forked from OSchip/llvm-project
AMDGPU: Add macro fusion schedule DAG mutation
Try to increase opportunities to shrink vcc uses. llvm-svn: 307313
This commit is contained in:
Matt Arsenault
parent
a81198d82d
commit
9aa45f047f
|
|
@ -0,0 +1,64 @@
|
|||
//===--- AMDGPUMacroFusion.cpp - AMDGPU Macro Fusion ----------------------===//
|
||||
//
|
||||
// The LLVM Compiler Infrastructure
|
||||
//
|
||||
// This file is distributed under the University of Illinois Open Source
|
||||
// License. See LICENSE.TXT for details.
|
||||
//
|
||||
//===----------------------------------------------------------------------===//
|
||||
//
|
||||
/// \file This file contains the AMDGPU implementation of the DAG scheduling
|
||||
/// mutation to pair instructions back to back.
|
||||
//
|
||||
//===----------------------------------------------------------------------===//
|
||||
|
||||
#include "AMDGPUMacroFusion.h"
|
||||
#include "AMDGPUSubtarget.h"
|
||||
#include "SIInstrInfo.h"
|
||||
|
||||
#include "llvm/CodeGen/MacroFusion.h"
|
||||
|
||||
using namespace llvm;
|
||||
|
||||
namespace {
|
||||
|
||||
/// \brief Check if the instr pair, FirstMI and SecondMI, should be fused
|
||||
/// together. Given SecondMI, when FirstMI is unspecified, then check if
|
||||
/// SecondMI may be part of a fused pair at all.
|
||||
static bool shouldScheduleAdjacent(const TargetInstrInfo &TII_,
|
||||
const TargetSubtargetInfo &TSI,
|
||||
const MachineInstr *FirstMI,
|
||||
const MachineInstr &SecondMI) {
|
||||
const SIInstrInfo &TII = static_cast<const SIInstrInfo&>(TII_);
|
||||
|
||||
switch (SecondMI.getOpcode()) {
|
||||
case AMDGPU::V_ADDC_U32_e64:
|
||||
case AMDGPU::V_SUBB_U32_e64:
|
||||
case AMDGPU::V_CNDMASK_B32_e64: {
|
||||
// Try to cluster defs of condition registers to their uses. This improves
|
||||
// the chance VCC will be available which will allow shrinking to VOP2
|
||||
// encodings.
|
||||
if (!FirstMI)
|
||||
return true;
|
||||
|
||||
const MachineOperand *Src2 = TII.getNamedOperand(SecondMI,
|
||||
AMDGPU::OpName::src2);
|
||||
return FirstMI->definesRegister(Src2->getReg());
|
||||
}
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
} // end namespace
|
||||
|
||||
|
||||
namespace llvm {
|
||||
|
||||
std::unique_ptr<ScheduleDAGMutation> createAMDGPUMacroFusionDAGMutation () {
|
||||
return createMacroFusionDAGMutation(shouldScheduleAdjacent);
|
||||
}
|
||||
|
||||
} // end namespace llvm
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
//===- AMDGPUMacroFusion.h - AMDGPU Macro Fusion ----------------*- C++ -*-===//
|
||||
//
|
||||
// The LLVM Compiler Infrastructure
|
||||
//
|
||||
// This file is distributed under the University of Illinois Open Source
|
||||
// License. See LICENSE.TXT for details.
|
||||
//
|
||||
//===----------------------------------------------------------------------===//
|
||||
|
||||
#include "llvm/CodeGen/MachineScheduler.h"
|
||||
|
||||
namespace llvm {
|
||||
|
||||
/// Note that you have to add:
|
||||
/// DAG.addMutation(createAMDGPUMacroFusionDAGMutation());
|
||||
/// to AMDGPUPassConfig::createMachineScheduler() to have an effect.
|
||||
std::unique_ptr<ScheduleDAGMutation> createAMDGPUMacroFusionDAGMutation();
|
||||
|
||||
} // llvm
|
||||
|
|
@ -19,6 +19,7 @@
|
|||
#include "AMDGPUCallLowering.h"
|
||||
#include "AMDGPUInstructionSelector.h"
|
||||
#include "AMDGPULegalizerInfo.h"
|
||||
#include "AMDGPUMacroFusion.h"
|
||||
#include "AMDGPUTargetObjectFile.h"
|
||||
#include "AMDGPUTargetTransformInfo.h"
|
||||
#include "GCNIterativeScheduler.h"
|
||||
|
|
@ -173,6 +174,7 @@ createGCNMaxOccupancyMachineScheduler(MachineSchedContext *C) {
|
|||
new GCNScheduleDAGMILive(C, make_unique<GCNMaxOccupancySchedStrategy>(C));
|
||||
DAG->addMutation(createLoadClusterDAGMutation(DAG->TII, DAG->TRI));
|
||||
DAG->addMutation(createStoreClusterDAGMutation(DAG->TII, DAG->TRI));
|
||||
DAG->addMutation(createAMDGPUMacroFusionDAGMutation());
|
||||
return DAG;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -47,6 +47,7 @@ add_llvm_target(AMDGPUCodeGen
|
|||
AMDGPUIntrinsicInfo.cpp
|
||||
AMDGPUISelDAGToDAG.cpp
|
||||
AMDGPULowerIntrinsics.cpp
|
||||
AMDGPUMacroFusion.cpp
|
||||
AMDGPUMCInstLower.cpp
|
||||
AMDGPUMachineCFGStructurizer.cpp
|
||||
AMDGPUMachineFunction.cpp
|
||||
|
|
|
|||
|
|
@ -10,20 +10,22 @@
|
|||
; CI-DAG: s_load_dword [[PTR:s[0-9]+]], s[6:7], 0x0{{$}}
|
||||
; CI-DAG: s_load_dword [[APERTURE:s[0-9]+]], s[4:5], 0x10{{$}}
|
||||
; CI-DAG: v_mov_b32_e32 [[VAPERTURE:v[0-9]+]], [[APERTURE]]
|
||||
; CI-DAG: v_cmp_ne_u32_e64 vcc, [[PTR]], -1
|
||||
; CI-DAG: v_cndmask_b32_e32 v[[HI:[0-9]+]], 0, [[VAPERTURE]], vcc
|
||||
; CI-DAG: v_mov_b32_e32 [[VPTR:v[0-9]+]], [[PTR]]
|
||||
; CI-DAG: v_cndmask_b32_e32 v[[LO:[0-9]+]], 0, [[VPTR]]
|
||||
|
||||
; HSA-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
|
||||
; GFX9-DAG: s_load_dword [[PTR:s[0-9]+]], s[4:5], 0x0{{$}}
|
||||
; GFX9-DAG: s_getreg_b32 [[SSRC_SHARED:s[0-9]+]], hwreg(15, 16, 16)
|
||||
; GFX9-DAG: s_lshl_b32 [[SSRC_SHARED_BASE:s[0-9]+]], [[SSRC_SHARED]], 16
|
||||
; GFX9-DAG: v_mov_b32_e32 [[VAPERTURE:v[0-9]+]], [[SSRC_SHARED_BASE]]
|
||||
|
||||
; GFX9-XXX: v_mov_b32_e32 [[VAPERTURE:v[0-9]+]], src_shared_base
|
||||
|
||||
; HSA-DAG: v_mov_b32_e32 [[VPTR:v[0-9]+]], [[PTR]]
|
||||
|
||||
; HSA-DAG: v_cmp_ne_u32_e64 vcc, [[PTR]], -1
|
||||
; HSA-DAG: v_cndmask_b32_e32 v[[HI:[0-9]+]], 0, [[VAPERTURE]]
|
||||
; HSA-DAG: v_cndmask_b32_e32 v[[LO:[0-9]+]], 0, [[VPTR]]
|
||||
; HSA-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
|
||||
; GFX9: v_cmp_ne_u32_e64 vcc, [[PTR]], -1
|
||||
; GFX9: v_cndmask_b32_e32 v[[HI:[0-9]+]], 0, [[VAPERTURE]], vcc
|
||||
; GFX9-DAG: v_mov_b32_e32 [[VPTR:v[0-9]+]], [[PTR]]
|
||||
; GFX9-DAG: v_cndmask_b32_e32 v[[LO:[0-9]+]], 0, [[VPTR]]
|
||||
|
||||
; HSA: flat_store_dword v{{\[}}[[LO]]:[[HI]]{{\]}}, [[K]]
