXFAST-NEXT: vpaddb 144(%rdi), %xmm1, %xmm1 ; AVXFAST-NEXT: vpaddb 128(%rdi), %xmm0, %xmm0 @@ -239,7 +239,7 @@ define <32 x i8> @combine_16_byte_loads_i8(<16 x i8>* %ptr, <32 x i8> %x) { ; AVXFAST-NEXT: retq ; ; AVX2-LABEL: combine_16_byte_loads_i8: -; AVX2: # BB#0: +; AVX2: # %bb.0: ; AVX2-NEXT: vpaddb 128(%rdi), %ymm0, %ymm0 ; AVX2-NEXT: retq %ptr1 = getelementptr inbounds <16 x i8>, <16 x i8>* %ptr, i64 8 @@ -253,19 +253,19 @@ define <32 x i8> @combine_16_byte_loads_i8(<16 x i8>* %ptr, <32 x i8> %x) { define <4 x double> @combine_16_byte_loads_double(<2 x double>* %ptr, <4 x double> %x) { ; AVXSLOW-LABEL: combine_16_byte_loads_double: -; AVXSLOW: # BB#0: +; AVXSLOW: # %bb.0: ; AVXSLOW-NEXT: vmovups 144(%rdi), %xmm1 ; AVXSLOW-NEXT: vinsertf128 $1, 160(%rdi), %ymm1, %ymm1 ; AVXSLOW-NEXT: vaddpd %ymm0, %ymm1, %ymm0 ; AVXSLOW-NEXT: retq ; ; AVXFAST-LABEL: combine_16_byte_loads_double: -; AVXFAST: # BB#0: +; AVXFAST: # %bb.0: ; AVXFAST-NEXT: vaddpd 144(%rdi), %ymm0, %ymm0 ; AVXFAST-NEXT: retq ; ; AVX2-LABEL: combine_16_byte_loads_double: -; AVX2: # BB#0: +; AVX2: # %bb.0: ; AVX2-NEXT: vaddpd 144(%rdi), %ymm0, %ymm0 ; AVX2-NEXT: retq %ptr1 = getelementptr inbounds <2 x double>, <2 x double>* %ptr, i64 9 |