AMDGPU: Fix inst-selection of large scratch offsets with sgpr base

petar-avramovic · petar-avramovic · commit dcec93029eb0 · 2024-09-27T14:45:19.000+02:00
Use i32 for offset instead of i16, this way it does not get interpreted
as negative 16 bit offset.
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
@@ -1911,7 +1911,7 @@ bool AMDGPUDAGToDAGISel::SelectScratchSAddr(SDNode *Parent, SDValue Addr,
                     0);
   }
 
-  Offset = CurDAG->getTargetConstant(COffsetVal, DL, MVT::i16);
+  Offset = CurDAG->getTargetConstant(COffsetVal, DL, MVT::i32);
 
   return true;
 }
diff --git a/llvm/test/CodeGen/AMDGPU/flat-scratch.ll b/llvm/test/CodeGen/AMDGPU/flat-scratch.ll
@@ -4926,7 +4926,7 @@ define amdgpu_gs void @sgpr_base_large_offset(ptr addrspace(1) %out, ptr addrspa
 ;
 ; GFX12-LABEL: sgpr_base_large_offset:
 ; GFX12:       ; %bb.0: ; %entry
-; GFX12-NEXT:    scratch_load_b32 v2, off, s0 offset:-24
+; GFX12-NEXT:    scratch_load_b32 v2, off, s0 offset:65512
 ; GFX12-NEXT:    s_wait_loadcnt 0x0
 ; GFX12-NEXT:    global_store_b32 v[0:1], v2, off
 ; GFX12-NEXT:    s_nop 0
@@ -4985,7 +4985,7 @@ define amdgpu_gs void @sgpr_base_large_offset(ptr addrspace(1) %out, ptr addrspa
 ;
 ; GFX12-PAL-LABEL: sgpr_base_large_offset:
 ; GFX12-PAL:       ; %bb.0: ; %entry
-; GFX12-PAL-NEXT:    scratch_load_b32 v2, off, s0 offset:-24
+; GFX12-PAL-NEXT:    scratch_load_b32 v2, off, s0 offset:65512
 ; GFX12-PAL-NEXT:    s_wait_loadcnt 0x0
 ; GFX12-PAL-NEXT:    global_store_b32 v[0:1], v2, off
 ; GFX12-PAL-NEXT:    s_nop 0

Original file line number	Diff line number	Diff line change
`@@ -1911,7 +1911,7 @@ bool AMDGPUDAGToDAGISel::SelectScratchSAddr(SDNode *Parent, SDValue Addr,`
`1911`	`1911`	`0);`
`1912`	`1912`	`}`
`1913`	`1913`
`1914`		`- Offset = CurDAG->getTargetConstant(COffsetVal, DL, MVT::i16);`
	`1914`	`+ Offset = CurDAG->getTargetConstant(COffsetVal, DL, MVT::i32);`
`1915`	`1915`
`1916`	`1916`	`return true;`
`1917`	`1917`	`}`