|
||||
|
||||
|
|
@ -48,6 +50,12 @@ define amdgpu_kernel void @use_group_to_flat_addrspacecast(i32 addrspace(3)* %pt
|
|||
; CI-DAG: s_load_dword [[APERTURE:s[0-9]+]], s[4:5], 0x11{{$}}
|
||||
; CI-DAG: v_mov_b32_e32 [[VAPERTURE:v[0-9]+]], [[APERTURE]]
|
||||
|
||||
; CI-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
|
||||
; CI-DAG: v_cmp_ne_u32_e64 vcc, [[PTR]], 0
|
||||
; CI-DAG: v_cndmask_b32_e32 v[[HI:[0-9]+]], 0, [[VAPERTURE]], vcc
|
||||
; CI-DAG: v_mov_b32_e32 [[VPTR:v[0-9]+]], [[PTR]]
|
||||
; CI-DAG: v_cndmask_b32_e32 v[[LO:[0-9]+]], 0, [[VPTR]]
|
||||
|
||||
; GFX9-DAG: s_load_dword [[PTR:s[0-9]+]], s[4:5], 0x0{{$}}
|
||||
; GFX9-DAG: s_getreg_b32 [[SSRC_PRIVATE:s[0-9]+]], hwreg(15, 0, 16)
|
||||
; GFX9-DAG: s_lshl_b32 [[SSRC_PRIVATE_BASE:s[0-9]+]], [[SSRC_PRIVATE]], 16
|
||||
|
|
@ -55,12 +63,11 @@ define amdgpu_kernel void @use_group_to_flat_addrspacecast(i32 addrspace(3)* %pt
|
|||
|
||||
; GFX9-XXX: v_mov_b32_e32 [[VAPERTURE:v[0-9]+]], src_private_base
|
||||
|
||||
; HSA-DAG: v_mov_b32_e32 [[VPTR:v[0-9]+]], [[PTR]]
|
||||
|
||||
; HSA-DAG: v_cmp_ne_u32_e64 vcc, [[PTR]], 0
|
||||
; HSA-DAG: v_cndmask_b32_e32 v[[HI:[0-9]+]], 0, [[VAPERTURE]]
|
||||
; HSA-DAG: v_cndmask_b32_e32 v[[LO:[0-9]+]], 0, [[VPTR]]
|
||||
; HSA-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
|
||||
; GFX9-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
|
||||
; GFX9: v_cmp_ne_u32_e64 vcc, [[PTR]], 0
|
||||
; GFX9: v_cndmask_b32_e32 v[[HI:[0-9]+]], 0, [[VAPERTURE]], vcc
|
||||
; GFX9: v_mov_b32_e32 [[VPTR:v[0-9]+]], [[PTR]]
|
||||
; GFX9-DAG: v_cndmask_b32_e32 v[[LO:[0-9]+]], 0, [[VPTR]]
|
||||
|
||||
; HSA: flat_store_dword v{{\[}}[[LO]]:[[HI]]{{\]}}, [[K]]
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s
|
||||
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=FUNC %s
|
||||
; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
|
||||
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s
|
||||
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI -check-prefix=FUNC %s
|
||||
; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=EG -check-prefix=FUNC %s
|
||||
|
||||
declare i7 @llvm.ctlz.i7(i7, i1) nounwind readnone
|
||||
declare i8 @llvm.ctlz.i8(i8, i1) nounwind readnone
|
||||
|
|
@ -35,8 +35,8 @@ define amdgpu_kernel void @s_ctlz_i32(i32 addrspace(1)* noalias %out, i32 %val)
|
|||
|
||||
; FUNC-LABEL: {{^}}v_ctlz_i32:
|
||||
; GCN: {{buffer|flat}}_load_dword [[VAL:v[0-9]+]],
|
||||
; GCN-DAG: v_ffbh_u32_e32 [[CTLZ:v[0-9]+]], [[VAL]]
|
||||
; GCN-DAG: v_cmp_ne_u32_e32 vcc, 0, [[CTLZ]]
|
||||
; GCN: v_ffbh_u32_e32 [[CTLZ:v[0-9]+]], [[VAL]]
|
||||
; GCN: v_cmp_ne_u32_e32 vcc, 0, [[VAL]]
|
||||
; GCN: v_cndmask_b32_e32 [[RESULT:v[0-9]+]], 32, [[CTLZ]], vcc
|
||||
; GCN: buffer_store_dword [[RESULT]],
|
||||
; GCN: s_endpgm
|
||||
|
|
@ -104,8 +104,15 @@ define amdgpu_kernel void @v_ctlz_v4i32(<4 x i32> addrspace(1)* noalias %out, <4
|
|||
|
||||
; FUNC-LABEL: {{^}}v_ctlz_i8:
|
||||
; GCN: {{buffer|flat}}_load_ubyte [[VAL:v[0-9]+]],
|
||||
; SI-DAG: v_ffbh_u32_e32 [[RESULT:v[0-9]+]], [[VAL]]
|
||||
; VI-DAG: v_ffbh_u32_sdwa [[RESULT:v[0-9]+]], [[VAL]] dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0
|
||||
; SI-DAG: v_ffbh_u32_e32 [[FFBH:v[0-9]+]], [[VAL]]
|
||||
; VI-DAG: v_ffbh_u32_sdwa [[FFBH:v[0-9]+]], [[VAL]] dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0
|
||||
; SI: v_cmp_ne_u32_e32 vcc, 0, [[VAL]]
|
||||
; VI: v_cmp_ne_u16_e32 vcc, 0, [[VAL]]
|
||||
|
||||
; GCN: v_cndmask_b32_e32 [[SELECT:v[0-9]+]], 32, [[FFBH]], vcc
|
||||
|
||||
; SI: v_subrev_i32_e32 [[RESULT:v[0-9]+]], vcc, 24, [[SELECT]]
|
||||
; VI: v_add_i32_e32 [[RESULT:v[0-9]+]], vcc, -16, [[SELECT]]
|
||||
; GCN: buffer_store_byte [[RESULT]],
|
||||
; GCN: s_endpgm
|
||||
define amdgpu_kernel void @v_ctlz_i8(i8 addrspace(1)* noalias %out, i8 addrspace(1)* noalias %valptr) nounwind {
|
||||
|
|
@ -142,11 +149,11 @@ define amdgpu_kernel void @s_ctlz_i64_trunc(i32 addrspace(1)* noalias %out, i64
|
|||
|
||||
; FUNC-LABEL: {{^}}v_ctlz_i64:
|
||||
; GCN-DAG: {{buffer|flat}}_load_dwordx2 v{{\[}}[[LO:[0-9]+]]:[[HI:[0-9]+]]{{\]}}
|
||||
; GCN-DAG: v_cmp_eq_u32_e64 [[CMPHI:s\[[0-9]+:[0-9]+\]]], 0, v[[HI]]
|
||||
; GCN-DAG: v_cmp_eq_u32_e32 vcc, 0, v[[HI]]
|
||||
; GCN-DAG: v_ffbh_u32_e32 [[FFBH_LO:v[0-9]+]], v[[LO]]
|
||||
; GCN-DAG: v_add_i32_e32 [[ADD:v[0-9]+]], vcc, 32, [[FFBH_LO]]
|
||||
; GCN-DAG: v_ffbh_u32_e32 [[FFBH_HI:v[0-9]+]], v[[HI]]
|
||||
; GCN-DAG: v_cndmask_b32_e64 v[[CTLZ:[0-9]+]], [[FFBH_HI]], [[ADD]], [[CMPHI]]
|
||||
; GCN-DAG: v_cndmask_b32_e32 v[[CTLZ:[0-9]+]], [[FFBH_HI]], [[ADD]], vcc
|
||||
; GCN-DAG: v_or_b32_e32 [[OR:v[0-9]+]], v[[HI]], v[[LO]]
|
||||
; GCN-DAG: v_cmp_ne_u32_e32 vcc, 0, [[OR]]
|
||||
; GCN-DAG: v_cndmask_b32_e32 v[[CLTZ_LO:[0-9]+]], 64, v[[CTLZ:[0-9]+]], vcc
|
||||
|
|
|
|||
|
|
@ -124,11 +124,11 @@ define amdgpu_kernel void @s_ctlz_zero_undef_i64_trunc(i32 addrspace(1)* noalias
|
|||
|
||||
; FUNC-LABEL: {{^}}v_ctlz_zero_undef_i64:
|
||||
; GCN-DAG: {{buffer|flat}}_load_dwordx2 v{{\[}}[[LO:[0-9]+]]:[[HI:[0-9]+]]{{\]}}
|
||||
; GCN-DAG: v_cmp_eq_u32_e64 [[CMPHI:s\[[0-9]+:[0-9]+\]]], 0, v[[HI]]
|
||||
; GCN-DAG: v_cmp_eq_u32_e32 vcc, 0, v[[HI]]
|
||||
; GCN-DAG: v_ffbh_u32_e32 [[FFBH_LO:v[0-9]+]], v[[LO]]
|
||||
; GCN-DAG: v_add_i32_e32 [[ADD:v[0-9]+]], vcc, 32, [[FFBH_LO]]
|
||||
; GCN-DAG: v_ffbh_u32_e32 [[FFBH_HI:v[0-9]+]], v[[HI]]
|
||||
; GCN-DAG: v_cndmask_b32_e64 v[[CTLZ:[0-9]+]], [[FFBH_HI]], [[FFBH_LO]]
|
||||
; GCN-DAG: v_cndmask_b32_e32 v[[CTLZ:[0-9]+]], [[FFBH_HI]], [[FFBH_LO]]
|
||||
; GCN: {{buffer|flat}}_store_dwordx2 {{.*}}v{{\[}}[[CTLZ]]:[[CTLZ_HI:[0-9]+]]{{\]}}
|
||||
define amdgpu_kernel void @v_ctlz_zero_undef_i64(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %in) nounwind {
|
||||
%tid = call i32 @llvm.r600.read.tidig.x()
