#include "mlir/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.h"
#include "mlir/Conversion/LLVMCommon/ConversionTarget.h"
#include "mlir/Conversion/LLVMCommon/Pattern.h"
#include "mlir/Conversion/LLVMCommon/TypeConverter.h"
#include "mlir/Dialect/AMDGPU/IR/AMDGPUDialect.h"
#include "mlir/Dialect/AMDGPU/Utils/Chipset.h"
#include "mlir/Dialect/LLVMIR/LLVMDialect.h"
#include "mlir/Dialect/LLVMIR/ROCDLDialect.h"
#include "mlir/IR/BuiltinTypes.h"
#include "mlir/IR/TypeUtilities.h"
#include "mlir/Pass/Pass.h"
#include "llvm/ADT/STLExtras.h"
#include <optional>
namespace mlir {
#define GEN_PASS_DEF_CONVERTAMDGPUTOROCDL
#include "mlir/Conversion/Passes.h.inc"
}
usingnamespacemlir;
usingnamespacemlir::amdgpu;
static Value createI32Constant(ConversionPatternRewriter &rewriter,
Location loc, int32_t value) { … }
static Value createI1Constant(ConversionPatternRewriter &rewriter, Location loc,
bool value) { … }
namespace {
constexpr Chipset kGfx908 = …;
constexpr Chipset kGfx90a = …;
constexpr Chipset kGfx940 = …;
template <typename GpuOp, typename Intrinsic>
struct RawBufferOpLowering : public ConvertOpToLLVMPattern<GpuOp> { … };
struct LDSBarrierOpLowering : public ConvertOpToLLVMPattern<LDSBarrierOp> { … };
struct SchedBarrierOpLowering : public ConvertOpToLLVMPattern<SchedBarrierOp> { … };
}
static Value mfmaConcatIfNeeded(ConversionPatternRewriter &rewriter,
Location loc, Value input) { … }
static void wmmaPushInputOperand(ConversionPatternRewriter &rewriter,
Location loc,
const TypeConverter *typeConverter,
bool isUnsigned, Value llvmInput,
Value mlirInput,
SmallVector<Value, 4> &operands) { … }
static void wmmaPushOutputOperand(ConversionPatternRewriter &rewriter,
Location loc,
const TypeConverter *typeConverter,
Value output, int32_t subwordOffset,
bool clamp, SmallVector<Value, 4> &operands) { … }
static std::optional<StringRef> mfmaOpToIntrinsic(MFMAOp mfma,
Chipset chipset) { … }
static std::optional<StringRef> wmmaOpToIntrinsic(WMMAOp wmma,
Chipset chipset) { … }
namespace {
struct MFMAOpLowering : public ConvertOpToLLVMPattern<MFMAOp> { … };
struct WMMAOpLowering : public ConvertOpToLLVMPattern<WMMAOp> { … };
namespace {
struct ExtPackedFp8OpLowering final
: public ConvertOpToLLVMPattern<ExtPackedFp8Op> { … };
struct PackedTrunc2xFp8OpLowering final
: public ConvertOpToLLVMPattern<PackedTrunc2xFp8Op> { … };
struct PackedStochRoundFp8OpLowering final
: public ConvertOpToLLVMPattern<PackedStochRoundFp8Op> { … };
}
LogicalResult ExtPackedFp8OpLowering::matchAndRewrite(
ExtPackedFp8Op op, ExtPackedFp8OpAdaptor adaptor,
ConversionPatternRewriter &rewriter) const { … }
LogicalResult PackedTrunc2xFp8OpLowering::matchAndRewrite(
PackedTrunc2xFp8Op op, PackedTrunc2xFp8OpAdaptor adaptor,
ConversionPatternRewriter &rewriter) const { … }
LogicalResult PackedStochRoundFp8OpLowering::matchAndRewrite(
PackedStochRoundFp8Op op, PackedStochRoundFp8OpAdaptor adaptor,
ConversionPatternRewriter &rewriter) const { … }
struct AMDGPUDPPLowering : public ConvertOpToLLVMPattern<DPPOp> { … };
struct ConvertAMDGPUToROCDLPass
: public impl::ConvertAMDGPUToROCDLBase<ConvertAMDGPUToROCDLPass> { … };
}
void mlir::populateAMDGPUToROCDLConversionPatterns(LLVMTypeConverter &converter,
RewritePatternSet &patterns,
Chipset chipset) { … }
std::unique_ptr<Pass> mlir::createConvertAMDGPUToROCDLPass() { … }