From: Simon Pilgrim Date: Wed, 25 Nov 2015 09:06:17 +0000 (+0000) Subject: [X86][AVX] Regenerate Splat OptSize tests X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=9c3a9de18eb40e1f6c9b0339f0f9c6949a257f32;p=oota-llvm.git [X86][AVX] Regenerate Splat OptSize tests Tidied up triple and regenerate tests using update_llc_test_checks.py git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@254060 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/test/CodeGen/X86/splat-for-size.ll b/test/CodeGen/X86/splat-for-size.ll index 6469786d879..277472f49b3 100644 --- a/test/CodeGen/X86/splat-for-size.ll +++ b/test/CodeGen/X86/splat-for-size.ll @@ -1,141 +1,191 @@ -; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=avx < %s | FileCheck %s -check-prefix=CHECK --check-prefix=AVX -; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=avx2 < %s | FileCheck %s -check-prefix=CHECK --check-prefix=AVX2 +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=CHECK --check-prefix=AVX +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=CHECK --check-prefix=AVX2 -; Check constant loads of every 128-bit and 256-bit vector type +; Check constant loads of every 128-bit and 256-bit vector type ; for size optimization using splat ops available with AVX and AVX2. ; There is no AVX broadcast from double to 128-bit vector because movddup has been around since SSE3 (grrr). define <2 x double> @splat_v2f64(<2 x double> %x) #0 { +; CHECK-LABEL: splat_v2f64: +; CHECK: # BB#0: +; CHECK-NEXT: vmovddup {{.*#+}} xmm1 = mem[0,0] +; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0 +; CHECK-NEXT: retq %add = fadd <2 x double> %x, ret <2 x double> %add -; CHECK-LABEL: splat_v2f64 -; CHECK: vmovddup -; CHECK: vaddpd -; CHECK-NEXT: retq } define <4 x double> @splat_v4f64(<4 x double> %x) #1 { +; CHECK-LABEL: splat_v4f64: +; CHECK: # BB#0: +; CHECK-NEXT: vbroadcastsd {{.*}}(%rip), %ymm1 +; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0 +; CHECK-NEXT: retq %add = fadd <4 x double> %x, ret <4 x double> %add -; CHECK-LABEL: splat_v4f64 -; CHECK: vbroadcastsd -; CHECK-NEXT: vaddpd -; CHECK-NEXT: retq } define <4 x float> @splat_v4f32(<4 x float> %x) #0 { +; CHECK-LABEL: splat_v4f32: +; CHECK: # BB#0: +; CHECK-NEXT: vbroadcastss {{.*}}(%rip), %xmm1 +; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0 +; CHECK-NEXT: retq %add = fadd <4 x float> %x, ret <4 x float> %add -; CHECK-LABEL: splat_v4f32 -; CHECK: vbroadcastss -; CHECK-NEXT: vaddps -; CHECK-NEXT: retq } define <8 x float> @splat_v8f32(<8 x float> %x) #1 { +; CHECK-LABEL: splat_v8f32: +; CHECK: # BB#0: +; CHECK-NEXT: vbroadcastss {{.