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

[GVN] Add testcase that uses masked loads and stores, NFC

This commit is contained in:
Krzysztof Parzyszek 2020-09-08 11:26:10 -05:00
parent 514df1b2bb
commit d0ccfcb040
1 changed files with 39 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
llvm/test/Transforms/GVN/masked-load-store.ll Normal file
View File

@ -0,0 +1,39 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -gvn -S < %s | FileCheck %s
define <128 x i8> @f0(<128 x i8>* %a0, <128 x i8> %a1, <128 x i8> %a2) {
; CHECK-LABEL: @f0(
; CHECK-NEXT: [[V0:%.*]] = icmp eq <128 x i8> [[A1:%.*]], [[A2:%.*]]
; CHECK-NEXT: [[V1:%.*]] = call <128 x i8> @llvm.masked.load.v128i8.p0v128i8(<128 x i8>* [[A0:%.*]], i32 4, <128 x i1> [[V0]], <128 x i8> undef)
; CHECK-NEXT: [[V3:%.*]] = add <128 x i8> [[V1]], [[V1]]
; CHECK-NEXT: ret <128 x i8> [[V3]]
;
%v0 = icmp eq <128 x i8> %a1, %a2
%v1 = call <128 x i8> @llvm.masked.load.v128i8.p0v128i8(<128 x i8>* %a0, i32 4, <128 x i1> %v0, <128 x i8> undef)
%v2 = call <128 x i8> @llvm.masked.load.v128i8.p0v128i8(<128 x i8>* %a0, i32 4, <128 x i1> %v0, <128 x i8> undef)
%v3 = add <128 x i8> %v1, %v2
ret <128 x i8> %v3
}
define <128 x i8> @f1(<128 x i8>* %a0, <128 x i8> %a1, <128 x i8> %a2) {
; CHECK-LABEL: @f1(
; CHECK-NEXT: [[V0:%.*]] = icmp eq <128 x i8> [[A1:%.*]], [[A2:%.*]]
; CHECK-NEXT: [[V1:%.*]] = getelementptr <128 x i8>, <128 x i8>* [[A0:%.*]], i32 1
; CHECK-NEXT: [[V2:%.*]] = call <128 x i8> @llvm.masked.load.v128i8.p0v128i8(<128 x i8>* [[A0]], i32 4, <128 x i1> [[V0]], <128 x i8> undef)
; CHECK-NEXT: call void @llvm.masked.store.v128i8.p0v128i8(<128 x i8> [[A2]], <128 x i8>* [[V1]], i32 4, <128 x i1> [[V0]])
; CHECK-NEXT: [[V3:%.*]] = call <128 x i8> @llvm.masked.load.v128i8.p0v128i8(<128 x i8>* [[A0]], i32 4, <128 x i1> [[V0]], <128 x i8> undef)
; CHECK-NEXT: [[V4:%.*]] = add <128 x i8> [[V2]], [[V3]]
; CHECK-NEXT: ret <128 x i8> [[V4]]
;
%v0 = icmp eq <128 x i8> %a1, %a2
%v1 = getelementptr <128 x i8>, <128 x i8>* %a0, i32 1
%v2 = call <128 x i8> @llvm.masked.load.v128i8.p0v128i8(<128 x i8>* %a0, i32 4, <128 x i1> %v0, <128 x i8> undef)
call void @llvm.masked.store.v128i8.p0v128i8(<128 x i8> %a2, <128 x i8>* %v1, i32 4, <128 x i1> %v0)
%v3 = call <128 x i8> @llvm.masked.load.v128i8.p0v128i8(<128 x i8>* %a0, i32 4, <128 x i1> %v0, <128 x i8> undef)
%v4 = add <128 x i8> %v2, %v3
ret <128 x i8> %v4
}
declare <128 x i8> @llvm.masked.load.v128i8.p0v128i8(<128 x i8>*, i32, <128 x i1>, <128 x i8>)
declare void @llvm.masked.store.v128i8.p0v128i8(<128 x i8>, <128 x i8>*, i32, <128 x i1>)