ZihengJiang commented on issue #6486: URL: https://github.com/apache/incubator-tvm/issues/6486#issuecomment-698661161
## Operator Coverage - Allow empty tensor for reshape, tile and strided_slice [#4618](https://github.com/apache/incubator-tvm/issues/4618) - Fix meaning of conv2d_transpose output_padding parameter"; [#4708](https://github.com/apache/incubator-tvm/issues/4708) - Remove cpp upsampling and resize op [#4769](https://github.com/apache/incubator-tvm/issues/4769) - upsample operator 'NCHWinic' format support. [#4791](https://github.com/apache/incubator-tvm/pull/4791) - Injective schedule improvement [#4786](https://github.com/apache/incubator-tvm/pull/4786) - Enable vectorization on fp16 type [#4867](https://github.com/apache/incubator-tvm/pull/4867) - Support for Int8 schedules - CUDA/x86 [#5031](https://github.com/apache/incubator-tvm/pull/5031) - New PR to re-add tan to TVM [#5025](https://github.com/apache/incubator-tvm/pull/5025) - Register topi schedule for Relay fast_exp and fast_tanh [#5131](https://github.com/apache/incubator-tvm/pull/5131) - Move Dilation2d from nn to image namespace [#5110](https://github.com/apache/incubator-tvm/pull/5110) - Use Thrust sort for argsort and topk [#5097](https://github.com/apache/incubator-tvm/pull/5097) - Conv2d and Dense ops support on Tensor Core [#5099](https://github.com/apache/incubator-tvm/pull/5099) - Setting workload correctly for Depthwise Spatial conv ARM. [#5182](https://github.com/apache/incubator-tvm/pull/5182) - Adding a few missing math intrin [#5011](https://github.com/apache/incubator-tvm/pull/5011) - Missing vectorize for depthwise conv2d. [#5196](https://github.com/apache/incubator-tvm/pull/5196) - [TOPI] Using x86 schedules for ARM conv2d ([#5334](https://github.com/apache/incubator-tvm/pull/5334)) - [TOPI-ARM] Do not alter layout if layout is NHWC ([#5350](https://github.com/apache/incubator-tvm/pull/5350)) - [TOPI] Setting workload correctly for Depthwise Spatial conv ARM. ([#5182](https://github.com/apache/incubator-tvm/pull/5182)) - [Relay][OP] Add fast_erf implementation ([#5241](https://github.com/apache/incubator-tvm/pull/5241)) - [Topi] Tensorcore support for Conv3D ([#5284](https://github.com/apache/incubator-tvm/pull/5284)) - [intrin] a few more math functions ([#5468](https://github.com/apache/incubator-tvm/pull/5468)) - [Intrinsic] Add log1p, ldexp, atan2, hypot, nextafter, copysign ([#5312](https://github.com/apache/incubator-tvm/pull/5312)) - [relay][topi] Add operation relay.nn.dilate() which calls topi.nn.dilate() ([#5331](https://github.com/apache/incubator-tvm/pull/5331)) - [Topi x86] Missing vectorize for depthwise conv2d. ([#5196](https://github.com/apache/incubator-tvm/pull/5196)) - [TOPI x86] Adding unroll_kw config option for depthwise conv2d. (#5197) - [Topi] Breakdown [topi.cc](http://topi.cc/) into smaller files ([#5253](https://github.com/apache/incubator-tvm/pull/5253)) - ReduceLogSumExp Operator support [#5453](https://github.com/apache/incubator-tvm/pull/5453) - Math ops added [#5502](https://github.com/apache/incubator-tvm/pull/5502) - Enable blocking format in x86 conv2d and fold scale axis [#5357](https://github.com/apache/incubator-tvm/pull/5357) - Add operation gather to relay. [#5716](https://github.com/apache/incubator-tvm/pull/5716) - Add storage_order ignore in pooling layer. [#5781](https://github.com/apache/incubator-tvm/pull/5781) - Fix bifrost spatial packing conv2d auto tune [#5684](https://github.com/apache/incubator-tvm/pull/5684) - Fix