[llvm] 2759cfa - [AMDGPU] Remove unnecessary add instructions in ctlz.i8 (#77615)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Jan 19 02:16:50 PST 2024
Author: Leon Clark
Date: 2024-01-19T10:16:46Z
New Revision: 2759cfa0c35478b5a3bc1e51a1ed817d1b1dc39f
URL: https://github.com/llvm/llvm-project/commit/2759cfa0c35478b5a3bc1e51a1ed817d1b1dc39f
DIFF: https://github.com/llvm/llvm-project/commit/2759cfa0c35478b5a3bc1e51a1ed817d1b1dc39f.diff
LOG: [AMDGPU] Remove unnecessary add instructions in ctlz.i8 (#77615)
Add custom lowering for ctlz.i8 to avoid multiple add/sub operations.
---------
Co-authored-by: Leon Clark <leoclark at amd.com>
Co-authored-by: Matt Arsenault <Matthew.Arsenault at amd.com>
Added:
Modified:
llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
llvm/test/CodeGen/AMDGPU/ctlz.ll
llvm/test/CodeGen/AMDGPU/ctlz_zero_undef.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
index 6f26e0e82ece11..55d95154c75878 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -446,6 +446,9 @@ AMDGPUTargetLowering::AMDGPUTargetLowering(const TargetMachine &TM,
{ISD::CTTZ, ISD::CTTZ_ZERO_UNDEF, ISD::CTLZ, ISD::CTLZ_ZERO_UNDEF},
MVT::i64, Custom);
+ for (auto VT : {MVT::i8, MVT::i16})
+ setOperationAction({ISD::CTLZ, ISD::CTLZ_ZERO_UNDEF}, VT, Custom);
+
static const MVT::SimpleValueType VectorIntTypes[] = {
MVT::v2i32, MVT::v3i32, MVT::v4i32, MVT::v5i32, MVT::v6i32, MVT::v7i32,
MVT::v9i32, MVT::v10i32, MVT::v11i32, MVT::v12i32};
@@ -1398,6 +1401,11 @@ void AMDGPUTargetLowering::ReplaceNodeResults(SDNode *N,
if (SDValue Lowered = lowerFEXP(SDValue(N, 0), DAG))
Results.push_back(Lowered);
return;
+ case ISD::CTLZ:
+ case ISD::CTLZ_ZERO_UNDEF:
+ if (auto Lowered = lowerCTLZResults(SDValue(N, 0u), DAG))
+ Results.push_back(Lowered);
+ return;
default:
return;
}
@@ -3063,6 +3071,26 @@ static bool isCttzOpc(unsigned Opc) {
return Opc == ISD::CTTZ || Opc == ISD::CTTZ_ZERO_UNDEF;
}
+SDValue AMDGPUTargetLowering::lowerCTLZResults(SDValue Op,
+ SelectionDAG &DAG) const {
+ auto SL = SDLoc(Op);
+ auto Arg = Op.getOperand(0u);
+ auto ResultVT = Op.getValueType();
+
+ if (ResultVT != MVT::i8 && ResultVT != MVT::i16)
+ return {};
+
+ assert(isCtlzOpc(Op.getOpcode()));
+ assert(ResultVT == Arg.getValueType());
+
+ auto const LeadingZeroes = 32u - ResultVT.getFixedSizeInBits();
+ auto NewOp = DAG.getNode(ISD::ZERO_EXTEND, SL, MVT::i32, Arg);
+ auto ShiftVal = DAG.getConstant(LeadingZeroes, SL, MVT::i32);
+ NewOp = DAG.getNode(ISD::SHL, SL, MVT::i32, NewOp, ShiftVal);
+ NewOp = DAG.getNode(Op.getOpcode(), SL, MVT::i32, NewOp);
+ return DAG.getNode(ISD::TRUNCATE, SL, ResultVT, NewOp);
