[PATCH] D22021: AMDGPU/SI: Don't handle a loop if there is no loop at all for a terminator BB.
Changpeng Fang via llvm-commits
llvm-commits at lists.llvm.org
Wed Jul 20 15:00:41 PDT 2016
cfang updated this revision to Diff 64773.
cfang added a comment.
Update based on review comments:
1. remove irrelevant comment;
2. add OPT test to check the llvm.amdgcn.loop intrinsic is not added;
3. add test that uses "ret" instruction instead of "unreachable".
https://reviews.llvm.org/D22021
Files:
lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
test/CodeGen/AMDGPU/si-annotate-cf-noloop.ll
Index: test/CodeGen/AMDGPU/si-annotate-cf-noloop.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/si-annotate-cf-noloop.ll
@@ -0,0 +1,71 @@
+; RUN: opt -mtriple=amdgcn-- -S -structurizecfg -si-annotate-control-flow %s | FileCheck -check-prefix=OPT %s
+; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+
+
+; OPT-LABEL: @annotate_unreachable_noloop(
+; OPT-NOT: call i1 @llvm.amdgcn.loop
+
+; GCN-LABEL: {{^}}annotate_unreachable_noloop:
+; GCN: s_cbranch_vccnz
+; GCN-NOT: s_endpgm
+; GCN: .Lfunc_end0
+define void @annotate_unreachable_noloop(<4 x float> addrspace(1)* noalias nocapture readonly %arg) #0 {
+bb:
+ %tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
+ br label %bb1
+
+bb1: ; preds = %bb
+ %tmp2 = sext i32 %tmp to i64
+ %tmp3 = getelementptr inbounds <4 x float>, <4 x float> addrspace(1)* %arg, i64 %tmp2
+ %tmp4 = load <4 x float>, <4 x float> addrspace(1)* %tmp3, align 16
+ br i1 undef, label %bb5, label %bb3
+
+bb3: ; preds = %bb1
+ %tmp6 = extractelement <4 x float> %tmp4, i32 2
+ %tmp7 = fcmp olt float %tmp6, 0.000000e+00
+ br i1 %tmp7, label %bb4, label %bb5 ; crash goes away if these are swapped
+
+bb4: ; preds = %bb3
+ unreachable
+
+bb5: ; preds = %bb3, %bb1
+ unreachable
+}
+
+
+; OPT-LABEL: @annotate_ret_noloop(
+; OPT-NOT: call i1 @llvm.amdgcn.loop
+
+; GCN-LABEL: {{^}}annotate_ret_noloop:
+; GCN: s_and_b64 vcc
+; GCN: s_cbranch_vccnz
+; GCN: s_endpgm
+; GCN: .Lfunc_end1
+define void @annotate_ret_noloop(<4 x float> addrspace(1)* noalias nocapture readonly %arg) #0 {
+bb:
+ %tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
+ br label %bb1
+
+bb1: ; preds = %bb
+ %tmp2 = sext i32 %tmp to i64
+ %tmp3 = getelementptr inbounds <4 x float>, <4 x float> addrspace(1)* %arg, i64 %tmp2
+ %tmp4 = load <4 x float>, <4 x float> addrspace(1)* %tmp3, align 16
+ br i1 undef, label %bb5, label %bb3
+
+bb3: ; preds = %bb1
+ %tmp6 = extractelement <4 x float> %tmp4, i32 2
+ %tmp7 = fcmp olt float %tmp6, 0.000000e+00
+ br i1 %tmp7, label %bb4, label %bb5 ; crash goes away if these are swapped
+
+bb4: ; preds = %bb3
+ ret void
+
+bb5: ; preds = %bb3, %bb1
+ ret void
+}
+
+
+declare i32 @llvm.amdgcn.workitem.id.x() #1
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind readnone }
Index: lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
===================================================================
--- lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
+++ lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
@@ -331,6 +331,8 @@
BasicBlock *BB = Term->getParent();
llvm::Loop *L = LI->getLoopFor(BB);
+ if (!L)
+ return;
BasicBlock *Target = Term->getSuccessor(1);
PHINode *Broken = PHINode::Create(Int64, 0, "", &Target->front());
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D22021.64773.patch
Type: text/x-patch
Size: 3159 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160720/775b9c99/attachment.bin>
More information about the llvm-commits
mailing list