summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/AMDGPU/branch-condition-and.ll
diff options
context:
space:
mode:
authorNicolai Haehnle <nhaehnle@gmail.com>2016-10-07 08:40:14 +0000
committerNicolai Haehnle <nhaehnle@gmail.com>2016-10-07 08:40:14 +0000
commit87bc4c218bb8aa0479c3775de451f2552ab4a8f1 (patch)
tree4b42e0fd6094e0276e5c6a67f2c3c086420af6b2 /llvm/test/CodeGen/AMDGPU/branch-condition-and.ll
parenta0016ec95faa172e00896a4c13396ae7d775d13b (diff)
downloadbcm5719-llvm-87bc4c218bb8aa0479c3775de451f2552ab4a8f1.tar.gz
bcm5719-llvm-87bc4c218bb8aa0479c3775de451f2552ab4a8f1.zip
AMDGPU: Fix use-after-free in SIOptimizeExecMasking
Summary: There was a bug with sequences like s_mov_b64 s[0:1], exec s_and_b64 s[2:3]<def>, s[0:1], s[2:3]<kill> ... s_mov_b64_term exec, s[2:3] because s[2:3] was defined and used in the same instruction, ending up with SaveExecInst inside OtherUseInsts. Note that the test case also exposes an unrelated bug. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=98028 Reviewers: tstellarAMD, arsenm Subscribers: kzhuravl, wdng, yaxunl, llvm-commits, tony-tye Differential Revision: https://reviews.llvm.org/D25306 llvm-svn: 283528
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/branch-condition-and.ll')
-rw-r--r--llvm/test/CodeGen/AMDGPU/branch-condition-and.ll39
1 files changed, 39 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/branch-condition-and.ll b/llvm/test/CodeGen/AMDGPU/branch-condition-and.ll
new file mode 100644
index 00000000000..40a66c26675
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/branch-condition-and.ll
@@ -0,0 +1,39 @@
+; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+
+; This used to crash because during intermediate control flow lowering, there
+; was a sequence
+; s_mov_b64 s[0:1], exec
+; s_and_b64 s[2:3], s[0:1], s[2:3] ; def & use of the same register pair
+; ...
+; s_mov_b64_term exec, s[2:3]
+; that was not treated correctly.
+;
+; GCN-LABEL: {{^}}ham:
+; GCN-DAG: v_cmp_lt_f32_e64 [[OTHERCC:s\[[0-9]+:[0-9]+\]]],
+; GCN-DAG: v_cmp_lt_f32_e32 vcc,
+; GCN: s_and_b64 [[AND:s\[[0-9]+:[0-9]+\]]], vcc, [[OTHERCC]]
+; GCN: s_and_saveexec_b64 [[SAVED:s\[[0-9]+:[0-9]+\]]], [[AND]]
+; GCN: s_xor_b64 [[SAVED]], exec, [[SAVED]]
+;
+; TODO: The following sequence is a bug (missing s_endpgm)!
+;
+; GCN: s_branch [[BB:BB[0-9]+_[0-9]+]]
+; GCN: [[BB]]:
+; GCN-NEXT: .Lfunc_end0:
+define amdgpu_ps void @ham(float %arg, float %arg1) #0 {
+bb:
+ %tmp = fcmp ogt float %arg, 0.000000e+00
+ %tmp2 = fcmp ogt float %arg1, 0.000000e+00
+ %tmp3 = and i1 %tmp, %tmp2
+ br i1 %tmp3, label %bb4, label %bb5
+
+bb4: ; preds = %bb
+ unreachable
+
+bb5: ; preds = %bb
+ ret void
+}
+
+attributes #0 = { nounwind readonly "InitialPSInputAddr"="36983" }
+attributes #1 = { nounwind readnone }
OpenPOWER on IntegriCloud