+}
+
SDValue AMDGPUTargetLowering::LowerCTLZ_CTTZ(SDValue Op, SelectionDAG &DAG) const {
SDLoc SL(Op);
SDValue Src = Op.getOperand(0);
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
index db8dc922c974ce..f10a357125e562 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
@@ -84,6 +84,8 @@ class AMDGPUTargetLowering : public TargetLowering {
SDNodeFlags Flags) const;
SDValue lowerFEXP(SDValue Op, SelectionDAG &DAG) const;
+ SDValue lowerCTLZResults(SDValue Op, SelectionDAG &DAG) const;
+
SDValue LowerCTLZ_CTTZ(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerINT_TO_FP32(SDValue Op, SelectionDAG &DAG, bool Signed) const;
diff --git a/llvm/test/CodeGen/AMDGPU/ctlz.ll b/llvm/test/CodeGen/AMDGPU/ctlz.ll
index b426a15669417a..9307d8952293b1 100644
--- a/llvm/test/CodeGen/AMDGPU/ctlz.ll
+++ b/llvm/test/CodeGen/AMDGPU/ctlz.ll
@@ -492,9 +492,9 @@ define amdgpu_kernel void @v_ctlz_i8(ptr addrspace(1) noalias %out, ptr addrspac
; SI-NEXT: s_mov_b32 s4, s0
; SI-NEXT: s_mov_b32 s5, s1
; SI-NEXT: s_waitcnt vmcnt(0)
+; SI-NEXT: v_lshlrev_b32_e32 v0, 24, v0
; SI-NEXT: v_ffbh_u32_e32 v0, v0
; SI-NEXT: v_min_u32_e32 v0, 32, v0
-; SI-NEXT: v_subrev_i32_e32 v0, vcc, 24, v0
; SI-NEXT: buffer_store_byte v0, off, s[4:7], 0
; SI-NEXT: s_endpgm
;
@@ -512,10 +512,9 @@ define amdgpu_kernel void @v_ctlz_i8(ptr addrspace(1) noalias %out, ptr addrspac
; VI-NEXT: s_mov_b32 s4, s0
; VI-NEXT: s_mov_b32 s5, s1
; VI-NEXT: s_waitcnt vmcnt(0)
+; VI-NEXT: v_lshlrev_b32_e32 v0, 24, v0
; VI-NEXT: v_ffbh_u32_e32 v0, v0
; VI-NEXT: v_min_u32_e32 v0, 32, v0
-; VI-NEXT: v_add_u32_e32 v0, vcc, -16, v0
-; VI-NEXT: v_add_u16_e32 v0, -8, v0
; VI-NEXT: buffer_store_byte v0, off, s[4:7], 0
; VI-NEXT: s_endpgm
;
@@ -523,7 +522,7 @@ define amdgpu_kernel void @v_ctlz_i8(ptr addrspace(1) noalias %out, ptr addrspac
; EG: ; %bb.0:
; EG-NEXT: ALU 0, @8, KC0[CB0:0-32], KC1[]
; EG-NEXT: TEX 0 @6
-; EG-NEXT: ALU 15, @9, KC0[CB0:0-32], KC1[]
+; EG-NEXT: ALU 16, @9, KC0[CB0:0-32], KC1[]
; EG-NEXT: MEM_RAT MSKOR T0.XW, T1.X
; EG-NEXT: CF_END
; EG-NEXT: PAD
@@ -532,14 +531,15 @@ define amdgpu_kernel void @v_ctlz_i8(ptr addrspace(1) noalias %out, ptr addrspac
; EG-NEXT: ALU clause starting at 8:
; EG-NEXT: MOV * T0.X, KC0[2].Z,
; EG-NEXT: ALU clause starting at 9:
-; EG-NEXT: FFBH_UINT * T0.W, T0.X,
-; EG-NEXT: CNDE_INT T0.W, T0.X, literal.x, PV.W,
-; EG-NEXT: AND_INT * T1.W, KC0[2].Y, literal.y,
-; EG-NEXT: 32(4.484155e-44), 3(4.203895e-45)
-; EG-NEXT: ADD_INT * T0.W, PV.W, literal.x,
-; EG-NEXT: -24(nan), 0(0.000000e+00)
+; EG-NEXT: LSHL * T0.W, T0.X, literal.x,
