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

[AMDGPU] Ignore call graph node which does not have function info. 

While collecting reachable callees (from kernels), ignore call graph node which
does not have associated function or associated function is not a definition.

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D107329
This commit is contained in:
hsmahesha 2021-08-04 09:38:55 +05:30
parent df4e0beaeb
commit 596e61c332
2 changed files with 43 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/lib/Target/AMDGPU/Utils/AMDGPULDSUtils.cpp
View File

@ -68,6 +68,11 @@ class CollectReachableCallees {
if (!VisitedCGNodes.insert(CGN).second)
continue;
// Ignore call graph node which does not have associated function or
// associated function is not a definition.
if (!CGN->getFunction() || CGN->getFunction()->isDeclaration())
continue;
for (auto GI = CGN->begin(), GE = CGN->end(); GI != GE; ++GI) {
auto *RCB = cast<CallBase>(GI->first.getValue());
auto *RCGN = GI->second;

38
llvm/test/CodeGen/AMDGPU/replace-lds-by-ptr-call-to-declare-only-func.ll Normal file
View File

@ -0,0 +1,38 @@
; RUN: opt -S -mtriple=amdgcn-- -amdgpu-replace-lds-use-with-pointer -amdgpu-enable-lds-replace-with-pointer=true < %s | FileCheck %s
; DESCRIPTION:
;
; The kernel 'kern' makes a call to declared only function `foo`, hence `foo`
; is not considered as reachable callee, and is ignored. The function `goo`
; which uses LDS is not called from kernel 'kern', hence it is also ignored.
;
; Original LDS should exist.
; CHECK: @lds = internal local_unnamed_addr addrspace(3) global i32 undef, align 4
@lds = internal local_unnamed_addr addrspace(3) global i32 undef, align 4
; Pointer should not be created.
; CHECK-NOT: @lds.ptr = internal unnamed_addr addrspace(3) global i16 undef, align 2
; CHECK: declare i32 @foo()
declare i32 @foo()
; No change
define internal void @goo() {
; CHECK-LABEL: entry:
; CHECK: store i32 undef, i32 addrspace(3)* @lds, align 4
; CHECK: ret void
entry:
store i32 undef, i32 addrspace(3)* @lds, align 4
ret void
}
; No change
define weak amdgpu_kernel void @kern() {
; CHECK-LABEL: entry:
; CHECK-LABEL: %nt = call i32 @foo()
; CHECK-LABEL: ret void
entry:
%nt = call i32 @foo()
ret void
}