[llvm] 3b0f506 - [AMDGPU] Support `nuw` and `nusw` in buffer fat pointer lowering (#115039)

[via llvm-commits]

Author: Krzysztof Drewniak
Date: 2024-11-06T11:42:47-06:00
New Revision: 3b0f506c87cf7cf32604c9592aeca3ede0e1f79e

URL: https://github.com/llvm/llvm-project/commit/3b0f506c87cf7cf32604c9592aeca3ede0e1f79e
DIFF: https://github.com/llvm/llvm-project/commit/3b0f506c87cf7cf32604c9592aeca3ede0e1f79e.diff

LOG: [AMDGPU] Support `nuw` and `nusw` in buffer fat pointer lowering (#115039)

This commit usis the `nuw` flag on `getelemnetptr` to set the `nuw` flag
on buffer offset additions, and also moves from `inbounds` to the looser
`nusw` for the existing case.

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/AMDGPULowerBufferFatPointers.cpp
    llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-pointer-ops.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/AMDGPULowerBufferFatPointers.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerBufferFatPointers.cpp
index 787747e6055805..c7cdd7a37282c7 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerBufferFatPointers.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerBufferFatPointers.cpp
@@ -1256,7 +1256,8 @@ PtrParts SplitPtrStructs::visitGetElementPtrInst(GetElementPtrInst &GEP) {
 
   auto [Rsrc, Off] = getPtrParts(Ptr);
   const DataLayout &DL = GEP.getDataLayout();
-  bool InBounds = GEP.isInBounds();
+  bool IsNUW = GEP.hasNoUnsignedWrap();
+  bool IsNUSW = GEP.hasNoUnsignedSignedWrap();
 
   // In order to call emitGEPOffset() and thus not have to reimplement it,
   // we need the GEP result to have ptr addrspace(7) type.
@@ -1280,7 +1281,7 @@ PtrParts SplitPtrStructs::visitGetElementPtrInst(GetElementPtrInst &GEP) {
     NewOff = OffAccum;
   } else {
     NewOff = IRB.CreateAdd(Off, OffAccum, "",
-                           /*hasNUW=*/InBounds && HasNonNegativeOff,
+                           /*hasNUW=*/IsNUW || (IsNUSW && HasNonNegativeOff),
                            /*hasNSW=*/false);
   }
   copyMetadata(NewOff, &GEP);

diff  --git a/llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-pointer-ops.ll b/llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-pointer-ops.ll
index 3191abae34ac60..e7589690cd6702 100644
--- a/llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-pointer-ops.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-pointer-ops.ll
@@ -89,6 +89,53 @@ define ptr addrspace(7) @simple_inbounds_gep(ptr addrspace(7) %ptr, i32 %off) {
   ret ptr addrspace(7) %ret
 }
 
+define ptr addrspace(7) @simple_nuw_gep(ptr addrspace(7) %ptr, i32 %off) {
+; CHECK-LABEL: define { ptr addrspace(8), i32 } @simple_nuw_gep
+; CHECK-SAME: ({ ptr addrspace(8), i32 } [[PTR:%.*]], i32 [[OFF:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:    [[PTR_RSRC:%.*]] = extractvalue { ptr addrspace(8), i32 } [[PTR]], 0
+; CHECK-NEXT:    [[PTR_OFF:%.*]] = extractvalue { ptr addrspace(8), i32 } [[PTR]], 1
+; CHECK-NEXT:    [[RET_IDX:%.*]] = mul nuw i32 [[OFF]], 4
+; CHECK-NEXT:    [[RET:%.*]] = add nuw i32 [[PTR_OFF]], [[RET_IDX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = insertvalue { ptr addrspace(8), i32 } poison, ptr addrspace(8) [[PTR_RSRC]], 0
+; CHECK-NEXT:    [[TMP2:%.*]] = insertvalue { ptr addrspace(8), i32 } [[TMP1]], i32 [[RET]], 1
+; CHECK-NEXT:    ret { ptr addrspace(8), i32 } [[TMP2]]
+;
+  %ret = getelementptr nuw i32, ptr addrspace(7) %ptr, i32 %off
+  ret ptr addrspace(7) %ret
+}
+
+define ptr addrspace(7) @simple_nusw_gep(ptr addrspace(7) %ptr, i32 %off) {
+; CHECK-LABEL: define { ptr addrspace(8), i32 } @simple_nusw_gep
+; CHECK-SAME: ({ ptr addrspace(8), i32 } [[PTR:%.*]], i32 [[OFF:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:    [[PTR_RSRC:%.*]] = extractvalue { ptr addrspace(8), i32 } [[PTR]], 0
+; CHECK-NEXT:    [[PTR_OFF:%.*]] = extractvalue { ptr addrspace(8), i32 } [[PTR]], 1
+; CHECK-NEXT:    [[RET_IDX:%.*]] = mul nsw i32 [[OFF]], 4
+; CHECK-NEXT:    [[RET:%.*]] = add i32 [[PTR_OFF]], [[RET_IDX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = insertvalue { ptr addrspace(8), i32 } poison, ptr addrspace(8) [[PTR_RSRC]], 0
+; CHECK-NEXT:    [[TMP2:%.*]] = insertvalue { ptr addrspace(8), i32 } [[TMP1]], i32 [[RET]], 1
+; CHECK-NEXT:    ret { ptr addrspace(8), i32 } [[TMP2]]
+;
+  %ret = getelementptr nusw i32, ptr addrspace(7) %ptr, i32 %off
+  ret ptr addrspace(7) %ret
+}
+
+define ptr addrspace(7) @nusw_gep_pair(ptr addrspace(7) %ptr, i32 %off) {
+; CHECK-LABEL: define { ptr addrspace(8), i32 } @nusw_gep_pair
+; CHECK-SAME: ({ ptr addrspace(8), i32 } [[PTR:%.*]], i32 [[OFF:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:    [[PTR_RSRC:%.*]] = extractvalue { ptr addrspace(8), i32 } [[PTR]], 0
+; CHECK-NEXT:    [[PTR_OFF:%.*]] = extractvalue { ptr addrspace(8), i32 } [[PTR]], 1
+; CHECK-NEXT:    [[P1_IDX:%.*]] = mul nsw i32 [[OFF]], 4
+; CHECK-NEXT:    [[P1:%.*]] = add i32 [[PTR_OFF]], [[P1_IDX]]
+; CHECK-NEXT:    [[RET:%.*]] = add nuw i32 [[P1]], 16
+; CHECK-NEXT:    [[TMP1:%.*]] = insertvalue { ptr addrspace(8), i32 } poison, ptr addrspace(8) [[PTR_RSRC]], 0
+; CHECK-NEXT:    [[TMP2:%.*]] = insertvalue { ptr addrspace(8), i32 } [[TMP1]], i32 [[RET]], 1
+; CHECK-NEXT:    ret { ptr addrspace(8), i32 } [[TMP2]]
+;
+  %p1 = getelementptr nusw i32, ptr addrspace(7) %ptr, i32 %off
+  %ret = getelementptr nusw i32, ptr addrspace(7) %p1, i32 4
+  ret ptr addrspace(7) %ret
+}
+
 define ptr addrspace(7) @zero_gep(ptr addrspace(7) %ptr) {
 ; CHECK-LABEL: define { ptr addrspace(8), i32 } @zero_gep
 ; CHECK-SAME: ({ ptr addrspace(8), i32 } [[PTR:%.*]]) #[[ATTR0]] {