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
|
||||
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
|
||||
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=SI %s
|
||||
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI %s
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_f16_lt
|
||||
; GCN: buffer_load_ushort v[[A_F16:[0-9]+]]
|
||||
|
|
@ -351,23 +351,12 @@ entry:
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_lt
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_lt_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_lt_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_lt_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_lt_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_lt:
|
||||
; SI: v_cmp_lt_f32_e32 vcc,
|
||||
; SI: v_cmp_lt_f32_e32 vcc,
|
||||
|
||||
; VI: v_cmp_lt_f16_e32 vcc,
|
||||
; VI: v_cmp_lt_f16_e32 vcc,
|
||||
define amdgpu_kernel void @fcmp_v2f16_lt(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -382,22 +371,11 @@ entry:
|
|||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_eq
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_eq_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_eq_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_eq_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_eq_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; SI: v_cmp_eq_f32_e32 vcc,
|
||||
; SI: v_cmp_eq_f32_e32 vcc,
|
||||
|
||||
; VI: v_cmp_eq_f16_e32 vcc,
|
||||
; VI: v_cmp_eq_f16_e32 vcc,
|
||||
define amdgpu_kernel void @fcmp_v2f16_eq(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -411,23 +389,11 @@ entry:
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_le
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_le_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_le_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_le_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_le_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_le:
|
||||
; SI: v_cmp_le_f32_e32 vcc
|
||||
; SI: v_cmp_le_f32_e32 vcc
|
||||
; VI: v_cmp_le_f16_e32 vcc
|
||||
; VI: v_cmp_le_f16_e32 vcc
|
||||
define amdgpu_kernel void @fcmp_v2f16_le(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -441,23 +407,12 @@ entry:
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_gt
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_gt_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_gt_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_gt_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_gt_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_gt:
|
||||
; SI: v_cmp_gt_f32_e32 vcc,
|
||||
; SI: v_cmp_gt_f32_e32 vcc,
|
||||
|
||||
; VI: v_cmp_gt_f16_e32 vcc,
|
||||
; VI: v_cmp_gt_f16_e32 vcc,
|
||||
define amdgpu_kernel void @fcmp_v2f16_gt(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -471,23 +426,12 @@ entry:
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_lg
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_lg_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_lg_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_lg_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_lg_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_lg:
|
||||
; SI: v_cmp_lg_f32_e32 vcc,
|
||||
; SI: v_cmp_lg_f32_e32 vcc,
|
||||
|
||||
; VI: v_cmp_lg_f16_e32 vcc,
|
||||
; VI: v_cmp_lg_f16_e32 vcc,
|
||||
define amdgpu_kernel void @fcmp_v2f16_lg(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -501,23 +445,12 @@ entry:
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_ge
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_ge_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_ge_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_ge_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_ge_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_ge:
|
||||
; SI: v_cmp_ge_f32_e32 vcc,
|
||||
; SI: v_cmp_ge_f32_e32 vcc,
|
||||
|
||||
; VI: v_cmp_ge_f16_e32 vcc,
|
||||
; VI: v_cmp_ge_f16_e32 vcc,
|
||||
define amdgpu_kernel void @fcmp_v2f16_ge(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -531,23 +464,12 @@ entry:
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_o
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_o_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_o_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_o_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_o_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_o:
|
||||
; SI: v_cmp_o_f32_e32 vcc,
|
||||
; SI: v_cmp_o_f32_e32 vcc,
|
||||
|
||||
; VI: v_cmp_o_f16_e32 vcc,
|
||||
; VI: v_cmp_o_f16_e32 vcc,
|
||||
define amdgpu_kernel void @fcmp_v2f16_o(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -561,23 +483,12 @@ entry:
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_u
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_u_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_u_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_u_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_u_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_u:
|
||||
; SI: v_cmp_u_f32_e32 vcc,
|
||||
; SI: v_cmp_u_f32_e32 vcc,
|
||||
|
||||
; VI: v_cmp_u_f16_e32 vcc,
|
||||
; VI: v_cmp_u_f16_e32 vcc,
|
||||
define amdgpu_kernel void @fcmp_v2f16_u(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -592,22 +503,11 @@ entry:
|
|||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_nge
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_nge_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_nge_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_nge_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_nge_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; SI: v_cmp_nge_f32_e32 vcc,
|
||||
; SI: v_cmp_nge_f32_e32 vcc,
|
||||
|
||||
; VI: v_cmp_nge_f16_e32 vcc,
|
||||
; VI: v_cmp_nge_f16_e32 vcc,
|
||||
define amdgpu_kernel void @fcmp_v2f16_nge(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -622,22 +522,11 @@ entry:
