[PATCH] D77245: [AMDGPU] Fix crash in SILoadStoreOptimizer

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec created this revision.
rampitec added reviewers: arsenm, tstellar.
Herald added subscribers: kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely, kzhuravl.

SILoadStoreOptimizer::checkAndPrepareMerge() expects base and
paired instruction to come in order and scans MBB from base to
the paired instruction. An original order can be changed if
there were a dependent instruction in between and base instruction
was moved.

Fixed by bailing the optimization. In theory it might be possible
still to perform a merge by swapping instructions, but on practice
it bails anyway because it finds dependency on that same instruction
which has resulted in the base move.


https://reviews.llvm.org/D77245

Files:
  llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
  llvm/test/CodeGen/AMDGPU/merge-out-of-order-ldst.ll


Index: llvm/test/CodeGen/AMDGPU/merge-out-of-order-ldst.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/merge-out-of-order-ldst.ll
@@ -0,0 +1,28 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+
+ at L = external local_unnamed_addr addrspace(3) global [9 x double], align 16
+ at Ldisp = external local_unnamed_addr addrspace(3) global [96 x double], align 16
+
+; Stores are reordered during loads merge. This case used to assert while
+; scanning for a paired instruction because it used to expect paired one
+; to follow a base one.
+
+; GCN-LABEL: {{^}}out_of_order_merge:
+; GCN-COUNT2: ds_read2_b64
+; GCN-COUNT3: ds_write_b64
+define amdgpu_kernel void @out_of_order_merge() {
+entry:
+  %gep1 = getelementptr inbounds [96 x double], [96 x double] addrspace(3)* @Ldisp, i32 0, i32 0
+  %gep2 = getelementptr inbounds [96 x double], [96 x double] addrspace(3)* @Ldisp, i32 0, i32 1
+  %tmp12 = load <2 x double>, <2 x double> addrspace(3)* bitcast (double addrspace(3)* getelementptr inbounds ([9 x double], [9 x double] addrspace(3)* @L, i32 0, i32 1) to <2 x double> addrspace(3)*), align 8
+  %tmp14 = extractelement <2 x double> %tmp12, i32 0
+  %tmp15 = extractelement <2 x double> %tmp12, i32 1
+  %add50.i = fadd double %tmp14, %tmp15
+  store double %add50.i, double addrspace(3)* %gep1, align 8
+  %tmp16 = load double, double addrspace(3)* getelementptr inbounds ([9 x double], [9 x double] addrspace(3)* @L, i32 1, i32 0), align 8
+  store double %tmp16, double addrspace(3)* %gep2, align 8
+  %tmp17 = load <2 x double>, <2 x double> addrspace(3)* bitcast (double addrspace(3)* getelementptr inbounds ([9 x double], [9 x double] addrspace(3)* @L, i32 2, i32 1) to <2 x double> addrspace(3)*), align 8
+  %tmp19 = extractelement <2 x double> %tmp17, i32 1
+  store double %tmp19, double addrspace(3)* undef, align 8
+  ret void
+}
Index: llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
+++ llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
@@ -884,8 +884,19 @@
 
   MachineBasicBlock::iterator E = std::next(Paired.I);
   MachineBasicBlock::iterator MBBI = std::next(CI.I);
+  MachineBasicBlock::iterator MBBE = CI.I->getParent()->end();
   for (; MBBI != E; ++MBBI) {
 
+    if (MBBI == MBBE) {
+      // CombineInfo::Order is a hint on the instruction ordering within the
+      // basic block. This hint suggests that CI precedes Paired, which is
+      // true most of the times. However, moveInstsAfter() processing a
+      // previous list may have changed this order in a situation when it
+      // moves an instruction which exists in some other merge list.
+      // In this case it must be dependent.
+      return false;
+    }
+
     if ((getInstClass(MBBI->getOpcode(), *TII) != InstClass) ||
         (getInstSubclass(MBBI->getOpcode(), *TII) != InstSubclass)) {
       // This is not a matching instruction, but we can keep looking as


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D77245.254320.patch
Type: text/x-patch
Size: 3114 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200401/356f321b/attachment.bin>