*}}(%rip), %ymm1 +; CHECK-NEXT: vaddps %ymm1, %ymm0, %ymm0 +; CHECK-NEXT: retq %add = fadd <8 x float> %x, ret <8 x float> %add -; CHECK-LABEL: splat_v8f32 -; CHECK: vbroadcastss -; CHECK-NEXT: vaddps -; CHECK-NEXT: retq } ; AVX can't do integer splats, so fake it: use vmovddup to splat 64-bit value. ; We also generate vmovddup for AVX2 because it's one byte smaller than vpbroadcastq. define <2 x i64> @splat_v2i64(<2 x i64> %x) #1 { +; CHECK-LABEL: splat_v2i64: +; CHECK: # BB#0: +; CHECK-NEXT: vmovddup {{.*#+}} xmm1 = mem[0,0] +; CHECK-NEXT: vpaddq %xmm1, %xmm0, %xmm0 +; CHECK-NEXT: retq %add = add <2 x i64> %x, ret <2 x i64> %add -; CHECK-LABEL: splat_v2i64 -; CHECK: vmovddup -; CHECK: vpaddq -; CHECK-NEXT: retq } ; AVX can't do 256-bit integer ops, so we split this into two 128-bit vectors, ; and then we fake it: use vmovddup to splat 64-bit value. define <4 x i64> @splat_v4i64(<4 x i64> %x) #0 { +; AVX-LABEL: splat_v4i64: +; AVX: # BB#0: +; AVX-NEXT: vextractf128 $1, %ymm0, %xmm1 +; AVX-NEXT: vmovddup {{.*#+}} xmm2 = mem[0,0] +; AVX-NEXT: vpaddq %xmm2, %xmm1, %xmm1 +; AVX-NEXT: vpaddq %xmm2, %xmm0, %xmm0 +; AVX-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 +; AVX-NEXT: retq +; +; AVX2-LABEL: splat_v4i64: +; AVX2: # BB#0: +; AVX2-NEXT: vpbroadcastq {{.*}}(%rip), %ymm1 +; AVX2-NEXT: vpaddq %ymm1, %ymm0, %ymm0 +; AVX2-NEXT: retq %add = add <4 x i64> %x, ret <4 x i64> %add -; CHECK-LABEL: splat_v4i64 -; AVX: vmovddup -; AVX: vpaddq -; AVX: vpaddq -; AVX2: vpbroadcastq -; AVX2: vpaddq -; CHECK: retq } ; AVX can't do integer splats, so fake it: use vbroadcastss to splat 32-bit value. define <4 x i32> @splat_v4i32(<4 x i32> %x) #1 { +; AVX-LABEL: splat_v4i32: +; AVX: # BB#0: +; AVX-NEXT: vbroadcastss {{.*}}(%rip), %xmm1 +; AVX-NEXT: vpaddd %xmm1, %xmm0, %xmm0 +; AVX-NEXT: retq +; +; AVX2-LABEL: splat_v4i32: +; AVX2: # BB#0: +; AVX2-NEXT: vpbroadcastd {{.*}}(%rip), %xmm1 +; AVX2-NEXT: vpaddd %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: retq %add = add <4 x i32> %x, ret <4 x i32> %add -; CHECK-LABEL: splat_v4i32 -; AVX: vbroadcastss -; AVX2: vpbroadcastd -; CHECK-NEXT: vpaddd -; CHECK-NEXT: retq } ; AVX can't do integer splats, so fake it: use vbroadcastss to splat 32-bit value. define <8 x i32> @splat_v8i32(<8 x i32> %x) #0 { +; AVX-LABEL: splat_v8i32: +; AVX: # BB#0: +; AVX-NEXT: vextractf128 $1, %ymm0, %xmm1 +; AVX-NEXT: vbroadcastss {{.*}}(%rip), %xmm2 +; AVX-NEXT: vpaddd %xmm2, %xmm1, %xmm1 +; AVX-NEXT: vpaddd %xmm2, %xmm0, %xmm0 +; AVX-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 +; AVX-NEXT: retq +; +; AVX2-LABEL: splat_v8i32: +; AVX2: # BB#0: +; AVX2-NEXT: vpbroadcastd {{.*}}(%rip), %ymm1 +; AVX2-NEXT: vpaddd %ymm1, %ymm0, %ymm0 +; AVX2-NEXT: retq %add = add <8 x i32> %x, ret <8 x i32> %add -; CHECK-LABEL: splat_v8i32 -; AVX: vbroadcastss -; AVX: vpaddd -; AVX: vpaddd -; AVX2: vpbroadcastd -; AVX2: vpaddd -; CHECK: retq } ; AVX can't do integer splats, and there's no broadcast fakery for 16-bit. Could use pshuflw, etc? define <8 x i16> @splat_v8i16(<8 x i16> %x) #1 { +; AVX-LABEL: splat_v8i16: +; AVX: # BB#0: +; AVX-NEXT: vpaddw {{.