|
|||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_nlg
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_nlg_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_nlg_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_nlg_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_nlg_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; SI: v_cmp_nlg_f32_e32 vcc
|
||||
; SI: v_cmp_nlg_f32_e32 vcc
|
||||
|
||||
; VI: v_cmp_nlg_f16_e32 vcc
|
||||
; VI: v_cmp_nlg_f16_e32 vcc
|
||||
define amdgpu_kernel void @fcmp_v2f16_nlg(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -652,22 +541,11 @@ entry:
|
|||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_ngt
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_ngt_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_ngt_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_ngt_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_ngt_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; SI: v_cmp_ngt_f32_e32 vcc,
|
||||
; SI: v_cmp_ngt_f32_e32 vcc,
|
||||
|
||||
; VI: v_cmp_ngt_f16_e32 vcc,
|
||||
; VI: v_cmp_ngt_f16_e32 vcc,
|
||||
define amdgpu_kernel void @fcmp_v2f16_ngt(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -682,22 +560,11 @@ entry:
|
|||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_nle
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_nle_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_nle_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_nle_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_nle_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; SI: v_cmp_nle_f32_e32 vcc, v{{[0-9]+}}, v{{[0-9]+}}
|
||||
; SI: v_cmp_nle_f32_e32 vcc, v{{[0-9]+}}, v{{[0-9]+}}
|
||||
|
||||
; VI: v_cmp_nle_f16_e32 vcc, v{{[0-9]+}}, v{{[0-9]+}}
|
||||
; VI: v_cmp_nle_f16_e32 vcc, v{{[0-9]+}}, v{{[0-9]+}}
|
||||
define amdgpu_kernel void @fcmp_v2f16_nle(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -712,22 +579,11 @@ entry:
|
|||
}
|
||||
|
||||
; GCN-LABEL: {{^}}fcmp_v2f16_neq
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_neq_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_neq_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_neq_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_neq_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
; SI: v_cmp_neq_f32_e32 vcc, v{{[0-9]+}}, v{{[0-9]+}}
|
||||
; SI: v_cmp_neq_f32_e32 vcc, v{{[0-9]+}}, v{{[0-9]+}}
|
||||
|
||||
; VI: v_cmp_neq_f16_e32 vcc, v{{[0-9]+}}, v{{[0-9]+}}
|
||||
; VI: v_cmp_neq_f16_e32 vcc, v{{[0-9]+}}, v{{[0-9]+}}
|
||||
define amdgpu_kernel void @fcmp_v2f16_neq(
|
||||
<2 x i32> addrspace(1)* %r,
|
||||
<2 x half> addrspace(1)* %a,
|
||||
|
|
@ -744,17 +600,19 @@ entry:
|
|||
; GCN-LABEL: {{^}}fcmp_v2f16_nlt
|
||||
; GCN: buffer_load_dword v[[A_V2_F16:[0-9]+]]
|
||||
; GCN: buffer_load_dword v[[B_V2_F16:[0-9]+]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; GCN: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI: v_cmp_nlt_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
; SI: v_cmp_nlt_f32_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI: v_cmp_nlt_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; VI: v_cmp_nlt_f16_e64 s[{{[0-9]+}}:{{[0-9]+}}], v[[A_F16_1]], v[[B_F16_1]]
|
||||
; SI-DAG: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
|
||||
; GCN-DAG: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
|
||||
; SI-DAG: v_cvt_f32_f16_e32 v[[B_F32_0:[0-9]+]], v[[B_V2_F16]]
|
||||
; SI-DAG: v_cmp_nlt_f32_e32 vcc, v[[A_F32_0]], v[[B_F32_0]]
|
||||
|
||||
; GCN-DAG: v_lshrrev_b32_e32 v[[B_F16_1:[0-9]+]], 16, v[[B_V2_F16]]
|
||||
; SI-DAG: v_cvt_f32_f16_e32 v[[A_F32_1:[0-9]+]], v[[A_F16_1]]
|
||||
; SI-DAG: v_cvt_f32_f16_e32 v[[B_F32_1:[0-9]+]], v[[B_F16_1]]
|
||||
; SI-DAG: v_cmp_nlt_f32_e32 vcc, v[[A_F32_1]], v[[B_F32_1]]
|
||||
; VI-DAG: v_cmp_nlt_f16_e32 vcc, v[[A_V2_F16]], v[[B_V2_F16]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_0:[0-9]+]]
|
||||
|
||||
; VI: v_cmp_nlt_f16_e32 vcc, v[[A_F16_1]], v[[B_F16_1]]
|
||||
; GCN: v_cndmask_b32_e64 v[[R_I32_1:[0-9]+]]
|
||||
; GCN: buffer_store_dwordx2 v{{\[}}[[R_I32_0]]:[[R_I32_1]]{{\]}}
|
||||
; GCN: s_endpgm
|
||||
|
|
|
|||
|
|
@ -222,9 +222,9 @@ entry:
|
|||
; FIXME: Should be scheduled to shrink vcc
|
||||
; CHECK-LABEL: {{^}}i1_input_phys_vgpr_x2:
|
||||
; CHECK: v_cmp_eq_u32_e32 vcc, 1, v0
|
||||
; CHECK: v_cmp_eq_u32_e64 s[0:1], 1, v1
|
||||
; CHECK: v_cndmask_b32_e64 v0, 0, -1, vcc
|
||||
; CHECK: v_cndmask_b32_e64 v1, 0, -1, s[0:1]
|
||||
; CHECK: v_cmp_eq_u32_e32 vcc, 1, v1
|
||||
; CHECK: v_cndmask_b32_e64 v1, 0, -1, vcc
|
||||
define amdgpu_kernel void @i1_input_phys_vgpr_x2() {
|
||||
entry:
|
||||
%val0 = load volatile i1, i1 addrspace(1)* undef
|
||||
|
|
|
|||
|
|
@ -0,0 +1,227 @@
|
|||
# RUN: llc -march=amdgcn -verify-machineinstrs -run-pass machine-scheduler -o - %s | FileCheck -check-prefix=GCN %s
|
||||
|
||||
# GCN-LABEL: name: cluster_add_addc
|
||||
# GCN: S_NOP 0, implicit-def %vcc
|
||||
# GCN: dead %2, %3 = V_ADD_I32_e64 %0, %1, implicit %exec
|
||||
# GCN: dead %4, dead %5 = V_ADDC_U32_e64 %6, %7, %3, implicit %exec
|
||||
name: cluster_add_addc
|
||||
registers:
|
||||
- { id: 0, class: vgpr_32 }
|
||||
- { id: 1, class: vgpr_32 }
|
||||
- { id: 2, class: vgpr_32 }
|
||||
- { id: 3, class: sreg_64 }
|
||||
- { id: 4, class: vgpr_32 }
|
||||
- { id: 5, class: sreg_64 }
|
||||
- { id: 6, class: vgpr_32 }
|
||||
- { id: 7, class: vgpr_32 }
|
||||
|
||||
body: |
|
||||
bb.0:
|
||||
%0 = V_MOV_B32_e32 0, implicit %exec
|
||||
%1 = V_MOV_B32_e32 0, implicit %exec
|
||||
%2, %3 = V_ADD_I32_e64 %0, %1, implicit %exec
|
||||
%6 = V_MOV_B32_e32 0, implicit %exec
|
||||
%7 = V_MOV_B32_e32 0, implicit %exec
|
||||
S_NOP 0, implicit def %vcc
|
||||
%4, %5 = V_ADDC_U32_e64 %6, %7, %3, implicit %exec
|
||||
...