reshape usage in ARM schedule [#5732](https://github.com/apache/incubator-tvm/pull/5732) - Block sparse dense on cuda [#5746](https://github.com/apache/incubator-tvm/pull/5746) - Improve CUDA softmax scheduling [#5600](https://github.com/apache/incubator-tvm/pull/5600) - block sparse dense on cuda [#5746](https://github.com/apache/incubator-tvm/pull/5746) - pass-by-value -> pass-by-const-reference [#5783](https://github.com/apache/incubator-tvm/pull/5783) - Using MKL blas for quantized dense [#6115](https://github.com/apache/incubator-tvm/pull/6115) - topi -> tvm/topi [#6186](https://github.com/apache/incubator-tvm/pull/6186) - Use auto-tuner to improve conv2d_gemm performance [#6117](https://github.com/apache/incubator-tvm/pull/6117) - Improve CUDA conv2d_transpose_nchw [#4762](https://github.com/apache/incubator-tvm/issues/4762) - Add CUDA conv2d for NHWC layout [#4737](https://github.com/apache/incubator-tvm/issues/4737) - conv3d_ndhwc schedule [#4775](https://github.com/apache/incubator-tvm/issues/4775) - Fast exponent [#4790](https://github.com/apache/incubator-tvm/pull/4790) - Add Scatter to Topi/Relay/ONNX via hybrid script [#5619](https://github.com/apache/incubator-tvm/pull/5619) - Split MKL from BLAS. [#6182](https://github.com/apache/incubator-tvm/pull/6182) - Change the meaning of conv3d_transpose output_padding to match conv{1,2}d_transpose [#6065](https://github.com/apache/incubator-tvm/pull/6065) - Gather op support added [#6013](https://github.com/apache/incubator-tvm/pull/6013) ## Runtime and Backend - Cythonize NDArray.copyto ([#4549](https://github.com/apache/incubator-tvm/pull/4549)) - Unified Object System runtime refactor ([#4578](https://github.com/apache/incubator-tvm/pull/4578), [#4581](https://github.com/apache/incubator-tvm/pull/4581), [#4603](https://github.com/apache/incubator-tvm/pull/4603)) - VM profiler: sort VM stats by time ([#4601](https://github.com/apache/incubator-tvm/pull/4601)) - Update RPC runtime to allow remote module as arg ([#4462](https://github.com/apache/incubator-tvm/pull/4462)) - Refactorying system lib and dso lib into library module ([#4481](https://github.com/apache/incubator-tvm/pull/4481)) - Improve TSIM virtual memory mapping ([#4545](https://github.com/apache/incubator-tvm/pull/4545)) - make adt tag signed [#4605](https://github.com/apache/incubator-tvm/issues/4605) - Improve TVMBackendPackedCFunc to allow return val [#4637](https://github.com/apache/incubator-tvm/issues/4637) - EdgeTPU runtime for Coral Boards [#4698](https://github.com/apache/incubator-tvm/issues/4698) - Fix memory leak when using openMP [#4811](https://github.com/apache/incubator-tvm/issues/4811) - Fix memory leakage of TVMByteArray [#4856](https://github.com/apache/incubator-tvm/pull/4856) - Fix TVM_DLL_EXPORT_TYPED_FUNC to work on Windows [#4955](https://github.com/apache/incubator-tvm/pull/4955) - Fix memory leak when using openMP [#4811](https://github.com/apache/incubator-tvm/pull/4811) - Export GraphRuntime in tvm_runtime.dll [#5002](https://github.com/apache/incubator-tvm/pull/5002) - MISRA-C compliant TVM runtime [#3934](https://github.com/apache/incubator-tvm/pull/3934) - Update the type_keys to reflect the code-org [#5074](https://github.com/apache/incubator-tvm/pull/5074) - Fix AttrEqual for Array and StrMap, double [#5054](https://github.com/apache/incubator-tvm/pull/5054) - Export GraphRuntime in tvm_runtime.dll [#5002](https://github.com/apache/incubator-tvm/pull/5002) - Fix unused-value warning [#5140](https://github.com/apache/incubator-tvm/pull/5140) - crt error handling [#5147](https://github.com/apache/incubator-tvm/pull/5147) - Bundle deployment with static linking [#5158](https://github.com/apache/incubator-tvm/pull/5158) - Implemented kDLCPUPinned (cudaMallocHost) [#4985](https://github.com/apache/incubator-tvm/pull/4985) - Explicitly cast min/max operands [#5090](https://github.com/apache/incubator-tvm/pull/5090) - ref_counter -> ref_counter_ [#5184](https://github.com/apache/incubator-tvm/pull/5184) - Expose runtime::String to Python ([#5212](https://github.com/apache/incubator-tvm/pull/5212)) - [PY][FFI] Refactor runtime.String to subclass str ([#5426](https://github.com/apache/incubator-tvm/pull/5426)) - [RUNTIME] Auto conversion from str to runtime::String in PackedFUnc ([#5251](https://github.com/apache/incubator-tvm/pull/5251)) - [RUNTIME] Improved Packed FFI for optional. ([#5478](https://github.com/apache/incubator-tvm/pull/5478)) - [Hexagon] Add hexagon_posix.cc to TVM/RT sources in the right place (#5346) - [PY][FFI] Refactor runtime.String to subclass str (#5426) - Fix workspace [#5503](https://github.com/apache/incubator-tvm/pull/5503) - Store nullptr PackedFunc as nullptr for better error propagation [#5540](https://github.com/apache/incubator-tvm/pull/5540) - Improve PackedFunc robustness [#5517](https://github.com/apache/incubator-tvm/pull/5517) - Seg fault in WorkspacePool's destructor (#5632) [#5636](https://github.com/apache/incubator-tvm/pull/5636) - Resolve constexpr issue in debug mode. [#5651](https://github.com/apache/incubator-tvm/pull/5651) - Add compile_shared option to linux compile utility fn [#5751](https://github.com/apache/incubator-tvm/pull/5751) - Call sync in CopyFromRemote and CopyToRemote [#5512](https://github.com/apache/incubator-tvm/pull/5512) - Fix the multihop cpu case [#5522](https://github.com/apache/incubator-tvm/pull/5522) - Improve RPCServer AsyncIO support. [#5544](https://github.com/apache/incubator-tvm/pull/5544) - Modularize the RPC infra [#5484](https://github.com/apache/incubator-tvm/pull/5484) - Add compile_shared option to linux compile utility fn [#5751](https://github.com/apache/incubator-tvm/pull/5751) - Overload string operators [#5806](https://github.com/apache/incubator-tvm/pull/5806) - Only initialize required module [#5926](https://github.com/apache/incubator-tvm/pull/5926) - if a param not in input, we should still consume it’s data [#5990](https://github.com/apache/incubator-tvm/pull/5990) - init TVMPackedFunc’s name [#6044](https://github.com/apache/incubator-tvm/pull/6044) - Enable auto conversion String->DLDataType [#6214](https://github.com/apache/incubator-tvm/pull/6214) - Support random fill [#5913](https://github.com/apache/incubator-tvm/pull/5913) - Use new to avoid exit-time de-allocation order [#6292](https://github.com/apache/incubator-tvm/pull/6292) - Add parallel_for support to run a loop in parallel [#6275](https://github.com/apache/incubator-tvm/pull/6275) - Solve ARM BIG.LITTLE heterogeneous multicores [#4747](https://github.com/apache/incubator-tvm/issues/4747) - [RUNTIME] Quick fix PackedFunc String passing ([#5266](https://github.com/apache/incubator-tvm/pull/5266)) - Introduce runtime::String::CanConvertFrom [#5718](https://github.com/apache/incubator-tvm/pull/5718) - Restore the StrMap behavior in JSON/SHash/SEqual [#5719](https://github.com/apache/incubator-tvm/pull/5719) - Support overriding RPCWatchdog termination behavior on Android and other platforms [#6216](https://github.com/apache/incubator-tvm/pull/6216) - Set NDArray::Container.shape_ in NDArray::FromDLPack ([#5301](https://github.com/apache/incubator-tvm/pull/5301)) - Enable x86 cpu cache flush [#5914](https://github.com/apache/incubator-tvm/pull/5914) ## Quantization - Conv2D type checking for kernel per-channel scales. [#4732](https://github.com/apache/incubator-tvm/issues/4732) - Add missing nullptr check [#4773](https://github.com/apache/incubator-tvm/issues/4773) - Doc fix on convolution and dequantize [#4799](https://github.com/apache/incubator-tvm/issues/4799) - Conv2D with dilation support. [#4796](https://github.com/apache/incubator-tvm/issues/4796) - Making scale/zero_points as expr instead of attrs. [#4611](https://github.com/apache/incubator-tvm/issues/4611) - Make calibration faster and more memory usage friendly [#4589](https://github.com/apache/incubator-tvm/issues/4589) - Doc fix on convolution and dequantize [#4799](https://github.com/apache/incubator-tvm/pull/4799) - Conv2D with dilation support. [#4796](https://github.com/apache/incubator-tvm/pull/4796) - Optimize lowering for requantize and FixedPointMultiply. [#4798](https://github.com/apache/incubator-tvm/pull/4798) - More doc fix on quantize and convolution [#4874](https://github.com/apache/incubator-tvm/pull/4874) - Add support for per channel weight scale in dense op [#4880](https://github.com/apache/incubator-tvm/pull/4880) - Add support for quantized models via QNN [#4977](https://github.com/apache/incubator-tvm/pull/4977) [#5013](https://github.com/apache/incubator-tvm/pull/5013) - Support 4D padding. [#5036](https://github.com/apache/incubator-tvm/pull/5036) - [Requantize] Cleanup and Optimize Lowering ([#5286](https://github.com/apache/incubator-tvm/pull/5286)) - [Topi, ARM] Disbale Winograd for quantized tensors. ([#5363](https://github.com/apache/incubator-tvm/pull/5363)) - Adding support for TFLite QnnSubtract operator. ([#5230](https://github.com/apache/incubator-tvm/pull/5230)) - Remove developer facing api from frontend exports. ([#5375](https://github.com/apache/incubator-tvm/pull/5375)) - Add Quantize/Dequantize Partitioning [#5940](https://github.com/apache/incubator-tvm/pull/5940) - Add support for quantized models via QNN [#5016](https://github.com/apache/incubator-tvm/pull/5016) - Quanitze operation expanded to take const argument [#6127](https://github.com/apache/incubator-tvm/pull/6127) - FP32 and Quantized Object Detection Model [#5479](https://github.com/apache/incubator-tvm/pull/5479) - Support CallNode inputs in qnn.concatenate [#5360](https://github.com/apache/incubator-tvm/pull/5360) - QNN support for TFLite 2.1.0 quantized models [#5848](https://github.com/apache/incubator-tvm/pull/5848) ## TE - Tighten split's extent [#4931](https://github.com/apache/incubator-tvm/pull/4931) - Set split node's range to minimum of ext and split factor or split np… [#5044](https://github.com/apache/incubator-tvm/pull/5044) - Support mixing normal and cross-thread reduction ([#5193](https://github.com/apache/incubator-tvm/pull/5193)) - Inline -> te/schedule/operation_inline.h ([#5386](https://github.com/apache/incubator-tvm/pull/5386)) - Create loops according to storage scope and thread hierarchies ([#5190](https://github.com/apache/incubator-tvm/pull/5190)) - Fix import in dump pass ir (#5327) - Scalar support for `te.extern` [#6079](https://github.com/apache/incubator-tvm/pull/6079) ## TIR - IR readability enhancement ([#4501](https://github.com/apache/incubator-tvm/pull/4501)) - Introduce tir::PrimFunc [#5070](https://github.com/apache/incubator-tvm/pull/5070) - Introduce PrimFuncPass. [#5139](https://github.com/apache/incubator-tvm/pull/5139) - [TIR] Enhance Substitute, python bindings for Substitute/PostOrderVisit ([#5400](https://github.com/apache/incubator-tvm/pull/5400)) - [TIR] Remove ProducerConsumer and AllocateNode::new_expr ([#5333](https://github.com/apache/incubator-tvm/pull/5333)) - [IR][TRANSFORM] Enable CopyOnWrite for TIR passes. ([#5309](https://github.com/apache/incubator-tvm/pull/5309)) - [REFACTOR][TIR] Migrate LowerTVMBuiltin, InferFragment, LowerThreadAllreduce, ThreadSync to Pass Manager ([#5213](https://github.com/apache/incubator-tvm/pull/5213)) - [TIR][REFACTOR] Remove te::Tensor dependencies from TIR passes. ([#5372](https://github.com/apache/incubator-tvm/pull/5372)) - [TIR] Refactor MakePackedAPI to target dependent stage. ([#5326](https://github.com/apache/incubator-tvm/pull/5326)) - [REFACTOR] tvm.hybrid -> te.hybrid ([#5223](https://github.com/apache/incubator-tvm/pull/5223)) - [REFACTOR][TIR] Migrate most of low-level build to use the Pass Manager. ([#5225](https://github.com/apache/incubator-tvm/pull/5225)) - [TIR][REFACTOR] Migrate low-level passes in tvm.lower to the Pass Manager ([#5364](https://github.com/apache/incubator-tvm/pull/5364)) - [TIR] Migrate VTA TIR passes to the new pass manager. ([#5397](https://github.com/apache/incubator-tvm/pull/5397)) - [REFACTOR][TIR] Migrate all low-level passes to the Pass Manager. ([#5233](https://github.com/apache/incubator-tvm/pull/5233)) - [REFACTOR][TIR] Introduce ExprDeepEqual, Remove IRDeepCompare (#5206) - [TIR][REFACTOR] RewriteForTensorCore -> te/schedule (#5379) - [TIR][REFACTOR] Remove ir_pass in favor of analysis/transform. (#5415) - text format printer considering future parsing use [#5483](https://github.com/apache/incubator-tvm/pull/5483) - Remove buffer params from pass config. [#5652](https://github.com/apache/incubator-tvm/pull/5652) - std::string -> String Migration in TIR nodes [#5596](https://github.com/apache/incubator-tvm/pull/5596) - Remove CallNode.call_type in favor of attribute. [#5937](https://github.com/apache/incubator-tvm/pull/5937) - Remove legacy HoistIfThenElse [#5944](https://github.com/apache/incubator-tvm/pull/5944) - Improve Let/LetStmt support. [#5949](https://github.com/apache/incubator-tvm/pull/5949) - Refine side effect analysis. [#5954](https://github.com/apache/incubator-tvm/pull/5954) - Provide->ProducerStore, Realize->ProducerRealize. [#5750](https://github.com/apache/incubator-tvm/pull/5750) - Migrate the tvm/tir/expr.h to constructor [#5773](https://github.com/apache/incubator-tvm/pull/5773) - Migrate tir/stmt.h to use constructor. [#5778](https://github.com/apache/incubator-tvm/pull/5778) - Cleanup unused classes [#5789](https://github.com/apache/incubator-tvm/pull/5789) - Add tir prefix to type keys [#5802](https://github.com/apache/incubator-tvm/pull/5802) - Enhance VerifyGPUCode [#6194](https://github.com/apache/incubator-tvm/pull/6194) - Enforce buffer pointer var type to be consistent with dtype. [#6317](https://github.com/apache/incubator-tvm/pull/6317) - Create a StringImm reference type [#4806](https://github.com/apache/incubator-tvm/issues/4806) - Add `init` member to ReduceNode [#6138](https://github.com/apache/incubator-tvm/pull/6138) - Add dump and print for debugging (NFC) [#5207](https://github.com/apache/incubator-tvm/pull/5207) - Streamline Function Attr interface. [#5045](https://github.com/apache/incubator-tvm/pull/5045) - alpha_equal to structural_equal [#5161](https://github.com/apache/incubator-tvm/pull/5161) - Remove AttrsEqual and AttrsHash related code [#5169](https://github.com/apache/incubator-tvm/pull/5169) - [NODE] General serialzation of leaf objects into bytes. ([#5299](https://github.com/apache/incubator-tvm/pull/5299)) - [POC][IR] Initial stab at std::string->String upgrade ([#5438](https://github.com/apache/incubator-tvm/pull/5438)) - [TIR] Make lower_warp_memory support extent(threadIdx.x) < warp_size ([#5307](https://github.com/apache/incubator-tvm/pull/5307)) - [TIR][PASS] dtype rewrite for indexing variables ([#5092](https://github.com/apache/incubator-tvm/pull/5092)) - [PYTHON] Enhance with_attr API, cleanup MakeAPILegacy in testcases ([#5335](https://github.com/apache/incubator-tvm/pull/5335)) - [PYTHON] Make IntImm more like an integer ([#5232](https://github.com/apache/incubator-tvm/pull/5232)) - [REFACTOR][IR] Move to runtime::String ([#5276](https://github.com/apache/incubator-tvm/pull/5276)) - [REFACTOR][IR] kExternalSymbol -> kGlobalSymbol ([#5211](https://github.com/apache/incubator-tvm/pull/5211)) - [REFACTOR][IR] Remove PrimExpr from String ([#5311](https://github.com/apache/incubator-tvm/pull/5311)) - IRModule is updated with String [#5523](https://github.com/apache/incubator-tvm/pull/5523) - IR is updated with String [#5547](https://github.com/apache/incubator-tvm/pull/5547) - Streamline ir/op Registry [#5609](https://github.com/apache/incubator-tvm/pull/5609) - Migrate IRModule ObjectRef to not-null [#5654](https://github.com/apache/incubator-tvm/pull/5654) - Migrate BuildConfig to PassContext. [#5668](https://github.com/apache/incubator-tvm/pull/5668) - relay.op.Op -> tvm.ir.Op [#5705](https://github.com/apache/incubator-tvm/pull/5705) - Separate ArgTypeCode from DLDataTypeCode [#5730](https://github.com/apache/incubator-tvm/pull/5730) - Remove legacy compute_expr.h [#5738](https://github.com/apache/incubator-tvm/pull/5738) - Call::Halide => ProducerLoad, DSL/TIR decouple. [#5743](https://github.com/apache/incubator-tvm/pull/5743) - Provide->ProducerStore, Realize->ProducerRealize. [#5750](https://github.com/apache/incubator-tvm/pull/5750) - Migrate the tvm/tir/expr.h to constructor [#5773](https://github.com/apache/incubator-tvm/pull/5773) - Migrate tir/stmt.h to use constructor. [#5778](https://github.com/apache/incubator-tvm/pull/5778) - Migrate all Object construction to constructor. [#5784](https://github.com/apache/incubator-tvm/pull/5784) - Cleanup unused classes [#5789](https://github.com/apache/incubator-tvm/pull/5789) - Finish std::string->String updates [#5793](https://github.com/apache/incubator-tvm/pull/5793) - Add tir prefix to type keys [#5802](https://github.com/apache/incubator-tvm/pull/5802) - Change [Call.name](http://call.name/) to Call.op(RelayExpr) [#5863](https://github.com/apache/incubator-tvm/pull/5863) - Range/IntSet API style consistency. [#5953](https://github.com/apache/incubator-tvm/pull/5953) - Separate ArgTypeCode from DLDataTypeCode [#5730](https://github.com/apache/incubator-tvm/pull/5730) - Migrate all Object construction to constructor. [#5784](https://github.com/apache/incubator-tvm/pull/5784) - Finish std::string->String updates [#5793](https://github.com/apache/incubator-tvm/pull/5793) - Unify StrMapNode and MapNode [#5687](https://github.com/apache/incubator-tvm/pull/5687) ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
