Skip to content

[AMDGPU] - Add constant folding for s_bitreplicate #72366

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Nov 16, 2023
Merged

[AMDGPU] - Add constant folding for s_bitreplicate #72366

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
44b4463
[AMDGPU] - Add constant folding for s_bitreplicate
OutOfCache Nov 14, 2023
22a1189
fixup! [AMDGPU] - Add constant folding for s_bitreplicate
OutOfCache Nov 15, 2023
8c69df4
fixup! [AMDGPU] - Add constant folding for s_bitreplicate
OutOfCache Nov 15, 2023
a6e5a61
fixup! [AMDGPU] - Add constant folding for s_bitreplicate
OutOfCache Nov 15, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions llvm/lib/Analysis/ConstantFolding.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1533,6 +1533,7 @@ bool llvm::canConstantFoldCallTo(const CallBase *Call, const Function *F) {
case Intrinsic::amdgcn_perm:
case Intrinsic::amdgcn_wave_reduce_umin:
case Intrinsic::amdgcn_wave_reduce_umax:
case Intrinsic::amdgcn_s_bitreplicate:
case Intrinsic::arm_mve_vctp8:
case Intrinsic::arm_mve_vctp16:
case Intrinsic::arm_mve_vctp32:
Expand Down Expand Up @@ -2422,6 +2423,18 @@ static Constant *ConstantFoldScalarCall1(StringRef Name,

return ConstantFP::get(Ty->getContext(), Val);
}

case Intrinsic::amdgcn_s_bitreplicate: {
uint64_t Val = Op->getZExtValue();
Val = (Val & 0x000000000000FFFFULL) | (Val & 0x00000000FFFF0000ULL) << 16;
Val = (Val & 0x000000FF000000FFULL) | (Val & 0x0000FF000000FF00ULL) << 8;
Val = (Val & 0x000F000F000F000FULL) | (Val & 0x00F000F000F000F0ULL) << 4;
Val = (Val & 0x0303030303030303ULL) | (Val & 0x0C0C0C0C0C0C0C0CULL) << 2;
Val = (Val & 0x1111111111111111ULL) | (Val & 0x2222222222222222ULL) << 1;
Val = Val | Val << 1;
return ConstantInt::get(Ty, Val);
}

default:
return nullptr;
}
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/AMDGPU/llvm.amdgcn.bitreplicate.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,8 +8,8 @@ define i64 @test_s_bitreplicate_constant() {
; GFX11-LABEL: test_s_bitreplicate_constant:
; GFX11: ; %bb.0: ; %entry
; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX11-NEXT: s_bitreplicate_b64_b32 s[0:1], 0x85fe3a92
; GFX11-NEXT: v_dual_mov_b32 v0, s0 :: v_dual_mov_b32 v1, s1
; GFX11-NEXT: v_mov_b32_e32 v0, 0xfccc30c
; GFX11-NEXT: v_mov_b32_e32 v1, 0xc033fffc
; GFX11-NEXT: s_setpc_b64 s[30:31]
entry:
%br = call i64 @llvm.amdgcn.s.bitreplicate(i32 u0x85FE3A92)
Expand Down