|
||||
|
||||
# GCN-LABEL: name: interleave_add64s
|
||||
# GCN: dead %8, %9 = V_ADD_I32_e64 %0, %1, implicit %exec
|
||||
# GCN-NEXT: dead %12, dead %13 = V_ADDC_U32_e64 %4, %5, %9, implicit %exec
|
||||
# GCN-NEXT: dead %10, %11 = V_ADD_I32_e64 %2, %3, implicit %exec
|
||||
# GCN-NEXT: dead %14, dead %15 = V_ADDC_U32_e64 %6, %7, %11, implicit %exec
|
||||
name: interleave_add64s
|
||||
registers:
|
||||
- { id: 0, class: vgpr_32 }
|
||||
- { id: 1, class: vgpr_32 }
|
||||
- { id: 2, class: vgpr_32 }
|
||||
- { id: 3, class: vgpr_32 }
|
||||
- { id: 4, class: vgpr_32 }
|
||||
- { id: 5, class: vgpr_32 }
|
||||
- { id: 6, class: vgpr_32 }
|
||||
- { id: 7, class: vgpr_32 }
|
||||
- { id: 8, class: vgpr_32 }
|
||||
- { id: 9, class: sreg_64 }
|
||||
- { id: 10, class: vgpr_32 }
|
||||
- { id: 11, class: sreg_64 }
|
||||
- { id: 12, class: vgpr_32 }
|
||||
- { id: 13, class: sreg_64 }
|
||||
- { id: 14, class: vgpr_32 }
|
||||
- { id: 15, class: sreg_64 }
|
||||
|
||||
body: |
|
||||
bb.0:
|
||||
%0 = V_MOV_B32_e32 0, implicit %exec
|
||||
%1 = V_MOV_B32_e32 0, implicit %exec
|
||||
%2 = V_MOV_B32_e32 0, implicit %exec
|
||||
%3 = V_MOV_B32_e32 0, implicit %exec
|
||||
%4 = V_MOV_B32_e32 0, implicit %exec
|
||||
%5 = V_MOV_B32_e32 0, implicit %exec
|
||||
%6 = V_MOV_B32_e32 0, implicit %exec
|
||||
%7 = V_MOV_B32_e32 0, implicit %exec
|
||||
|
||||
%8, %9 = V_ADD_I32_e64 %0, %1, implicit %exec
|
||||
%10, %11 = V_ADD_I32_e64 %2, %3, implicit %exec
|
||||
|
||||
|
||||
%12, %13 = V_ADDC_U32_e64 %4, %5, %9, implicit %exec
|
||||
%14, %15 = V_ADDC_U32_e64 %6, %7, %11, implicit %exec
|
||||
...
|
||||
|
||||
# GCN-LABEL: name: cluster_mov_addc
|
||||
# GCN: S_NOP 0, implicit-def %vcc
|
||||
# GCN-NEXT: %2 = S_MOV_B64 0
|
||||
# GCN-NEXT: dead %3, dead %4 = V_ADDC_U32_e64 %0, %1, %2, implicit %exec
|
||||
name: cluster_mov_addc
|
||||
registers:
|
||||
- { id: 0, class: vgpr_32 }
|
||||
- { id: 1, class: vgpr_32 }
|
||||
- { id: 2, class: sreg_64 }
|
||||
- { id: 3, class: vgpr_32 }
|
||||
- { id: 4, class: sreg_64 }
|
||||
- { id: 6, class: vgpr_32 }
|
||||
- { id: 7, class: vgpr_32 }
|
||||
|
||||
body: |
|
||||
bb.0:
|
||||
%0 = V_MOV_B32_e32 0, implicit %exec
|
||||
%1 = V_MOV_B32_e32 0, implicit %exec
|
||||
%2 = S_MOV_B64 0
|
||||
S_NOP 0, implicit def %vcc
|
||||
%3, %4 = V_ADDC_U32_e64 %0, %1, %2, implicit %exec
|
||||
...
|
||||
|
||||
# GCN-LABEL: name: no_cluster_add_addc_diff_sgpr
|
||||
# GCN: dead %2, dead %3 = V_ADD_I32_e64 %0, %1, implicit %exec
|
||||
# GCN-NEXT: %6 = V_MOV_B32_e32 0, implicit %exec
|
||||
# GCN-NEXT: %7 = V_MOV_B32_e32 0, implicit %exec
|
||||
# GCN-NEXT: S_NOP 0, implicit-def %vcc
|
||||
# GCN-NEXT: %8 = S_MOV_B64 0
|
||||
# GCN-NEXT: dead %4, dead %5 = V_ADDC_U32_e64 %6, %7, %8, implicit %exec
|
||||
name: no_cluster_add_addc_diff_sgpr
|
||||
registers:
|
||||
- { id: 0, class: vgpr_32 }
|
||||
- { id: 1, class: vgpr_32 }
|
||||
- { id: 2, class: vgpr_32 }
|
||||
- { id: 3, class: sreg_64 }
|
||||
- { id: 4, class: vgpr_32 }
|
||||
- { id: 5, class: sreg_64 }
|
||||
- { id: 6, class: vgpr_32 }
|
||||
- { id: 7, class: vgpr_32 }
|
||||
- { id: 8, class: sreg_64 }
|
||||
body: |
|
||||
bb.0:
|
||||
%0 = V_MOV_B32_e32 0, implicit %exec
|
||||
%1 = V_MOV_B32_e32 0, implicit %exec
|
||||
%8 = S_MOV_B64 0
|
||||
%2, %3 = V_ADD_I32_e64 %0, %1, implicit %exec
|
||||
%6 = V_MOV_B32_e32 0, implicit %exec
|
||||
%7 = V_MOV_B32_e32 0, implicit %exec
|
||||
S_NOP 0, implicit def %vcc
|
||||
%4, %5 = V_ADDC_U32_e64 %6, %7, %8, implicit %exec
|
||||
...
|
||||
# GCN-LABEL: name: cluster_sub_subb
|
||||
# GCN: S_NOP 0, implicit-def %vcc
|
||||
# GCN: dead %2, %3 = V_SUB_I32_e64 %0, %1, implicit %exec
|
||||
# GCN: dead %4, dead %5 = V_SUBB_U32_e64 %6, %7, %3, implicit %exec
|
||||
name: cluster_sub_subb
|
||||
registers:
|
||||
- { id: 0, class: vgpr_32 }
|
||||
- { id: 1, class: vgpr_32 }
|
||||
- { id: 2, class: vgpr_32 }
|
||||
- { id: 3, class: sreg_64 }
|
||||
- { id: 4, class: vgpr_32 }
|
||||
- { id: 5, class: sreg_64 }
|
||||
- { id: 6, class: vgpr_32 }
|
||||
- { id: 7, class: vgpr_32 }
|
||||
|
||||
body: |
|
||||
bb.0:
|
||||
%0 = V_MOV_B32_e32 0, implicit %exec
|
||||
%1 = V_MOV_B32_e32 0, implicit %exec
|
||||
%2, %3 = V_SUB_I32_e64 %0, %1, implicit %exec
|
||||
%6 = V_MOV_B32_e32 0, implicit %exec
|
||||
%7 = V_MOV_B32_e32 0, implicit %exec
|
||||
S_NOP 0, implicit def %vcc
|
||||
%4, %5 = V_SUBB_U32_e64 %6, %7, %3, implicit %exec
|
||||
...
