[AMDGPU] Turn off MergeConsecutiveStores() before Instruction Selection for AMDGPU...

Differential Revision: https://reviews.llvm.org/D41377

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321100 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AMDGPU/AMDGPUISelLowering.h b/lib/Target/AMDGPU/AMDGPUISelLowering.h
index 3f8a9b1..5c31bdd 100644 (file)
--- a/lib/Target/AMDGPU/AMDGPUISelLowering.h
+++ b/lib/Target/AMDGPU/AMDGPUISelLowering.h
@@ -202,6 +202,16 @@ public:
 
   const char* getTargetNodeName(unsigned Opcode) const override;
 
+  // FIXME: Turn off MergeConsecutiveStores() before Instruction Selection
+  // for AMDGPU.
+  // A commit ( git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319036
+  // 91177308-0d34-0410-b5e6-96231b3b80d8 ) turned on
+  // MergeConsecutiveStores() before Instruction Selection for all targets.
+  // Enough AMDGPU compiles go into an infinite loop ( MergeConsecutiveStores()
+  // merges two stores; LegalizeStoreOps() un-merges; MergeConsecutiveStores()
+  // re-merges, etc. ) to warrant turning it off for now.
+  bool mergeStoresAfterLegalization() const override { return false; }
+
   bool isFsqrtCheap(SDValue Operand, SelectionDAG &DAG) const override {
     return true;
   }

diff --git a/test/CodeGen/AMDGPU/amdgpu.private-memory.ll b/test/CodeGen/AMDGPU/amdgpu.private-memory.ll
index 228d3c7..71c4c83 100644 (file)
--- a/test/CodeGen/AMDGPU/amdgpu.private-memory.ll
+++ b/test/CodeGen/AMDGPU/amdgpu.private-memory.ll
@@ -251,7 +251,8 @@ entry:
 
 ; R600: MOVA_INT
 
-; SI-PROMOTE-DAG: buffer_store_short v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:4 ; encoding:
+; SI-PROMOTE-DAG: buffer_store_byte v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:4 ; encoding:
+; SI-PROMOTE-DAG: buffer_store_byte v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:5 ; encoding:
 
 ; SI-ALLOCA-DAG: buffer_store_byte v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:4 ; encoding: [0x04,0x00,0x60,0xe0
 ; SI-ALLOCA-DAG: buffer_store_byte v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:5 ; encoding: [0x05,0x00,0x60,0xe0

diff --git a/test/CodeGen/AMDGPU/memory-legalizer-store-infinite-loop.ll b/test/CodeGen/AMDGPU/memory-legalizer-store-infinite-loop.ll
new file mode 100644 (file)
index 0000000..f97785b
--- /dev/null
+++ b/test/CodeGen/AMDGPU/memory-legalizer-store-infinite-loop.ll
@@ -0,0 +1,32 @@
+; RUN: llc -mtriple=amdgcn--amdhsa-amdgiz -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+
+; Effectively, check that the compile finishes; in the case
+; of an infinite loop, llc toggles between merging 2 ST4s
+; ( MergeConsecutiveStores() ) and breaking the resulting ST8
+; apart ( LegalizeStoreOps() ).
+
+target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:32:32-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5"
+
+; GCN-LABEL: {{^}}_Z6brokenPd:
+; GCN: flat_store_dword v[{{[0-9]+}}:{{[0-9]+}}], {{v[0-9]+}}
+; GCN: flat_store_dword v[{{[0-9]+}}:{{[0-9]+}}], {{v[0-9]+}}
+define amdgpu_kernel void @_Z6brokenPd(double* %arg) {
+bb:
+  %tmp = alloca double, align 8, addrspace(5)
+  %tmp1 = alloca double, align 8, addrspace(5)
+  %tmp2 = load double, double* %arg, align 8
+  br i1 1, label %bb6, label %bb4
+
+bb3:                                             ; No predecessors!
+  br label %bb4
+
+bb4:                                             ; preds = %bb3, %bb
+  %tmp5 = phi double addrspace(5)* [ %tmp1, %bb3 ], [ %tmp, %bb ]
+  store double %tmp2, double addrspace(5)* %tmp5, align 8
+  br label %bb6
+
+bb6:                                             ; preds = %bb4, %bb
+  %tmp7 = phi double [ 0x7FF8123000000000, %bb4 ], [ 0x7FF8000000000000, %bb ]
+  store double %tmp7, double* %arg, align 8
+  ret void
+}