6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-04-06 09:44:39 +00:00
Code Issues Projects Releases Wiki Activity

Improve test to actually check for a folded load.

Browse Source 
This test was checking for lack of a "movaps" (an aligned load)
rather than a "movups" (an unaligned load). It also included
a store which complicated the checking.

Add specific CPU runs to prevent subtarget feature flag overrides
from inhibiting this optimization.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227972 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sanjay Patel 2015-02-03 15:37:18 +00:00
parent 7df357f552
commit ec60318bf5
1 changed files with 15 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
test/CodeGen/X86/fold-vex.ll
View File

@ -1,16 +1,20 @@
; Use CPU parameters to ensure that a CPU-specific attribute is not overriding the AVX definition.
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=corei7-avx | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=btver2 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s
;CHECK: @test
; No need to load from memory. The operand will be loaded as part of the AND instr.
;CHECK-NOT: vmovaps
;CHECK: vandps
;CHECK: ret
; No need to load unaligned operand from memory using an explicit instruction with AVX.
; The operand should be folded into the AND instr.
define void @test1(<8 x i32>* %p0, <8 x i32> %in1) nounwind {
entry:
%in0 = load <8 x i32>* %p0, align 2
%a = and <8 x i32> %in0, %in1
store <8 x i32> %a, <8 x i32>* undef
ret void
define <4 x i32> @test1(<4 x i32>* %p0, <4 x i32> %in1) nounwind {
%in0 = load <4 x i32>* %p0, align 2
%a = and <4 x i32> %in0, %in1
ret <4 x i32> %a
; CHECK-LABEL: @test1
; CHECK-NOT: vmovups
; CHECK: vandps (%rdi), %xmm0, %xmm0
; CHECK-NEXT: ret
}