|
||||
|
||||
# GCN-LABEL: name: cluster_cmp_cndmask
|
||||
# GCN: S_NOP 0, implicit-def %vcc
|
||||
# GCN-NEXT: %3 = V_CMP_EQ_I32_e64 %0, %1, implicit %exec
|
||||
# GCN-NEXT: dead %4 = V_CNDMASK_B32_e64 %0, %1, %3, implicit %exec
|
||||
name: cluster_cmp_cndmask
|
||||
registers:
|
||||
- { id: 0, class: vgpr_32 }
|
||||
- { id: 1, class: vgpr_32 }
|
||||
- { id: 2, class: vgpr_32 }
|
||||
- { id: 3, class: sreg_64 }
|
||||
- { id: 4, class: vgpr_32 }
|
||||
- { id: 5, class: sreg_64 }
|
||||
- { id: 6, class: vgpr_32 }
|
||||
- { id: 7, class: vgpr_32 }
|
||||
|
||||
body: |
|
||||
bb.0:
|
||||
%0 = V_MOV_B32_e32 0, implicit %exec
|
||||
%1 = V_MOV_B32_e32 0, implicit %exec
|
||||
%3 = V_CMP_EQ_I32_e64 %0, %1, implicit %exec
|
||||
S_NOP 0, implicit def %vcc
|
||||
%4 = V_CNDMASK_B32_e64 %0, %1, %3, implicit %exec
|
||||
...
|
||||
|
||||
# GCN-LABEL: name: cluster_multi_use_cmp_cndmask
|
||||
# GCN: %4 = V_CMP_EQ_I32_e64 %0, %1, implicit %exec
|
||||
# GCN-NEXT: dead %5 = V_CNDMASK_B32_e64 %2, %1, %4, implicit %exec
|
||||
# GCN-NEXT: dead %6 = V_CNDMASK_B32_e64 %1, %3, %4, implicit %exec
|
||||
name: cluster_multi_use_cmp_cndmask
|
||||
registers:
|
||||
- { id: 0, class: vgpr_32 }
|
||||
- { id: 1, class: vgpr_32 }
|
||||
- { id: 2, class: vgpr_32 }
|
||||
- { id: 3, class: vgpr_32 }
|
||||
- { id: 4, class: sreg_64 }
|
||||
- { id: 5, class: vgpr_32 }
|
||||
- { id: 6, class: vgpr_32 }
|
||||
- { id: 7, class: vgpr_32 }
|
||||
|
||||
body: |
|
||||
bb.0:
|
||||
%0 = V_MOV_B32_e32 0, implicit %exec
|
||||
%1 = V_MOV_B32_e32 0, implicit %exec
|
||||
%2 = V_MOV_B32_e32 0, implicit %exec
|
||||
%3 = V_MOV_B32_e32 0, implicit %exec
|
||||
|
||||
%4 = V_CMP_EQ_I32_e64 %0, %1, implicit %exec
|
||||
S_NOP 0, implicit def %vcc
|
||||
%5 = V_CNDMASK_B32_e64 %2, %1, %4, implicit %exec
|
||||
%6 = V_CNDMASK_B32_e64 %1, %3, %4, implicit %exec
|
||||
...
|
||||
|
||||
# GCN-LABEL: name: cluster_multi_use_cmp_cndmask2
|
||||
# GCN: %4 = V_CMP_EQ_I32_e64 %0, %1, implicit %exec
|
||||
# GCN-NEXT: dead %5 = V_CNDMASK_B32_e64 %2, %1, %4, implicit %exec
|
||||
# GCN-NEXT: %3 = V_MOV_B32_e32 0, implicit %exec
|
||||
# GCN-NEXT: dead %6 = V_CNDMASK_B32_e64 %1, %3, %4, implicit %exec
|
||||
name: cluster_multi_use_cmp_cndmask2
|
||||
registers:
|
||||
- { id: 0, class: vgpr_32 }
|
||||
- { id: 1, class: vgpr_32 }
|
||||
- { id: 2, class: vgpr_32 }
|
||||
- { id: 3, class: vgpr_32 }
|
||||
- { id: 4, class: sreg_64 }
|
||||
- { id: 5, class: vgpr_32 }
|
||||
- { id: 6, class: vgpr_32 }
|
||||
- { id: 7, class: vgpr_32 }
|
||||
|
||||
body: |
|
||||
bb.0:
|
||||
%0 = V_MOV_B32_e32 0, implicit %exec
|
||||
%1 = V_MOV_B32_e32 0, implicit %exec
|
||||
%4 = V_CMP_EQ_I32_e64 %0, %1, implicit %exec
|
||||
%2 = V_MOV_B32_e32 0, implicit %exec
|
||||
%5 = V_CNDMASK_B32_e64 %2, %1, %4, implicit %exec
|
||||
%3 = V_MOV_B32_e32 0, implicit %exec
|
||||
%6 = V_CNDMASK_B32_e64 %1, %3, %4, implicit %exec
|
||||
...
|
||||
|
|
@ -66,9 +66,9 @@
|
|||
|
||||
; FIXME: Why is this compare essentially repeated?
|
||||
; GCN: v_cmp_eq_u32_e32 vcc, 1, [[REG:v[0-9]+]]
|
||||
; GCN-NEXT: v_cmp_ne_u32_e64 s{{\[[0-9]+:[0-9]+\]}}, 1, [[REG]]
|
||||
; GCN: v_cndmask_b32_e64 v{{[0-9]+}}, 0, -1, vcc
|
||||
; GCN: v_cndmask_b32_e64 v{{[0-9]+}}, 0, -1
|
||||
; GCN: v_cmp_ne_u32_e32 vcc, 1, [[REG]]
|
||||
; GCN: v_cndmask_b32_e64 v{{[0-9]+}}, 0, -1, vcc
|
||||
|
||||
; GCN: ; %Flow1
|
||||
; GCN-NEXT: s_or_b64 exec, exec
|
||||
|
|
|
|||
|
|
@ -134,8 +134,8 @@ define amdgpu_kernel void @v_sad_u32_multi_use_sub_pat2(i32 addrspace(1)* %out,
|
|||
|
||||
; GCN-LABEL: {{^}}v_sad_u32_multi_use_select_pat2:
|
||||
; GCN: s_sub_i32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
|
||||
; GCN: v_cmp_gt_u32_e32 vcc, s{{[0-9]+}}, v{{[0-9]+}}
|
||||
; GCN: s_sub_i32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
|
||||
; GCN-DAG: v_cmp_gt_u32_e32 vcc, s{{[0-9]+}}, v{{[0-9]+}}
|
||||
; GCN-DAG: s_sub_i32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
|
||||
define amdgpu_kernel void @v_sad_u32_multi_use_select_pat2(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c) {
|
||||
%icmp0 = icmp ugt i32 %a, %b
|
||||
%sub0 = sub i32 %a, %b
|
||||
|
|
|
|||
|
|
@ -104,8 +104,8 @@ entry:
|
|||
; SI: v_cndmask_b32_e32 v[[R_F32:[0-9]+]], 0.5, v[[D_F32]], vcc
|
||||
; SI: v_cvt_f16_f32_e32 v[[R_F16:[0-9]+]], v[[R_F32]]
|
||||
|
||||
; VI: v_cmp_nlt_f16_e32 vcc, v[[A_F16]], v[[B_F16]]
|
||||
; VI: v_mov_b32_e32 v[[C_F16:[0-9]+]], 0x3800{{$}}
|
||||
; VI: v_cmp_nlt_f16_e32 vcc, v[[A_F16]], v[[B_F16]]
|
||||
; VI: v_cndmask_b32_e32 v[[R_F16:[0-9]+]], v[[C_F16]], v[[D_F16]], vcc
|
||||
; GCN: buffer_store_short v[[R_F16]]
|
||||
; GCN: s_endpgm
|
||||
|
|
@ -134,8 +134,8 @@ entry:
|
|||
; SI: v_cmp_lt_f32_e32 vcc, v[[A_F32]], v[[B_F32]]
