Merging r278268:

------------------------------------------------------------------------
r278268 | nhaehnle | 2016-08-10 11:51:14 -0700 (Wed, 10 Aug 2016) | 28 lines

LiveIntervalAnalysis: fix a crash in repairOldRegInRange

Summary:
See the new test case for one that was (non-deterministically) crashing
on trunk and deterministically hit the assertion that I added in D23302.
Basically, the machine function contains a sequence

     DS_WRITE_B32 %vreg4, %vreg14:sub0, ...
     DS_WRITE_B32 %vreg4, %vreg14:sub0, ...
     %vreg14:sub1<def> = COPY %vreg14:sub0

and SILoadStoreOptimizer::mergeWrite2Pair merges the two DS_WRITE_B32
instructions into one before calling repairIntervalsInRange.

Now repairIntervalsInRange wants to repair %vreg14, in particular, and
ends up trying to repair %vreg14:sub1 as well, but that only becomes
active _after_ the range that is to be repaired, hence the crash due
to LR.find(...) == LR.begin() at the start of repairOldRegInRange.

I believe that just skipping those subrange is fine, but again, not too
familiar with that code.

Reviewers: MatzeB, kparzysz, tstellarAMD

Subscribers: llvm-commits, MatzeB

Differential Revision: https://reviews.llvm.org/D23303

------------------------------------------------------------------------

llvm-svn: 288454

2 files changed, 41 insertions, 0 deletions

diff --git a/llvm/lib/CodeGen/LiveIntervalAnalysis.cpp b/llvm/lib/CodeGen/LiveIntervalAnalysis.cpp
index 5f3281f6771d..e2c35b0a1d86 100644
--- a/llvm/lib/CodeGen/LiveIntervalAnalysis.cpp
+++ b/llvm/lib/CodeGen/LiveIntervalAnalysis.cpp
@@ -1394,6 +1394,11 @@ void LiveIntervals::repairOldRegInRange(const MachineBasicBlock::iterator Begin,
                                         LaneBitmask LaneMask) {
   LiveInterval::iterator LII = LR.find(endIdx);
   SlotIndex lastUseIdx;
+  if (LII == LR.begin()) {
+    // This happens when the function is called for a subregister that only
+    // occurs _after_ the range that is to be repaired.
+    return;
+  }
   if (LII != LR.end() && LII->start < endIdx)
     lastUseIdx = LII->end;
   else
diff --git a/llvm/test/CodeGen/AMDGPU/merge-store-crash.ll b/llvm/test/CodeGen/AMDGPU/merge-store-crash.ll
new file mode 100644
index 000000000000..ef552e295fd4
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/merge-store-crash.ll
@@ -0,0 +1,36 @@
+; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck %s
+
+; This is used to crash in LiveIntervalAnalysis via SILoadStoreOptimizer
+; while fixing up the merge of two ds_write instructions.
+
+@tess_lds = external addrspace(3) global [8192 x i32]
+
+; CHECK-LABEL: {{^}}main:
+; CHECK: ds_write2_b32
+; CHECK: v_mov_b32_e32 v1, v0
+; CHECK: tbuffer_store_format_xyzw v[0:3],
+define amdgpu_vs void @main(i32 inreg %arg) {
+main_body:
+  %tmp = load float, float addrspace(3)* undef, align 4
+  %tmp1 = load float, float addrspace(3)* undef, align 4
+  store float %tmp, float addrspace(3)* null, align 4
+  %tmp2 = bitcast float %tmp to i32
+  %tmp3 = add nuw nsw i32 0, 1
+  %tmp4 = zext i32 %tmp3 to i64
+  %tmp5 = getelementptr [8192 x i32], [8192 x i32] addrspace(3)* @tess_lds, i64 0, i64 %tmp4
+  %tmp6 = bitcast i32 addrspace(3)* %tmp5 to float addrspace(3)*
+  store float %tmp1, float addrspace(3)* %tmp6, align 4
+  %tmp7 = bitcast float %tmp1 to i32
+  %tmp8 = insertelement <4 x i32> undef, i32 %tmp2, i32 0
+  %tmp9 = insertelement <4 x i32> %tmp8, i32 %tmp7, i32 1
+  %tmp10 = insertelement <4 x i32> %tmp9, i32 undef, i32 2
+  %tmp11 = insertelement <4 x i32> %tmp10, i32 undef, i32 3
+  call void @llvm.SI.tbuffer.store.v4i32(<16 x i8> undef, <4 x i32> %tmp11, i32 4, i32 undef, i32 %arg, i32 0, i32 14, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
+  ret void
+}
+
+; Function Attrs: nounwind
+declare void @llvm.SI.tbuffer.store.v4i32(<16 x i8>, <4 x i32>, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32) #0
+
+attributes #0 = { nounwind }