+; EG-NEXT: 24(3.363116e-44), 0(0.000000e+00)
+; EG-NEXT: FFBH_UINT T1.W, PV.W,
+; EG-NEXT: AND_INT * T2.W, KC0[2].Y, literal.x,
+; EG-NEXT: 3(4.203895e-45), 0(0.000000e+00)
+; EG-NEXT: CNDE_INT * T0.W, T0.W, literal.x, PV.W,
+; EG-NEXT: 32(4.484155e-44), 0(0.000000e+00)
; EG-NEXT: AND_INT T0.W, PV.W, literal.x,
-; EG-NEXT: LSHL * T1.W, T1.W, literal.y,
+; EG-NEXT: LSHL * T1.W, T2.W, literal.y,
; EG-NEXT: 255(3.573311e-43), 3(4.203895e-45)
; EG-NEXT: LSHL T0.X, PV.W, PS,
; EG-NEXT: LSHL * T0.W, literal.x, PS,
@@ -556,10 +556,9 @@ define amdgpu_kernel void @v_ctlz_i8(ptr addrspace(1) noalias %out, ptr addrspac
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-NEXT: global_load_ubyte v1, v0, s[2:3]
; GFX10-NEXT: s_waitcnt vmcnt(0)
+; GFX10-NEXT: v_lshlrev_b32_e32 v1, 24, v1
; GFX10-NEXT: v_ffbh_u32_e32 v1, v1
; GFX10-NEXT: v_min_u32_e32 v1, 32, v1
-; GFX10-NEXT: v_add_nc_u32_e32 v1, -16, v1
-; GFX10-NEXT: v_add_nc_u16 v1, v1, -8
; GFX10-NEXT: global_store_byte v0, v1, s[0:1]
; GFX10-NEXT: s_endpgm
;
@@ -583,12 +582,10 @@ define amdgpu_kernel void @v_ctlz_i8(ptr addrspace(1) noalias %out, ptr addrspac
; GFX11-NEXT: s_waitcnt lgkmcnt(0)
; GFX11-NEXT: global_load_u8 v1, v0, s[2:3]
; GFX11-NEXT: s_waitcnt vmcnt(0)
-; GFX11-NEXT: v_clz_i32_u32_e32 v1, v1
+; GFX11-NEXT: v_lshlrev_b32_e32 v1, 24, v1
; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-NEXT: v_clz_i32_u32_e32 v1, v1
; GFX11-NEXT: v_min_u32_e32 v1, 32, v1
-; GFX11-NEXT: v_add_nc_u32_e32 v1, -16, v1
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
-; GFX11-NEXT: v_add_nc_u16 v1, v1, -8
; GFX11-NEXT: global_store_b8 v0, v1, s[0:1]
; GFX11-NEXT: s_nop 0
; GFX11-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
diff --git a/llvm/test/CodeGen/AMDGPU/ctlz_zero_undef.ll b/llvm/test/CodeGen/AMDGPU/ctlz_zero_undef.ll
index 5be8882764ce78..2830e5258e92b2 100644
--- a/llvm/test/CodeGen/AMDGPU/ctlz_zero_undef.ll
+++ b/llvm/test/CodeGen/AMDGPU/ctlz_zero_undef.ll
@@ -314,9 +314,8 @@ define amdgpu_kernel void @s_ctlz_zero_undef_i8_with_select(ptr addrspace(1) noa
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_waitcnt lgkmcnt(0)
-; SI-NEXT: s_and_b32 s2, s2, 0xff
-; SI-NEXT: s_flbit_i32_b32 s2, s2
-; SI-NEXT: s_sub_i32 s4, s2, 24
+; SI-NEXT: s_lshl_b32 s2, s2, 24
+; SI-NEXT: s_flbit_i32_b32 s4, s2
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: v_mov_b32_e32 v0, s4
; SI-NEXT: buffer_store_byte v0, off, s[0:3], 0
@@ -327,12 +326,11 @@ define amdgpu_kernel void @s_ctlz_zero_undef_i8_with_select(ptr addrspace(1) noa
; VI-NEXT: s_load_dword s2, s[0:1], 0x2c
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: s_waitcnt lgkmcnt(0)