|
||||
; SI: v_cndmask_b32_e32 v[[R_F32:[0-9]+]], 0.5, v[[C_F32]]
|
||||
; SI: v_cvt_f16_f32_e32 v[[R_F16:[0-9]+]], v[[R_F32]]
|
||||
; VI: v_cmp_lt_f16_e32 vcc, v[[A_F16]], v[[B_F16]]
|
||||
; VI: v_mov_b32_e32 v[[D_F16:[0-9]+]], 0x3800{{$}}
|
||||
; VI: v_cmp_lt_f16_e32 vcc, v[[A_F16]], v[[B_F16]]
|
||||
; VI: v_cndmask_b32_e32 v[[R_F16:[0-9]+]], v[[D_F16]], v[[C_F16]], vcc
|
||||
; GCN: buffer_store_short v[[R_F16]]
|
||||
; GCN: s_endpgm
|
||||
|
|
@ -159,16 +159,16 @@ entry:
|
|||
; SI: v_cvt_f32_f16_e32
|
||||
; SI: v_cvt_f32_f16_e32
|
||||
; SI: v_cvt_f32_f16_e32
|
||||
; SI: v_cmp_lt_f32_e64
|
||||
; SI: v_cmp_lt_f32_e32
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cndmask_b32_e64
|
||||
; SI: v_cmp_lt_f32_e32
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cvt_f16_f32_e32
|
||||
; SI: v_cvt_f16_f32_e32
|
||||
|
||||
; VI: v_cmp_lt_f16_e64
|
||||
; VI: v_cmp_lt_f16_e32
|
||||
; VI: v_cndmask_b32_e64
|
||||
; VI: v_cndmask_b32_e32
|
||||
; VI: v_cmp_lt_f16_e32
|
||||
; VI: v_cndmask_b32_e32
|
||||
|
||||
; GCN: s_endpgm
|
||||
|
|
@ -196,13 +196,17 @@ entry:
|
|||
; SI: v_cvt_f32_f16_e32
|
||||
; SI: v_cvt_f32_f16_e32
|
||||
; SI: v_cvt_f32_f16_e32
|
||||
; SI-DAG: v_cmp_gt_f32_e64
|
||||
; SI-DAG: v_cmp_lt_f32_e32 vcc, 0.5
|
||||
|
||||
; SI: v_cmp_lt_f32_e32 vcc, 0.5
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cmp_gt_f32_e32
|
||||
; SI: v_cndmask_b32_e32
|
||||
|
||||
; VI: v_cmp_lt_f16_e32
|
||||
; VI: v_cmp_gt_f16_e64
|
||||
; GCN: v_cndmask_b32_e32
|
||||
; GCN: v_cndmask_b32_e64
|
||||
; VI: v_cndmask_b32_e32
|
||||
; VI: v_cmp_gt_f16_e32
|
||||
; VI: v_cndmask_b32_e32
|
||||
|
||||
; SI: v_cvt_f16_f32_e32
|
||||
; SI: v_cvt_f16_f32_e32
|
||||
; GCN: s_endpgm
|
||||
|
|
@ -228,13 +232,16 @@ entry:
|
|||
; SI: v_cvt_f32_f16_e32
|
||||
; SI: v_cvt_f32_f16_e32
|
||||
; SI: v_cvt_f32_f16_e32
|
||||
; SI-DAG: v_cmp_lt_f32_e64
|
||||
; SI-DAG: v_cmp_gt_f32_e32 vcc, 0.5
|
||||
|
||||
; SI: v_cmp_gt_f32_e32 vcc, 0.5
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cmp_lt_f32_e32
|
||||
; SI: v_cndmask_b32_e32
|
||||
|
||||
; VI: v_cmp_gt_f16_e32
|
||||
; VI: v_cmp_lt_f16_e64
|
||||
; GCN: v_cndmask_b32_e32
|
||||
; GCN: v_cndmask_b32_e64
|
||||
; VI: v_cndmask_b32_e32
|
||||
; VI: v_cmp_lt_f16_e32
|
||||
; VI: v_cndmask_b32_e32
|
||||
|
||||
; SI: v_cvt_f16_f32_e32
|
||||
; SI: v_cvt_f16_f32_e32
|
||||
|
|
@ -263,8 +270,8 @@ entry:
|
|||
; SI: v_cvt_f32_f16_e32
|
||||
|
||||
; SI: v_cmp_nlt_f32_e32
|
||||
; SI: v_cmp_nlt_f32_e64
|
||||
; SI: v_cndmask_b32_e64
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cmp_nlt_f32_e32
|
||||
; SI: v_cndmask_b32_e32
|
||||
|
||||
; VI: v_cmp_nlt_f16_e32
|
||||
|
|
@ -298,13 +305,17 @@ entry:
|
|||
; SI: v_cvt_f32_f16_e32
|
||||
; SI: v_cvt_f32_f16_e32
|
||||
; SI: v_cvt_f32_f16_e32
|
||||
; SI: v_cmp_lt_f32_e64
|
||||
|
||||
; SI: v_cmp_lt_f32_e32
|
||||
; SI: v_cndmask_b32
|
||||
; SI: v_cmp_lt_f32_e32
|
||||
; SI: v_cndmask_b32
|
||||
|
||||
; VI: v_cmp_lt_f16_e32
|
||||
; VI: v_cmp_lt_f16_e64
|
||||
; GCN: v_cndmask_b32
|
||||
; GCN: v_cndmask_b32
|
||||
; VI: v_cndmask_b32
|
||||
; VI: v_cmp_lt_f16_e32
|
||||
; VI: v_cndmask_b32
|
||||
|
||||
; SI: v_cvt_f16_f32_e32
|
||||
; SI: v_cvt_f16_f32_e32
|
||||
; GCN: s_endpgm
|
||||
|
|
|
|||
|
|
@ -7,8 +7,8 @@ declare i32 @llvm.r600.read.tidig.x() nounwind readnone
|
|||
; R600-DAG: SETE_INT * T{{[0-9]+\.[XYZW]}}, KC0[3].X, KC0[3].Z
|
||||
; R600-DAG: SETE_INT * T{{[0-9]+\.[XYZW]}}, KC0[2].W, KC0[3].Y
|
||||
|
||||
; GCN-DAG: v_cmp_eq_u32_e32
|
||||
; GCN-DAG: v_cmp_eq_u32_e64
|
||||
; GCN: v_cmp_eq_u32_e32
|
||||
; GCN: v_cmp_eq_u32_e32
|
||||
define amdgpu_kernel void @setcc_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> %a, <2 x i32> %b) #0 {
|
||||
%result = icmp eq <2 x i32> %a, %b
|
||||
%sext = sext <2 x i1> %result to <2 x i32>
|
||||
|
|
@ -23,9 +23,9 @@ define amdgpu_kernel void @setcc_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> %
|
|||
; R600-DAG: SETE_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
|
||||
; GCN: v_cmp_eq_u32_e32
|
||||
; GCN: v_cmp_eq_u32_e64
|
||||
; GCN: v_cmp_eq_u32_e64
|
||||
; GCN: v_cmp_eq_u32_e64
|
||||
; GCN: v_cmp_eq_u32_e32
|
||||
; GCN: v_cmp_eq_u32_e32
|
||||
; GCN: v_cmp_eq_u32_e32
|
||||
define amdgpu_kernel void @setcc_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) #0 {
|
||||
%b_ptr = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %in, i32 1
|
||||
%a = load <4 x i32>, <4 x i32> addrspace(1)* %in
|
||||
|
|
|
|||
|
|
@ -58,8 +58,8 @@ define amdgpu_kernel void @v_uaddo_i32(i32 addrspace(1)* %out, i1 addrspace(1)*
|
|||
}
|
||||
|
||||
; FUNC-LABEL: {{^}}v_uaddo_i32_novcc:
|
||||
; GCN: v_add_i32_e64 v{{[0-9]+}}, [[COND:s\[[0-9]+:[0-9]+\]]], v{{[0-9]+}}, v{{[0-9]+}}
|
||||
