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

[X86][AVX] Regenerate broadcast upgrade tests 

llvm-svn: 275398
This commit is contained in:
Simon Pilgrim 2016-07-14 11:05:43 +00:00
parent bd81a7eebc
commit 9e812169cc
2 changed files with 24 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
llvm/test/CodeGen/X86/x86-upgrade-avx-vbroadcast.ll
View File

@ -1,41 +1,44 @@
; RUN: llc -mattr=+avx < %s | FileCheck %s
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-macosx10.9.0 -mattr=+avx | FileCheck %s
; Check that we properly upgrade the AVX vbroadcast intrinsics to IR. The
; expectation is that we should still get the original instruction back that
; maps to the intrinsic.
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.9.0"
; CHECK-LABEL: test_mm_broadcast_ss:
define <4 x float> @test_mm_broadcast_ss(float* readonly %__a){
; CHECK-LABEL: test_mm_broadcast_ss:
; CHECK: ## BB#0: ## %entry
; CHECK-NEXT: vbroadcastss (%rdi), %xmm0
; CHECK-NEXT: retq
entry:
%0 = bitcast float* %__a to i8*
; CHECK: vbroadcastss (%{{.*}}), %xmm
%1 = tail call <4 x float> @llvm.x86.avx.vbroadcast.ss(i8* %0)
ret <4 x float> %1
}
declare <8 x float> @llvm.x86.avx.vbroadcast.ss.256(i8*)
; CHECK-LABEL: test_mm256_broadcast_sd:
define <4 x double> @test_mm256_broadcast_sd(double* readonly %__a) {
; CHECK-LABEL: test_mm256_broadcast_sd:
; CHECK: ## BB#0: ## %entry
; CHECK-NEXT: vbroadcastsd (%rdi), %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast double* %__a to i8*
; CHECK: vbroadcastsd (%{{.*}}), %ymm
%1 = tail call <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8* %0)
ret <4 x double> %1
}
declare <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8*)
; CHECK-LABEL: test_mm256_broadcast_ss:
define <8 x float> @test_mm256_broadcast_ss(float* readonly %__a) {
; CHECK-LABEL: test_mm256_broadcast_ss:
; CHECK: ## BB#0: ## %entry
; CHECK-NEXT: vbroadcastss (%rdi), %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast float* %__a to i8*
; CHECK: vbroadcastss (%{{.*}}), %ymm
%1 = tail call <8 x float> @llvm.x86.avx.vbroadcast.ss.256(i8* %0)
ret <8 x float> %1
}
declare <8 x float> @llvm.x86.avx.vbroadcast.ss.256(i8*)
declare <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8*)
declare <4 x float> @llvm.x86.avx.vbroadcast.ss(i8*)

12
llvm/test/CodeGen/X86/x86-upgrade-avx2-vbroadcast.ll
View File

@ -1,13 +1,17 @@
; RUN: llc -mattr=+avx2 < %s | FileCheck %s
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-macosx10.10.0 -mattr=+avx2 | FileCheck %s
; Check that we properly upgrade the AVX2 vbroadcast intrinsic to IR.
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.10.0"
define <4 x i64> @broadcast128(<2 x i64> %src) {
; CHECK-LABEL: broadcast128
; CHECK: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; CHECK-LABEL: broadcast128:
; CHECK: ## BB#0:
; CHECK-NEXT: ## kill: %XMM0<def> %XMM0<kill> %YMM0<def>
; CHECK-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; CHECK-NEXT: retq
%1 = alloca <2 x i64>, align 16
%2 = bitcast <2 x i64>* %1 to i8*
store <2 x i64> %src, <2 x i64>* %1, align 16