RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2025-02-21 21:41:43 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add some tests based on PR21711

Browse Source 
These were originally added in r227242,
but that patch was reverted because it
caused a failure on AArch64.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239860 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sanjay Patel 2015-06-16 22:37:50 +00:00
parent 20a6785cd2
commit f0cbe326ff
1 changed files with 61 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
test/CodeGen/X86/MergeConsecutiveStores.ll
View File

@ -463,6 +463,67 @@ define void @merge_vec_element_store(<8 x float> %v, float* %ptr) {
; CHECK-NEXT: retq
}
; PR21711 - Merge vector stores into wider vector stores.
; These should be merged into 32-byte stores.
define void @merge_vec_extract_stores(<8 x float> %v1, <8 x float> %v2, <4 x float>* %ptr) {
%idx0 = getelementptr inbounds <4 x float>, <4 x float>* %ptr, i64 3
%idx1 = getelementptr inbounds <4 x float>, <4 x float>* %ptr, i64 4
%idx2 = getelementptr inbounds <4 x float>, <4 x float>* %ptr, i64 5
%idx3 = getelementptr inbounds <4 x float>, <4 x float>* %ptr, i64 6
%shuffle0 = shufflevector <8 x float> %v1, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%shuffle1 = shufflevector <8 x float> %v1, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
%shuffle2 = shufflevector <8 x float> %v2, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%shuffle3 = shufflevector <8 x float> %v2, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
store <4 x float> %shuffle0, <4 x float>* %idx0, align 16
store <4 x float> %shuffle1, <4 x float>* %idx1, align 16
store <4 x float> %shuffle2, <4 x float>* %idx2, align 16
store <4 x float> %shuffle3, <4 x float>* %idx3, align 16
ret void
; CHECK-LABEL: merge_vec_extract_stores
; CHECK: vmovaps %xmm0, 48(%rdi)
; CHECK-NEXT: vextractf128 $1, %ymm0, 64(%rdi)
; CHECK-NEXT: vmovaps %xmm1, 80(%rdi)
; CHECK-NEXT: vextractf128 $1, %ymm1, 96(%rdi)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
}
; Merging vector stores when sourced from vector loads is not currently handled.
define void @merge_vec_stores_from_loads(<4 x float>* %v, <4 x float>* %ptr) {
%load_idx0 = getelementptr inbounds <4 x float>, <4 x float>* %v, i64 0
%load_idx1 = getelementptr inbounds <4 x float>, <4 x float>* %v, i64 1
%v0 = load <4 x float>, <4 x float>* %load_idx0
%v1 = load <4 x float>, <4 x float>* %load_idx1
%store_idx0 = getelementptr inbounds <4 x float>, <4 x float>* %ptr, i64 0
%store_idx1 = getelementptr inbounds <4 x float>, <4 x float>* %ptr, i64 1
store <4 x float> %v0, <4 x float>* %store_idx0, align 16
store <4 x float> %v1, <4 x float>* %store_idx1, align 16
ret void
; CHECK-LABEL: merge_vec_stores_from_loads
; CHECK: vmovaps
; CHECK-NEXT: vmovaps
; CHECK-NEXT: vmovaps
; CHECK-NEXT: vmovaps
; CHECK-NEXT: retq
}
; Merging vector stores when sourced from a constant vector is not currently handled.
define void @merge_vec_stores_of_constants(<4 x i32>* %ptr) {
%idx0 = getelementptr inbounds <4 x i32>, <4 x i32>* %ptr, i64 3
%idx1 = getelementptr inbounds <4 x i32>, <4 x i32>* %ptr, i64 4
store <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32>* %idx0, align 16
store <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32>* %idx1, align 16
ret void
; CHECK-LABEL: merge_vec_stores_of_constants
; CHECK: vxorps
; CHECK-NEXT: vmovaps
; CHECK-NEXT: vmovaps
; CHECK-NEXT: retq
}
; This is a minimized test based on real code that was failing.
; We could merge stores (and loads) like this...