*}}(%rip), %xmm0, %xmm0 +; AVX-NEXT: retq +; +; AVX2-LABEL: splat_v8i16: +; AVX2: # BB#0: +; AVX2-NEXT: vpbroadcastw {{.*}}(%rip), %xmm1 +; AVX2-NEXT: vpaddw %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: retq %add = add <8 x i16> %x, ret <8 x i16> %add -; CHECK-LABEL: splat_v8i16 -; AVX-NOT: broadcast -; AVX2: vpbroadcastw -; CHECK: vpaddw -; CHECK-NEXT: retq } ; AVX can't do integer splats, and there's no broadcast fakery for 16-bit. Could use pshuflw, etc? define <16 x i16> @splat_v16i16(<16 x i16> %x) #0 { +; AVX-LABEL: splat_v16i16: +; AVX: # BB#0: +; AVX-NEXT: vextractf128 $1, %ymm0, %xmm1 +; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [1,1,1,1,1,1,1,1] +; AVX-NEXT: vpaddw %xmm2, %xmm1, %xmm1 +; AVX-NEXT: vpaddw %xmm2, %xmm0, %xmm0 +; AVX-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 +; AVX-NEXT: retq +; +; AVX2-LABEL: splat_v16i16: +; AVX2: # BB#0: +; AVX2-NEXT: vpbroadcastw {{.*}}(%rip), %ymm1 +; AVX2-NEXT: vpaddw %ymm1, %ymm0, %ymm0 +; AVX2-NEXT: retq %add = add <16 x i16> %x, ret <16 x i16> %add -; CHECK-LABEL: splat_v16i16 -; AVX-NOT: broadcast -; AVX: vpaddw -; AVX: vpaddw -; AVX2: vpbroadcastw -; AVX2: vpaddw -; CHECK: retq } ; AVX can't do integer splats, and there's no broadcast fakery for 8-bit. Could use pshufb, etc? define <16 x i8> @splat_v16i8(<16 x i8> %x) #1 { +; AVX-LABEL: splat_v16i8: +; AVX: # BB#0: +; AVX-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0 +; AVX-NEXT: retq +; +; AVX2-LABEL: splat_v16i8: +; AVX2: # BB#0: +; AVX2-NEXT: vpbroadcastb {{.*}}(%rip), %xmm1 +; AVX2-NEXT: vpaddb %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: retq %add = add <16 x i8> %x, ret <16 x i8> %add -; CHECK-LABEL: splat_v16i8 -; AVX-NOT: broadcast -; AVX2: vpbroadcastb -; CHECK: vpaddb -; CHECK-NEXT: retq } ; AVX can't do integer splats, and there's no broadcast fakery for 8-bit. Could use pshufb, etc? define <32 x i8> @splat_v32i8(<32 x i8> %x) #0 { +; AVX-LABEL: splat_v32i8: +; AVX: # BB#0: +; AVX-NEXT: vextractf128 $1, %ymm0, %xmm1 +; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] +; AVX-NEXT: vpaddb %xmm2, %xmm1, %xmm1 +; AVX-NEXT: vpaddb %xmm2, %xmm0, %xmm0 +; AVX-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 +; AVX-NEXT: retq +; +; AVX2-LABEL: splat_v32i8: +; AVX2: # BB#0: +; AVX2-NEXT: vpbroadcastb {{.*}}(%rip), %ymm1 +; AVX2-NEXT: vpaddb %ymm1, %ymm0, %ymm0 +; AVX2-NEXT: retq %add = add <32 x i8> %x, ret <32 x i8> %add -; CHECK-LABEL: splat_v32i8 -; AVX-NOT: broadcast -; AVX: vpaddb -; AVX: vpaddb -; AVX2: vpbroadcastb -; AVX2: vpaddb -; CHECK: retq } ; PR23259: Verify that ISel doesn't crash with a 'fatal error in backend'