caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

AMDGPU: Add is.shared/is.private intrinsics to isBoolSGPR (#141804)

Browse Source 
No change in the net output since these ultimately expand to setcc,
but saves a step in the DAG.
This commit is contained in:
Matt Arsenault
2025-05-28 21:38:48 +02:00
committed by GitHub
parent 9ffbc8a4ce
commit d8235affcf
2 changed files with 60 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
View File

@@ -11915,6 +11915,18 @@ bool llvm::isBoolSGPR(SDValue V) {
case ISD::SMULO:
case ISD::UMULO:
return V.getResNo() == 1;
case ISD::INTRINSIC_WO_CHAIN: {
unsigned IntrinsicID = V.getConstantOperandVal(0);
switch (IntrinsicID) {
case Intrinsic::amdgcn_is_shared:
case Intrinsic::amdgcn_is_private:
return true;
default:
return false;
}
return false;
}
}
return false;
}

48
llvm/test/CodeGen/AMDGPU/combine-cond-add-sub.ll
View File

@@ -740,6 +740,54 @@ bb:
ret void
}
define i32 @add_sext_bool_is_shared(ptr %ptr, i32 %y) {
; GCN-LABEL: add_sext_bool_is_shared:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: s_mov_b64 s[4:5], 0xe8
; GCN-NEXT: s_load_dword s4, s[4:5], 0x0
; GCN-NEXT: s_waitcnt lgkmcnt(0)
; GCN-NEXT: v_cmp_eq_u32_e32 vcc, s4, v1
; GCN-NEXT: v_subbrev_u32_e32 v0, vcc, 0, v2, vcc
; GCN-NEXT: s_setpc_b64 s[30:31]
;
; GFX9-LABEL: add_sext_bool_is_shared:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: s_mov_b64 s[4:5], src_shared_base
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, s5, v1
; GFX9-NEXT: v_subbrev_co_u32_e32 v0, vcc, 0, v2, vcc
; GFX9-NEXT: s_setpc_b64 s[30:31]
%is.shared = call i1 @llvm.amdgcn.is.shared(ptr %ptr)
%sext = sext i1 %is.shared to i32
%add = add i32 %sext, %y
ret i32 %add
}
define i32 @add_sext_bool_is_private(ptr %ptr, i32 %y) {
; GCN-LABEL: add_sext_bool_is_private:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: s_mov_b64 s[4:5], 0xe4
; GCN-NEXT: s_load_dword s4, s[4:5], 0x0
; GCN-NEXT: s_waitcnt lgkmcnt(0)
; GCN-NEXT: v_cmp_eq_u32_e32 vcc, s4, v1
; GCN-NEXT: v_subbrev_u32_e32 v0, vcc, 0, v2, vcc
; GCN-NEXT: s_setpc_b64 s[30:31]
;
; GFX9-LABEL: add_sext_bool_is_private:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: s_mov_b64 s[4:5], src_private_base
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, s5, v1
; GFX9-NEXT: v_subbrev_co_u32_e32 v0, vcc, 0, v2, vcc
; GFX9-NEXT: s_setpc_b64 s[30:31]
%is.private = call i1 @llvm.amdgcn.is.private(ptr %ptr)
%sext = sext i1 %is.private to i32
%add = add i32 %sext, %y
ret i32 %add
}
declare i1 @llvm.amdgcn.class.f32(float, i32) #0
declare i32 @llvm.amdgcn.workitem.id.x() #0