shifathosn
/
sharpemu
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[ShaderCompiler] Run lane-local wave64 programs as independent half waves

This commit is contained in:
ParantezTech 2026-10-11 01:34:56 +03:00
parent 7a6e3d0308
commit 08891b1fef
3 changed files with 165 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

158
src/SharpEmu.ShaderCompiler.Vulkan/Gen5SpirvTranslator.HalfWave64Lowering.cs Normal file
View File

@ -0,0 +1,158 @@
// Copyright (C) 2026 SharpEmu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
using SharpEmu.ShaderCompiler.Resources;
namespace SharpEmu.ShaderCompiler.Vulkan;
public static partial class Gen5SpirvTranslator
{
private sealed partial class CompilationContext
{
// Independent halves duplicate scalar work; a lane-local proof is not a performance proof.
private static readonly bool LaneLocalWave64Enabled = string.Equals(
Environment.GetEnvironmentVariable("SHARPEMU_WAVE64_LANE_LOCAL"), "1", StringComparison.Ordinal);
private static bool CanRunHalfWaves(ShaderCompileRequest request, int[] physicalAxisOfLogical)
{
if (!LaneLocalWave64Enabled ||
physicalAxisOfLogical is not [0, 1, 2])
{
return false;
}
var sharedFlatPcs = request.Memory.Entries
.Where(static memory => memory.AddressSpace is FlatAddressSpace.Shared or FlatAddressSpace.SharedOrPrivate)
.Select(static memory => memory.Pc)
.ToHashSet();
return Ir.Gen5WaveLaneLocalAnalysis.IsLaneLocal(request.Program, sharedFlatPcs, out _);
}
private sealed class HalfWave64Lowering : IWaveLowering
{
private readonly CompilationContext _context;
public HalfWave64Lowering(CompilationContext context)
{
_context = context;
}
public bool RequiresCrossSubgroupSynchronization => false;
public uint ReserveLdsDwords(uint guestDwordCount) => guestDwordCount;
public void DeclareResources() { }
public void DeclareFunctionResources() { }
public void BeginBlock() { }
public void BeforeInstruction(Gen5ShaderInstruction instruction) { }
public void EndBlock() { }
public void InitializeMasks()
{
var context = _context;
if (context._subgroupInvocationIdInput != 0)
{
StoreWaveMask(106, context._module.ConstantBool(false));
StoreWaveMask(126, context._module.ConstantBool(true));
return;
}
context.StoreS64(106, context._module.Constant64(context._ulongType, 0));
context.StoreS64(126, context._module.Constant64(context._ulongType, 1));
}
public uint BooleanToWaveMask(uint condition)
{
var context = _context;
if (context._subgroupInvocationIdInput == 0)
{
return context._module.AddInstruction(
SpirvOp.Select,
context._ulongType,
condition,
CurrentLaneBit(),
context._module.Constant64(context._ulongType, 0));
}
var ballot = context._module.AddInstruction(
SpirvOp.GroupNonUniformBallot,
context._uvec4Type,
context.UInt(3),
condition);
var low = context._module.AddInstruction(SpirvOp.CompositeExtract, context._uintType, ballot, 0);
var widened = context._module.AddInstruction(SpirvOp.UConvert, context._ulongType, low);
return context._module.AddInstruction(
SpirvOp.Select,
context._ulongType,
context._module.AddInstruction(
SpirvOp.UGreaterThanEqual,
context._boolType,
context.GuestWaveLane(),
context.UInt(32)),
context.ShiftLeftLogical64(widened, context._module.Constant64(context._ulongType, 32)),
widened);
}
public uint SubgroupAny(uint condition) =>
_context._subgroupInvocationIdInput == 0
? condition
: _context._module.AddInstruction(
SpirvOp.GroupNonUniformAny,
_context._boolType,
_context.UInt(3),
condition);
public uint CurrentLaneBit()
{
var context = _context;
if (context._subgroupInvocationIdInput == 0)
{
return context._module.Constant64(context._ulongType, 1);
}
return context.ShiftLeftLogical64(
context._module.Constant64(context._ulongType, 1),
context._module.AddInstruction(SpirvOp.UConvert, context._ulongType, context.GuestWaveLane()));
}
public uint BroadcastFirstActive(uint value)
{
var context = _context;
if (context._subgroupInvocationIdInput == 0)
{
return value;
}
var activeLanes = context._module.AddInstruction(
SpirvOp.GroupNonUniformBallot,
context._uvec4Type,
context.UInt(3),
context.Load(context._boolType, context._exec));
var activeLow = context._module.AddInstruction(SpirvOp.CompositeExtract, context._uintType, activeLanes, 0);
return context._module.AddInstruction(
SpirvOp.GroupNonUniformBroadcast,
context._uintType,
context.UInt(3),
value,
context.Ext(73, context._uintType, activeLow));
}
public uint BroadcastLane(uint value, uint lane) =>
throw new InvalidOperationException("a half-wave program reads no other lane");
public uint BroadcastValue(uint writer, uint value, uint lane) =>
throw new InvalidOperationException("a half-wave program writes no other lane");
public uint WaveMaskAny(uint register, uint laneActive) =>
SubgroupAny(_context.Load(_context._boolType, laneActive));
public uint CurrentExecMask() =>
BooleanToWaveMask(_context.Load(_context._boolType, _context._exec));
public uint NormalizeExecMask(uint mask) => mask;
public void StoreWaveMask(uint register, uint condition) =>
_context.StoreS64(register, BooleanToWaveMask(condition));
}
}
}

6
src/SharpEmu.ShaderCompiler.Vulkan/Gen5SpirvTranslator.Resources.cs
View File

@ -128,6 +128,12 @@ public static partial class Gen5SpirvTranslator
_waveLowering = new NativeWave64Lowering(this);
_guestLaneFromSubgroup = true;
}
else if (_stage == Gen5SpirvStage.Compute &&
request.HostComputeSubgroup32 &&
CanRunHalfWaves(request, _physicalAxisOfLogical))
{
_waveLowering = new HalfWave64Lowering(this);
}
else if (_stage == Gen5SpirvStage.Compute && request.HostComputeSubgroup32 && PairedWave64Enabled)
{
_pairedLanes = true;

2
src/SharpEmu.ShaderCompiler.Vulkan/Gen5SpirvTranslator.cs
View File

@ -7983,7 +7983,7 @@ public static partial class Gen5SpirvTranslator
_uintType,
UInt(3),
value,
_pairedLanes
_pairedLanes || _waveLowering is HalfWave64Lowering
? BitwiseAnd(lane, UInt(PairedHalfLaneCount - 1))
: lane);