-; VI-NEXT: s_and_b32 s2, s2, 0xff
+; VI-NEXT: s_lshl_b32 s2, s2, 24
; VI-NEXT: s_flbit_i32_b32 s2, s2
-; VI-NEXT: s_add_i32 s2, s2, -16
; VI-NEXT: v_mov_b32_e32 v0, s0
-; VI-NEXT: v_add_u16_e64 v2, s2, -8
; VI-NEXT: v_mov_b32_e32 v1, s1
+; VI-NEXT: v_mov_b32_e32 v2, s2
; VI-NEXT: flat_store_byte v[0:1], v2
; VI-NEXT: s_endpgm
;
@@ -349,13 +347,13 @@ define amdgpu_kernel void @s_ctlz_zero_undef_i8_with_select(ptr addrspace(1) noa
; EG-NEXT: ALU clause starting at 8:
; EG-NEXT: MOV * T0.X, 0.0,
; EG-NEXT: ALU clause starting at 9:
-; EG-NEXT: FFBH_UINT T0.W, T0.X,
+; EG-NEXT: LSHL * T0.W, T0.X, literal.x,
+; EG-NEXT: 24(3.363116e-44), 0(0.000000e+00)
+; EG-NEXT: FFBH_UINT T0.W, PV.W,
; EG-NEXT: AND_INT * T1.W, KC0[2].Y, literal.x,
; EG-NEXT: 3(4.203895e-45), 0(0.000000e+00)
-; EG-NEXT: ADD_INT * T0.W, PV.W, literal.x,
-; EG-NEXT: -24(nan), 0(0.000000e+00)
; EG-NEXT: AND_INT T0.W, PV.W, literal.x,
-; EG-NEXT: LSHL * T1.W, T1.W, literal.y,
+; EG-NEXT: LSHL * T1.W, PS, literal.y,
; EG-NEXT: 255(3.573311e-43), 3(4.203895e-45)
; EG-NEXT: LSHL T0.X, PV.W, PS,
; EG-NEXT: LSHL * T0.W, literal.x, PS,
@@ -391,9 +389,8 @@ define amdgpu_kernel void @s_ctlz_zero_undef_i16_with_select(ptr addrspace(1) no
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_waitcnt lgkmcnt(0)
-; SI-NEXT: s_and_b32 s2, s2, 0xffff
-; SI-NEXT: s_flbit_i32_b32 s2, s2
-; SI-NEXT: s_add_i32 s4, s2, -16
+; SI-NEXT: s_lshl_b32 s2, s2, 16
+; SI-NEXT: s_flbit_i32_b32 s4, s2
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: v_mov_b32_e32 v0, s4
; SI-NEXT: buffer_store_short v0, off, s[0:3], 0
@@ -426,13 +423,13 @@ define amdgpu_kernel void @s_ctlz_zero_undef_i16_with_select(ptr addrspace(1) no
; EG-NEXT: ALU clause starting at 8:
; EG-NEXT: MOV * T0.X, 0.0,
; EG-NEXT: ALU clause starting at 9:
-; EG-NEXT: FFBH_UINT T0.W, T0.X,
+; EG-NEXT: LSHL * T0.W, T0.X, literal.x,
+; EG-NEXT: 16(2.242078e-44), 0(0.000000e+00)
+; EG-NEXT: FFBH_UINT T0.W, PV.W,
; EG-NEXT: AND_INT * T1.W, KC0[2].Y, literal.x,
; EG-NEXT: 3(4.203895e-45), 0(0.000000e+00)
-; EG-NEXT: ADD_INT * T0.W, PV.W, literal.x,
-; EG-NEXT: -16(nan), 0(0.000000e+00)
; EG-NEXT: AND_INT T0.W, PV.W, literal.x,
-; EG-NEXT: LSHL * T1.W, T1.W, literal.y,
+; EG-NEXT: LSHL * T1.W, PS, literal.y,
; EG-NEXT: 65535(9.183409e-41), 3(4.203895e-45)
; EG-NEXT: LSHL T0.X, PV.W, PS,
; EG-NEXT: LSHL * T0.W, literal.x, PS,
@@ -590,8 +587,8 @@ define amdgpu_kernel void @v_ctlz_zero_undef_i8_with_select(ptr addrspace(1) noa
; SI-NEXT: s_mov_b32 s4, s0
; SI-NEXT: s_mov_b32 s5, s1
; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: v_ffbh_u32_e32 v1, v0
