e39f6c1844
There are many tests that specify a target triple/CPU flags but no DataLayout which can lead to IR being generated that has unusual behaviour. This commit attempts to use the default DataLayout based on the relevant flags if there is no explicit override on the command line or in the IR file. One thing that is not currently possible to differentiate from a missing datalayout `target datalayout = ""` in the IR file since the current APIs don't allow detecting this case. If it is considered useful to support this case (instead of passing "-data-layout=" on the command line), I can change IR parsers to track whether they have seen such a directive and change the callback type. Differential Revision: https://reviews.llvm.org/D141060
66 lines
2.7 KiB
LLVM
66 lines
2.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -passes=memcpyopt -mtriple=x86_64 < %s | FileCheck %s --check-prefixes=CHECK,LIBCALLS
|
|
; RUN: opt -S -passes=memcpyopt -mtriple=amdgcn-- < %s | FileCheck %s --check-prefixes=CHECK,NO-LIBCALLS
|
|
; RUN: opt -S -passes=memcpyopt -mtriple=amdgcn-- -enable-memcpyopt-without-libcalls < %s \
|
|
; RUN: | FileCheck %s --check-prefixes=CHECK,LIBCALLS
|
|
|
|
; REQUIRES: amdgpu-registered-target
|
|
|
|
define void @dont_create_memset(ptr %p) {
|
|
; LIBCALLS-LABEL: @dont_create_memset(
|
|
; LIBCALLS-NEXT: [[P1:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 1
|
|
; LIBCALLS-NEXT: [[P2:%.*]] = getelementptr i32, ptr [[P]], i64 2
|
|
; LIBCALLS-NEXT: [[P3:%.*]] = getelementptr i32, ptr [[P]], i64 3
|
|
; LIBCALLS-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[P]], i8 0, i64 16, i1 false)
|
|
; LIBCALLS-NEXT: ret void
|
|
;
|
|
; NO-LIBCALLS-LABEL: @dont_create_memset(
|
|
; NO-LIBCALLS-NEXT: store i32 0, ptr [[P:%.*]], align 4
|
|
; NO-LIBCALLS-NEXT: [[P1:%.*]] = getelementptr i32, ptr [[P]], i64 1
|
|
; NO-LIBCALLS-NEXT: store i32 0, ptr [[P1]], align 4
|
|
; NO-LIBCALLS-NEXT: [[P2:%.*]] = getelementptr i32, ptr [[P]], i64 2
|
|
; NO-LIBCALLS-NEXT: store i32 0, ptr [[P2]], align 4
|
|
; NO-LIBCALLS-NEXT: [[P3:%.*]] = getelementptr i32, ptr [[P]], i64 3
|
|
; NO-LIBCALLS-NEXT: store i32 0, ptr [[P3]], align 4
|
|
; NO-LIBCALLS-NEXT: ret void
|
|
;
|
|
store i32 0, ptr %p
|
|
%p1 = getelementptr i32, ptr %p, i64 1
|
|
store i32 0, ptr %p1
|
|
%p2 = getelementptr i32, ptr %p, i64 2
|
|
store i32 0, ptr %p2
|
|
%p3 = getelementptr i32, ptr %p, i64 3
|
|
store i32 0, ptr %p3
|
|
ret void
|
|
}
|
|
|
|
%ty = type { i64 }
|
|
|
|
define void @dont_create_memcpy(ptr %p1, ptr %p2) {
|
|
; LIBCALLS-LABEL: @dont_create_memcpy(
|
|
; LIBCALLS-NEXT: call void @llvm.memmove.p0.p0.i64(ptr align 8 [[P2:%.*]], ptr align 8 [[P1:%.*]], i64 8, i1 false)
|
|
; LIBCALLS-NEXT: ret void
|
|
;
|
|
; NO-LIBCALLS-LABEL: @dont_create_memcpy(
|
|
; NO-LIBCALLS-NEXT: [[V:%.*]] = load [[TY:%.*]], ptr [[P1:%.*]], align 8
|
|
; NO-LIBCALLS-NEXT: store [[TY]] [[V]], ptr [[P2:%.*]], align 8
|
|
; NO-LIBCALLS-NEXT: ret void
|
|
;
|
|
%v = load %ty, ptr %p1
|
|
store %ty %v, ptr %p2
|
|
ret void
|
|
}
|
|
|
|
define void @forward_memcpy(ptr noalias %p1, ptr noalias %p2, ptr noalias %p3) {
|
|
; CHECK-LABEL: @forward_memcpy(
|
|
; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr [[P2:%.*]], ptr [[P1:%.*]], i64 16, i1 false)
|
|
; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr [[P3:%.*]], ptr [[P1]], i64 16, i1 false)
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @llvm.memcpy.p0.p0.i64(ptr %p2, ptr %p1, i64 16, i1 false)
|
|
call void @llvm.memcpy.p0.p0.i64(ptr %p3, ptr %p2, i64 16, i1 false)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.memcpy.p0.p0.i64(ptr, ptr, i64, i1)
|