maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/NVPTX/intrin-nocapture.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

22 lines
686 B
LLVM
Raw Normal View History

[NVPTX] Remove NoCapture from address space conversion intrinsics. NoCapture is not valid in this case, and was causing incorrect optimizations. llvm-svn: 174896
2013-02-12 02:56:35 +08:00
; RUN: opt < %s -O3 -S | FileCheck %s
; Address space intrinsics were erroneously marked NoCapture, leading to bad
; optimizations (such as the store below being eliminated as dead code). This
; test makes sure we don't regress.
declare void @foo(i32 addrspace(1)*)
declare i32 addrspace(1)* @llvm.nvvm.ptr.gen.to.global.p1i32.p0i32(i32*)
; CHECK: @bar
define void @bar() {
%t1 = alloca i32
Reapply 239795 - [InstCombine] Propagate non-null facts to call parameters The original change broke clang side tests. I will be submitting those momentarily. This change includes post commit feedback on the original change from from Pete Cooper. Original Submission comments: If a parameter to a function is known non-null, use the existing parameter attributes to record that fact at the call site. This has no optimization benefit by itself - that I know of - but is an enabling change for http://reviews.llvm.org/D9129. Differential Revision: http://reviews.llvm.org/D9132 llvm-svn: 239849
2015-06-17 04:24:25 +08:00
; CHECK: call i32 addrspace(1)* @llvm.nvvm.ptr.gen.to.global.p1i32.p0i32(i32* nonnull %t1)
[NVPTX] Remove NoCapture from address space conversion intrinsics. NoCapture is not valid in this case, and was causing incorrect optimizations. llvm-svn: 174896
2013-02-12 02:56:35 +08:00
; CHECK-NEXT: store i32 10, i32* %t1
%t2 = call i32 addrspace(1)* @llvm.nvvm.ptr.gen.to.global.p1i32.p0i32(i32* %t1)
store i32 10, i32* %t1
call void @foo(i32 addrspace(1)* %t2)
ret void
}