-; SI-NEXT: v_subrev_i32_e32 v1, vcc, 24, v1
+; SI-NEXT: v_lshlrev_b32_e32 v1, 24, v0
+; SI-NEXT: v_ffbh_u32_e32 v1, v1
; SI-NEXT: v_cmp_ne_u32_e32 vcc, 0, v0
; SI-NEXT: v_cndmask_b32_e32 v0, 32, v1, vcc
; SI-NEXT: buffer_store_byte v0, off, s[4:7], 0
@@ -605,9 +602,8 @@ define amdgpu_kernel void @v_ctlz_zero_undef_i8_with_select(ptr addrspace(1) noa
; VI-NEXT: v_mov_b32_e32 v1, s3
; VI-NEXT: flat_load_ubyte v0, v[0:1]
; VI-NEXT: s_waitcnt vmcnt(0)
-; VI-NEXT: v_ffbh_u32_sdwa v1, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0
-; VI-NEXT: v_add_u32_e32 v1, vcc, -16, v1
-; VI-NEXT: v_add_u16_e32 v1, -8, v1
+; VI-NEXT: v_lshlrev_b32_e32 v1, 24, v0
+; VI-NEXT: v_ffbh_u32_e32 v1, v1
; VI-NEXT: v_cmp_ne_u16_e32 vcc, 0, v0
; VI-NEXT: v_cndmask_b32_e32 v2, 32, v1, vcc
; VI-NEXT: v_mov_b32_e32 v0, s0
@@ -619,7 +615,7 @@ define amdgpu_kernel void @v_ctlz_zero_undef_i8_with_select(ptr addrspace(1) noa
; EG: ; %bb.0:
; EG-NEXT: ALU 0, @8, KC0[CB0:0-32], KC1[]
; EG-NEXT: TEX 0 @6
-; EG-NEXT: ALU 15, @9, KC0[CB0:0-32], KC1[]
+; EG-NEXT: ALU 16, @9, KC0[CB0:0-32], KC1[]
; EG-NEXT: MEM_RAT MSKOR T0.XW, T1.X
; EG-NEXT: CF_END
; EG-NEXT: PAD
@@ -628,10 +624,11 @@ define amdgpu_kernel void @v_ctlz_zero_undef_i8_with_select(ptr addrspace(1) noa
; EG-NEXT: ALU clause starting at 8:
; EG-NEXT: MOV * T0.X, KC0[2].Z,
; EG-NEXT: ALU clause starting at 9:
-; EG-NEXT: FFBH_UINT * T0.W, T0.X,
-; EG-NEXT: ADD_INT T0.W, PV.W, literal.x,
-; EG-NEXT: AND_INT * T1.W, KC0[2].Y, literal.y,
-; EG-NEXT: -24(nan), 3(4.203895e-45)
+; EG-NEXT: LSHL * T0.W, T0.X, literal.x,
+; EG-NEXT: 24(3.363116e-44), 0(0.000000e+00)
+; EG-NEXT: FFBH_UINT T0.W, PV.W,
+; EG-NEXT: AND_INT * T1.W, KC0[2].Y, literal.x,
+; EG-NEXT: 3(4.203895e-45), 0(0.000000e+00)
; EG-NEXT: CNDE_INT * T0.W, T0.X, literal.x, PV.W,
; EG-NEXT: 32(4.484155e-44), 0(0.000000e+00)
; EG-NEXT: AND_INT T0.W, PV.W, literal.x,
@@ -686,8 +683,8 @@ define amdgpu_kernel void @v_ctlz_zero_undef_i16_with_select(ptr addrspace(1) no
; SI-NEXT: v_lshlrev_b32_e32 v0, 8, v0
; SI-NEXT: s_waitcnt vmcnt(0)
; SI-NEXT: v_or_b32_e32 v0, v0, v1
-; SI-NEXT: v_ffbh_u32_e32 v1, v0
-; SI-NEXT: v_add_i32_e32 v1, vcc, -16, v1
+; SI-NEXT: v_lshlrev_b32_e32 v1, 16, v0
+; SI-NEXT: v_ffbh_u32_e32 v1, v1
; SI-NEXT: v_cmp_ne_u32_e32 vcc, 0, v0
; SI-NEXT: v_cndmask_b32_e32 v0, 32, v1, vcc
; SI-NEXT: buffer_store_short v0, off, s[4:7], 0
@@ -722,7 +719,7 @@ define amdgpu_kernel void @v_ctlz_zero_undef_i16_with_select(ptr addrspace(1) no
; EG: ; %bb.0:
; EG-NEXT: ALU 0, @8, KC0[CB0:0-32], KC1[]
; EG-NEXT: TEX 0 @6
-; EG-NEXT: ALU 15, @9, KC0[CB0:0-32], KC1[]
