RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2026-07-18 13:16:24 -04:00
Code Issues Packages Projects Releases 10 Wiki Activity

[MemCpyOpt] Add tests for memset->memcpy forwaring with undef tail; NFC

Browse Source 
These are baseline tests for D55120.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@348644 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Nikita Popov
2018-12-07 21:16:52 +00:00
parent 9ee6b26355
commit f6f2b8d5fd
1 changed files with 152 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/Transforms/MemCpyOpt/memset-memcpy-oversized.ll
+152
View File
@@ -0,0 +1,152 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -memcpyopt -S %s | FileCheck %s
; memset -> memcpy forwarding, if memcpy is larger than memset, but trailing
; bytes are known to be undef.
%T = type { i64, i32, i32 }
define void @test_alloca(i8* %result) {
; CHECK-LABEL: @test_alloca(
; CHECK-NEXT: [[A:%.*]] = alloca [[T:%.*]], align 8
; CHECK-NEXT: [[B:%.*]] = bitcast %T* [[A]] to i8*
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 [[B]], i8 0, i64 12, i1 false)
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[RESULT:%.*]], i8* align 8 [[B]], i64 16, i1 false)
; CHECK-NEXT: ret void
;
%a = alloca %T, align 8
%b = bitcast %T* %a to i8*
call void @llvm.memset.p0i8.i64(i8* align 8 %b, i8 0, i64 12, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %result, i8* align 8 %b, i64 16, i1 false)
ret void
}
define void @test_alloca_with_lifetimes(i8* %result) {
; CHECK-LABEL: @test_alloca_with_lifetimes(
; CHECK-NEXT: [[A:%.*]] = alloca [[T:%.*]], align 8
; CHECK-NEXT: [[B:%.*]] = bitcast %T* [[A]] to i8*
; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 16, i8* [[B]])
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 [[B]], i8 0, i64 12, i1 false)
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[RESULT:%.*]], i8* align 8 [[B]], i64 16, i1 false)
; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 16, i8* [[B]])
; CHECK-NEXT: ret void
;
%a = alloca %T, align 8
%b = bitcast %T* %a to i8*
call void @llvm.lifetime.start.p0i8(i64 16, i8* %b)
call void @llvm.memset.p0i8.i64(i8* align 8 %b, i8 0, i64 12, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %result, i8* align 8 %b, i64 16, i1 false)
call void @llvm.lifetime.end.p0i8(i64 16, i8* %b)
ret void
}
define void @test_malloc_with_lifetimes(i8* %result) {
; CHECK-LABEL: @test_malloc_with_lifetimes(
; CHECK-NEXT: [[A:%.*]] = call i8* @malloc(i64 16)
; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 16, i8* [[A]])
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 [[A]], i8 0, i64 12, i1 false)
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[RESULT:%.*]], i8* align 8 [[A]], i64 16, i1 false)
; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 16, i8* [[A]])
; CHECK-NEXT: call void @free(i8* [[A]])
; CHECK-NEXT: ret void
;
%a = call i8* @malloc(i64 16)
call void @llvm.lifetime.start.p0i8(i64 16, i8* %a)
call void @llvm.memset.p0i8.i64(i8* align 8 %a, i8 0, i64 12, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %result, i8* align 8 %a, i64 16, i1 false)
call void @llvm.lifetime.end.p0i8(i64 16, i8* %a)
call void @free(i8* %a)
ret void
}
; memcpy size is larger than lifetime, don't optimize.
define void @test_copy_larger_than_lifetime_size(i8* %result) {
; CHECK-LABEL: @test_copy_larger_than_lifetime_size(
; CHECK-NEXT: [[A:%.*]] = call i8* @malloc(i64 16)
; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 12, i8* [[A]])
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 [[A]], i8 0, i64 12, i1 false)
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[RESULT:%.*]], i8* align 8 [[A]], i64 16, i1 false)
; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 12, i8* [[A]])
; CHECK-NEXT: call void @free(i8* [[A]])
; CHECK-NEXT: ret void
;
%a = call i8* @malloc(i64 16)
call void @llvm.lifetime.start.p0i8(i64 12, i8* %a)
call void @llvm.memset.p0i8.i64(i8* align 8 %a, i8 0, i64 12, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %result, i8* align 8 %a, i64 16, i1 false)
call void @llvm.lifetime.end.p0i8(i64 12, i8* %a)
call void @free(i8* %a)
ret void
}
; The trailing bytes are not known to be undef, we can't ignore them.
define void @test_not_undef_memory(i8* %result, i8* %input) {
; CHECK-LABEL: @test_not_undef_memory(
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 [[INPUT:%.*]], i8 0, i64 12, i1 false)
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[RESULT:%.*]], i8* align 8 [[INPUT]], i64 16, i1 false)
; CHECK-NEXT: ret void
;
call void @llvm.memset.p0i8.i64(i8* align 8 %input, i8 0, i64 12, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %result, i8* align 8 %input, i64 16, i1 false)
ret void
}
; Memset is volatile, memcpy is not. Can be optimized.
define void @test_volatile_memset(i8* %result) {
; CHECK-LABEL: @test_volatile_memset(
; CHECK-NEXT: [[A:%.*]] = alloca [[T:%.*]], align 8
; CHECK-NEXT: [[B:%.*]] = bitcast %T* [[A]] to i8*
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 [[B]], i8 0, i64 12, i1 true)
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[RESULT:%.*]], i8* align 8 [[B]], i64 16, i1 false)
; CHECK-NEXT: ret void
;
%a = alloca %T, align 8
%b = bitcast %T* %a to i8*
call void @llvm.memset.p0i8.i64(i8* align 8 %b, i8 0, i64 12, i1 true)
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %result, i8* align 8 %b, i64 16, i1 false)
ret void
}
; Memcpy is volatile, memset is not. Cannot be optimized.
define void @test_volatile_memcpy(i8* %result) {
; CHECK-LABEL: @test_volatile_memcpy(
; CHECK-NEXT: [[A:%.*]] = alloca [[T:%.*]], align 8
; CHECK-NEXT: [[B:%.*]] = bitcast %T* [[A]] to i8*
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 [[B]], i8 0, i64 12, i1 false)
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[RESULT:%.*]], i8* align 8 [[B]], i64 16, i1 true)
; CHECK-NEXT: ret void
;
%a = alloca %T, align 8
%b = bitcast %T* %a to i8*
call void @llvm.memset.p0i8.i64(i8* align 8 %b, i8 0, i64 12, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %result, i8* align 8 %b, i64 16, i1 true)
ret void
}
; Write between memset and memcpy, can't optimize.
define void @test_write_between(i8* %result) {
; CHECK-LABEL: @test_write_between(
; CHECK-NEXT: [[A:%.*]] = alloca [[T:%.*]], align 8
; CHECK-NEXT: [[B:%.*]] = bitcast %T* [[A]] to i8*
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 [[B]], i8 0, i64 12, i1 false)
; CHECK-NEXT: store i8 -1, i8* [[B]]
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[RESULT:%.*]], i8* align 8 [[B]], i64 16, i1 false)
; CHECK-NEXT: ret void
;
%a = alloca %T, align 8
%b = bitcast %T* %a to i8*
call void @llvm.memset.p0i8.i64(i8* align 8 %b, i8 0, i64 12, i1 false)
store i8 -1, i8* %b
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %result, i8* align 8 %b, i64 16, i1 false)
ret void
}
declare i8* @malloc(i64)
declare void @free(i8*)
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1)
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1)
declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture)
declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture)