[AMDGPU] Enable constant offset promotion to immediate operand for VMEM stores

Differential revision: https://reviews.llvm.org/D66958

llvm-svn: 371214

diff --git a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
index 70fb377..49f3481 100644 (file)
--- a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
+++ b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
@@ -1316,13 +1316,14 @@ bool SILoadStoreOptimizer::promoteConstantOffsetToImm(
     MemInfoMap &Visited,
     SmallPtrSet<MachineInstr *, 4> &AnchorList) {
 
+  if (!(MI.mayLoad() ^ MI.mayStore()))
+    return false;
+
   // TODO: Support flat and scratch.
-  if (AMDGPU::getGlobalSaddrOp(MI.getOpcode()) < 0 ||
-      TII->getNamedOperand(MI, AMDGPU::OpName::vdata) != NULL)
+  if (AMDGPU::getGlobalSaddrOp(MI.getOpcode()) < 0)
     return false;
 
-  // TODO: Support Store.
-  if (!MI.mayLoad())
+  if (MI.mayLoad() && TII->getNamedOperand(MI, AMDGPU::OpName::vdata) != NULL)
     return false;
 
   if (AnchorList.count(&MI))

diff --git a/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.mir b/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.mir
index 5c92afc..cf95723 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.mir
+++ b/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.mir
@@ -188,3 +188,27 @@ body:             |
     %30:vreg_64 = REG_SEQUENCE %26, %subreg.sub0, %28, %subreg.sub1
     %31:vreg_64 = GLOBAL_LOAD_DWORDX2 %30, 0, 0, 0, 0, implicit $exec
 ...
+---
+
+# GFX9-LABEL: name: diffoporder_add_store
+# GFX9: GLOBAL_STORE_DWORD %{{[0-9]+}}, %0.sub0, 1000, 0, 0, 0
+# GFX9: GLOBAL_STORE_DWORD %{{[0-9]+}}, %0.sub1, 0, 0, 0, 0
+
+name: diffoporder_add_store
+body:             |
+  bb.0.entry:
+
+    %0:vreg_64 = COPY $vgpr0_vgpr1
+
+    %1:sgpr_32 = S_MOV_B32 4000
+    %2:vgpr_32, %3:sreg_64_xexec = V_ADD_I32_e64 %0.sub0, %1, 0, implicit $exec
+    %4:vgpr_32, dead %5:sreg_64_xexec = V_ADDC_U32_e64 %0.sub1, 0, %3, 0, implicit $exec
+    %6:vreg_64 = REG_SEQUENCE %2, %subreg.sub0, %4, %subreg.sub1
+    GLOBAL_STORE_DWORD %6, %0.sub0, 0, 0, 0, 0, implicit $exec
+
+    %8:sgpr_32 = S_MOV_B32 3000
+    %9:vgpr_32, %10:sreg_64_xexec = V_ADD_I32_e64 %0.sub0, %8, 0, implicit $exec
+    %11:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 %0.sub1, 0, %10, 0, implicit $exec
+    %13:vreg_64 = REG_SEQUENCE %9, %subreg.sub0, %11, %subreg.sub1
+    GLOBAL_STORE_DWORD %13, %0.sub1, 0, 0, 0, 0, implicit $exec
+...