+; EG-NEXT: ALU 16, @9, KC0[CB0:0-32], KC1[]
; EG-NEXT: MEM_RAT MSKOR T0.XW, T1.X
; EG-NEXT: CF_END
; EG-NEXT: PAD
@@ -731,10 +728,11 @@ define amdgpu_kernel void @v_ctlz_zero_undef_i16_with_select(ptr addrspace(1) no
; EG-NEXT: ALU clause starting at 8:
; EG-NEXT: MOV * T0.X, KC0[2].Z,
; EG-NEXT: ALU clause starting at 9:
-; EG-NEXT: FFBH_UINT * T0.W, T0.X,
-; EG-NEXT: ADD_INT T0.W, PV.W, literal.x,
-; EG-NEXT: AND_INT * T1.W, KC0[2].Y, literal.y,
-; EG-NEXT: -16(nan), 3(4.203895e-45)
+; EG-NEXT: LSHL * T0.W, T0.X, literal.x,
+; EG-NEXT: 16(2.242078e-44), 0(0.000000e+00)
+; EG-NEXT: FFBH_UINT T0.W, PV.W,
+; EG-NEXT: AND_INT * T1.W, KC0[2].Y, literal.x,
+; EG-NEXT: 3(4.203895e-45), 0(0.000000e+00)
; EG-NEXT: CNDE_INT * T0.W, T0.X, literal.x, PV.W,
; EG-NEXT: 32(4.484155e-44), 0(0.000000e+00)
; EG-NEXT: AND_INT T0.W, PV.W, literal.x,
@@ -1103,8 +1101,8 @@ define amdgpu_kernel void @v_ctlz_zero_undef_i8(ptr addrspace(1) noalias %out, p
; SI-NEXT: s_mov_b32 s4, s0
; SI-NEXT: s_mov_b32 s5, s1
; SI-NEXT: s_waitcnt vmcnt(0)
+; SI-NEXT: v_lshlrev_b32_e32 v0, 24, v0
; SI-NEXT: v_ffbh_u32_e32 v0, v0
-; SI-NEXT: v_subrev_i32_e32 v0, vcc, 24, v0
; SI-NEXT: buffer_store_byte v0, off, s[4:7], 0
; SI-NEXT: s_endpgm
;
@@ -1117,9 +1115,8 @@ define amdgpu_kernel void @v_ctlz_zero_undef_i8(ptr addrspace(1) noalias %out, p
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
; VI-NEXT: flat_load_ubyte v0, v[0:1]
; VI-NEXT: s_waitcnt vmcnt(0)
-; VI-NEXT: v_ffbh_u32_e32 v0, v0
-; VI-NEXT: v_add_u32_e32 v0, vcc, -16, v0
-; VI-NEXT: v_add_u16_e32 v2, -8, v0
+; VI-NEXT: v_lshlrev_b32_e32 v0, 24, v0
+; VI-NEXT: v_ffbh_u32_e32 v2, v0
; VI-NEXT: v_mov_b32_e32 v0, s0
; VI-NEXT: v_mov_b32_e32 v1, s1
; VI-NEXT: flat_store_byte v[0:1], v2
@@ -1138,13 +1135,13 @@ define amdgpu_kernel void @v_ctlz_zero_undef_i8(ptr addrspace(1) noalias %out, p
; EG-NEXT: ALU clause starting at 8:
; EG-NEXT: ADD_INT * T0.X, KC0[2].Z, T0.X,
; EG-NEXT: ALU clause starting at 9:
-; EG-NEXT: FFBH_UINT T0.W, T0.X,
+; EG-NEXT: LSHL * T0.W, T0.X, literal.x,
+; EG-NEXT: 24(3.363116e-44), 0(0.000000e+00)
+; EG-NEXT: FFBH_UINT T0.W, PV.W,
; EG-NEXT: AND_INT * T1.W, KC0[2].Y, literal.x,
; EG-NEXT: 3(4.203895e-45), 0(0.000000e+00)
-; EG-NEXT: ADD_INT * T0.W, PV.W, literal.x,
-; EG-NEXT: -24(nan), 0(0.000000e+00)
; EG-NEXT: AND_INT T0.W, PV.W, literal.x,
-; EG-NEXT: LSHL * T1.W, T1.W, literal.y,
+; EG-NEXT: LSHL * T1.W, PS, literal.y,
; EG-NEXT: 255(3.573311e-43), 3(4.203895e-45)
; EG-NEXT: LSHL T0.X, PV.W, PS,
; EG-NEXT: LSHL * T0.W, literal.x, PS,
More information about the llvm-commits
mailing list