nnicolosi/Raptor
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

Add register reuse + peft scheduler cost model + Useless merger

Browse Source
This commit is contained in:
ilgeco
2026-06-18 10:56:57 +02:00
parent 852bef7605
commit e083c27d80
13 changed files with 350 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/PIM/Compiler/PimCompilerOptions.cpp
+42
View File
@@ -32,6 +32,31 @@ llvm::cl::opt<PimMemoryReportLevel> pimMemoryReport(
llvm::cl::init(PimMemoryReportNone),
llvm::cl::cat(OnnxMlirOptions));
llvm::cl::opt<PimConvLoweringType> pimConvLowering(
"pim-conv-lowering",
llvm::cl::desc("Convolution lowering strategy for PIM"),
llvm::cl::values(clEnumValN(PimConvLoweringAuto, "auto", "Select the Conv lowering strategy automatically")),
llvm::cl::values(clEnumValN(PimConvLoweringLegacy, "legacy", "Use the legacy explicit-im2col Conv lowering")),
llvm::cl::values(clEnumValN(PimConvLoweringDepthwise, "depthwise", "Force the depthwise-specialized Conv lowering")),
llvm::cl::values(
clEnumValN(PimConvLoweringPackedIm2Col, "packed-im2col", "Use explicit im2col with packed multi-position GEMM")),
llvm::cl::values(clEnumValN(PimConvLoweringStreamedPatch,
"streamed-patch",
"Use streamed/chunked im2col rows without multi-position packing")),
llvm::cl::values(clEnumValN(PimConvLoweringStreamedPacked,
"streamed-packed",
"Use streamed/chunked im2col rows with packed multi-position GEMM")),
llvm::cl::values(clEnumValN(PimConvLoweringOutputChannelTiled,
"output-channel-tiled",
"Force Conv lowering that relies on Gemm output-channel tiling")),
llvm::cl::values(
clEnumValN(PimConvLoweringInputKTiled, "input-k-tiled", "Force Conv lowering that relies on Gemm K tiling")),
llvm::cl::values(clEnumValN(PimConvLoweringTiled2D,
"tiled-2d",
"Force Conv lowering that relies on Gemm 2D K/C tiling")),
llvm::cl::init(PimConvLoweringAuto),
llvm::cl::cat(OnnxMlirOptions));
llvm::cl::opt<bool>
pimOnlyCodegen("pim-only-codegen",
llvm::cl::desc("Only generate code for PIM (assume input is already in bufferized PIM IR)"),
@@ -49,6 +74,23 @@ llvm::cl::opt<bool> useExperimentalConvImpl("use-experimental-conv-impl",
llvm::cl::init(false),
llvm::cl::cat(OnnxMlirOptions));
llvm::cl::opt<uint64_t> pimConvIm2colMaxElements(
"pim-conv-im2col-max-elements",
llvm::cl::desc("Maximum number of im2col elements to materialize globally for one Conv before streaming/chunking"),
llvm::cl::init(1ull << 20),
llvm::cl::cat(OnnxMlirOptions));
llvm::cl::opt<uint64_t> pimConvStreamChunkPositions(
"pim-conv-stream-chunk-positions",
llvm::cl::desc("Maximum number of Conv output positions to materialize in one streamed chunk"),
llvm::cl::init(1024),
llvm::cl::cat(OnnxMlirOptions));
llvm::cl::opt<bool> pimReportConvLowering("pim-report-conv-lowering",
llvm::cl::desc("Emit a bounded Conv lowering report"),
llvm::cl::init(true),
llvm::cl::cat(OnnxMlirOptions));
llvm::cl::opt<bool> pimEmitJson("pim-emit-json",
llvm::cl::desc("Also emit per-core JSON instruction files alongside binary .pim files"),
llvm::cl::init(false),