; GCN: v_cndmask_b32_e64 v{{[0-9]+}}, 0, 1, [[COND]]
|
||||
; GCN: v_add_i32_e32 v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}}
|
||||
; GCN: v_cndmask_b32_e64 v{{[0-9]+}}, 0, 1, vcc
|
||||
|
||||
; EG: ADDC_UINT
|
||||
; EG: ADD_INT
|
||||
|
|
|
|||
|
|
@ -58,8 +58,8 @@ define amdgpu_kernel void @v_usubo_i32(i32 addrspace(1)* %out, i1 addrspace(1)*
|
|||
}
|
||||
|
||||
; FUNC-LABEL: {{^}}v_usubo_i32_novcc:
|
||||
; GCN: v_sub_i32_e64 v{{[0-9]+}}, [[COND:s\[[0-9]+:[0-9]+\]]], v{{[0-9]+}}, v{{[0-9]+}}
|
||||
; GCN: v_cndmask_b32_e64 v{{[0-9]+}}, 0, 1, [[COND]]
|
||||
; GCN: v_sub_i32_e32 v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}}
|
||||
; GCN: v_cndmask_b32_e64 v{{[0-9]+}}, 0, 1, vcc
|
||||
|
||||
; EG-DAG: SUBB_UINT
|
||||
; EG-DAG: SUB_INT
|
||||
|
|
|
|||
|
|
@ -200,9 +200,9 @@ define amdgpu_kernel void @icmp_vgprX_k0_select_k1_vgprZ_i32(i32 addrspace(1)* %
|
|||
; SI-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 0, v[[Z_HI]], vcc
|
||||
; SI-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 2, v[[Z_LO]], vcc
|
||||
|
||||
; VI-DAG: v_cmp_lt_i64_e64 s{{\[[0-9]+:[0-9]+\]}}, -1, v{{\[}}[[X_LO]]:[[X_HI]]{{\]}}
|
||||
; VI-DAG: v_cndmask_b32_e64 v{{[0-9]+}}, 0, v[[Z_HI]], s
|
||||
; VI-DAG: v_cndmask_b32_e64 v{{[0-9]+}}, 2, v[[Z_LO]], s
|
||||
; VI-DAG: v_cmp_lt_i64_e32 vcc, -1, v{{\[}}[[X_LO]]:[[X_HI]]{{\]}}
|
||||
; VI-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 0, v[[Z_HI]], vcc
|
||||
; VI-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 2, v[[Z_LO]], vcc
|
||||
define amdgpu_kernel void @icmp_vgprX_k0_select_k1_vgprZ_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %x.ptr, i64 addrspace(1)* %z.ptr) #0 {
|
||||
%tid = call i32 @llvm.amdgcn.workitem.id.x() #1
|
||||
%tid.ext = sext i32 %tid to i64
|
||||
|
|
@ -292,10 +292,10 @@ define amdgpu_kernel void @fcmp_k0_vgprX_select_k1_vgprZ_v4f32(<4 x float> addrs
|
|||
; GCN-LABEL: {{^}}icmp_vgprX_k0_select_k1_vgprZ_i1:
|
||||
; GCN: load_dword
|
||||
; GCN: load_ubyte
|
||||
; GCN-DAG: v_cmp_gt_i32_e64 s{{\[[0-9]+:[0-9]+\]}}, 0, v
|
||||
; GCN-DAG: v_cmp_gt_i32_e32 vcc, 0, v
|
||||
; DCN-DAG: v_and_b32_e32 v{{[0-9]+}}, 1,
|
||||
; GCN-DAG: v_cmp_eq_u32_e32 vcc, 1, v
|
||||
; GCN-DAG: s_or_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, vcc
|
||||
; GCN-DAG: v_cmp_eq_u32_e64 s{{\[[0-9]+:[0-9]+\]}}, 1, v
|
||||
; GCN-DAG: s_or_b64 s{{\[[0-9]+:[0-9]+\]}}, vcc, s{{\[[0-9]+:[0-9]+\]}}
|
||||
; GCN: v_cndmask_b32_e64 v{{[0-9]+}}, 0, 1, s
|
||||
; GCN: store_byte
|
||||
define amdgpu_kernel void @icmp_vgprX_k0_select_k1_vgprZ_i1(i1 addrspace(1)* %out, i32 addrspace(1)* %x.ptr, i1 addrspace(1)* %z.ptr) #0 {
|
||||
|
|
|
|||
|
|
@ -7,7 +7,9 @@
|
|||
; EG-DAG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW]}}, KC0[3].Z
|
||||
; EG-DAG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW]}}, KC0[3].Y
|
||||
|
||||
; SI: v_cndmask_b32_e64
|
||||
; SI: v_cmp_gt_i32_e32 vcc
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cmp_gt_i32_e32 vcc
|
||||
; SI: v_cndmask_b32_e32
|
||||
|
||||
define amdgpu_kernel void @test_select_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in0, <2 x i32> addrspace(1)* %in1, <2 x i32> %val) {
|
||||
|
|
@ -25,7 +27,10 @@ entry:
|
|||
; EG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
; EG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
|
||||
;SI: v_cndmask_b32_e64
|
||||
|
||||
; SI: v_cmp_neq_f32_e32 vcc
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cmp_neq_f32_e32 vcc
|
||||
; SI: v_cndmask_b32_e32
|
||||
|
||||
define amdgpu_kernel void @test_select_v2f32(<2 x float> addrspace(1)* %out, <2 x float> addrspace(1)* %in0, <2 x float> addrspace(1)* %in1) {
|
||||
|
|
@ -45,12 +50,10 @@ entry:
|
|||
; EG-DAG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW]}}, KC0[3].Z
|
||||
; EG-DAG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW]}}, KC0[3].Y
|
||||
|
||||
; FIXME: The shrinking does not happen on tonga
|
||||
|
||||
; SI: v_cndmask_b32
|
||||
; SI: v_cndmask_b32
|
||||
; SI: v_cndmask_b32
|
||||
; SI: v_cndmask_b32
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cndmask_b32_e32
|
||||
|
||||
define amdgpu_kernel void @test_select_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in0, <4 x i32> addrspace(1)* %in1, <4 x i32> %val) {
|
||||
entry:
|
||||
|
|
@ -68,6 +71,10 @@ entry:
|
|||
;EG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
;EG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cndmask_b32_e32
|
||||
; SI: v_cndmask_b32_e32
|
||||
define amdgpu_kernel void @test_select_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in0, <4 x float> addrspace(1)* %in1) {
|
||||
entry:
|
||||
%0 = load <4 x float>, <4 x float> addrspace(1)* %in0
|
||||
|
|
|
|||
Loading…
Reference in New Issue