[PATCH] D91336: AMDGPU/GlobalISel: Fix negative offset folding for buffer_load

[Petar Avramovic via Phabricator via llvm-commits]

Petar.Avramovic updated this revision to Diff 306394.
Petar.Avramovic edited the summary of this revision.

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D91336/new/

https://reviews.llvm.org/D91336

Files:
  llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
  llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.s.buffer.load.mir


Index: llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.s.buffer.load.mir
===================================================================
--- llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.s.buffer.load.mir
+++ llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.s.buffer.load.mir
@@ -62,8 +62,9 @@
     ; FAST: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -60
     ; FAST: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
     ; FAST: [[ADD:%[0-9]+]]:vgpr(s32) = G_ADD [[COPY1]], [[COPY2]]
-    ; FAST: [[C1:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
-    ; FAST: [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[COPY]](<4 x s32>), [[C1]](s32), [[COPY1]], [[C]], 0, 0, 0 :: (dereferenceable invariant load 4)
+    ; FAST: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 0
+    ; FAST: [[C2:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
+    ; FAST: [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[COPY]](<4 x s32>), [[C2]](s32), [[ADD]], [[C1]], 0, 0, 0 :: (dereferenceable invariant load 4)
     ; FAST: S_ENDPGM 0, implicit [[AMDGPU_BUFFER_LOAD]](s32)
     ; GREEDY-LABEL: name: s_buffer_load_negative_offset
     ; GREEDY: liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $vgpr0
@@ -72,8 +73,9 @@
     ; GREEDY: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -60
     ; GREEDY: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
     ; GREEDY: [[ADD:%[0-9]+]]:vgpr(s32) = G_ADD [[COPY1]], [[COPY2]]
-    ; GREEDY: [[C1:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
-    ; GREEDY: [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[COPY]](<4 x s32>), [[C1]](s32), [[COPY1]], [[C]], 0, 0, 0 :: (dereferenceable invariant load 4)
+    ; GREEDY: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 0
+    ; GREEDY: [[C2:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 0
+    ; GREEDY: [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[COPY]](<4 x s32>), [[C2]](s32), [[ADD]], [[C1]], 0, 0, 0 :: (dereferenceable invariant load 4)
     ; GREEDY: S_ENDPGM 0, implicit [[AMDGPU_BUFFER_LOAD]](s32)
     %0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
     %1:_(s32) = COPY $vgpr0
Index: llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
@@ -1321,6 +1321,8 @@
   return Def->getOperand(0).getReg();
 }
 
+static bool signBitNotSet(unsigned Val) { return (Val & 0x80000000) == 0; }
+
 // Analyze a combined offset from an llvm.amdgcn.s.buffer intrinsic and store
 // the three offsets (voffset, soffset and instoffset)
 static unsigned setBufferOffsets(MachineIRBuilder &B,
@@ -1352,8 +1354,9 @@
       AMDGPU::getBaseWithConstantOffset(*MRI, CombinedOffset);
 
   uint32_t SOffset, ImmOffset;
-  if (Offset > 0 && AMDGPU::splitMUBUFOffset(Offset, SOffset, ImmOffset,
-                                             &RBI.Subtarget, Alignment)) {
+  if (Offset != 0 && signBitNotSet(Offset) &&
+      AMDGPU::splitMUBUFOffset(Offset, SOffset, ImmOffset, &RBI.Subtarget,
+                               Alignment)) {
     if (RBI.getRegBank(Base, *MRI, *RBI.TRI) == &AMDGPU::VGPRRegBank) {
       VOffsetReg = Base;
       SOffsetReg = B.buildConstant(S32, SOffset).getReg(0);
@@ -1373,7 +1376,8 @@
   }
 
   // Handle the variable sgpr + vgpr case.
-  if (MachineInstr *Add = getOpcodeDef(AMDGPU::G_ADD, CombinedOffset, *MRI)) {
+  MachineInstr *Add = getOpcodeDef(AMDGPU::G_ADD, CombinedOffset, *MRI);
+  if (Add && signBitNotSet(Offset)) {
     Register Src0 = getSrcRegIgnoringCopies(*MRI, Add->getOperand(1).getReg());
     Register Src1 = getSrcRegIgnoringCopies(*MRI, Add->getOperand(2).getReg());
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D91336.306394.patch
Type: text/x-patch
Size: 3689 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20201119/eaef37db/attachment.bin>