Tvm: TVM 0.5 Release Note

Created on 17 Jan 2019 · 18Comments · Source: apache/tvm

The release is managed by the TVM PMC, moderators for this release are @ZihengJiang and @yzhliu

The community welcomes new reviewers @nishi-t @were @siju-samuel @jroesch @xqdan @zhiics @grwlf @ajtulloch @vinx13 @junrushao1994 @FrozenGene @liangfu , new committers @srkreddy1238 @eqy @masahi @nhynes @phisiart @merrymercy @Laurawly @adityaatluri @Huyuwei

Change List

New Features

Fully featured 8-bit network support
- 8bit quantizer
- Arbitrary bits quantization algorithm
- Intel cpu support
NVidia GPU 8-bit kernel
- int8 gemm recipe
- int8 conv2d
- Autotvm integration
Automated tuning and scheduling
- AutoTVM optimizations for mobile GPUs
- AutoTVM optimizations for CUDA
- AutoTVM optimizations for x86
Initial release of the differentiable programming IR, Relay
- Generic & informative Relay error reporting #2408
- Relay IR text format support #1781
- Support control flows
- A Normal Form Canonicalization #2251
- Type system support
- End to end compilation
  - Frontend support: Caffe2 #2507 , CoreML #2476 , Keras #2376 , MXNet #2163 , ONNX, TFLite #2365
  - Operator coverage #1799 #2051
- FoldScaleAxis #2020
- SimplifyInference #2033
- CombineParallelConv2D #2089
- InstrumentBoundCheckers pass #2079
- Bind & FoldConstant #2100
- Alter Op Layout #2150
- General OpFusion #2090
CodeGen
- Gcc / g++ compatible C code generator for TVM #2161
- Device type annotation for heterogeneous compilation #2361
- Cache packed func ptr, lift alloca #2070
- Generalize compute to tensor region #1476
Runtime
- Relay interpreter and compiler #1954
- Heterogeneous runtime #1695
- Language bindings: Golang runtime #1470 , Rust runtime #1597
- Add min_repeat_ms to time_evaluator #2200
- Bundled interpreter demonstration #2297
- Enable PlanMemory in the graph runtime #2120
Language Binding
- Rust frontend #2292
VTA
- Improved RPC for VTA #2043
Hybrid python programming model
- Support for scheduling #2416
- Support for Inter-function call #2287
- Backend support https://github.com/dmlc/tvm/pull/2477
TOP
- Initial support for sparse tensor computation
- Improve ARM CPU depthwise convolution performance #2345
- Port winograd ops to relay #2356
Tutorials and docs
- Relay language docs #2232
- Tutorials on how to use SGX backend
- How to write a pass in python
- General lowering flow of TVM
- How to do tensorize
- TFLite frontend tutorial #2508
- Keras seq2seq model for translation tutorial #1815
- Committer guide and tips #2468
- Code review guideline on API designs #2459

Bug-fixes

Fix bug of ignoring user-defined shape in Tensorflow frontend. #2444
Prevent generating 0-dim tensors in Tensorflow frontend. #2326
Fix the bug of incorrect inferred layout when registered alter_layout function returns None. #2101
Fix the return type of read character from a buffer. #2255
Fix subgraph loading from JSON. #1980
Fix incorrect value index in hybrid script. #2268
Fix out-of-bound access when buffer.access_ptr contains non-zero extent. #1939
Add checker for vectorizing over reduce-axis. #1795
Bug fix for fusing injective operation and conv2d. #1603 #1608 #1760 #1622
Fix bilinear mode in topi::nn::upsampling. #1708
Fix the bug with which the Else statement disappears after inject virtual thread pass. #2039
Preventing negation of an undefined Expr in some cases. #1816
Fix CUDA path lookup when multiple CUDA versions are installed. #1788
Fix bugs for SSD sorting and multbox detection. #1578
Fix incorrect elem_offset calculation in Buffer. #1762
Fix rewrite_unsafe_select pass so that LLVM CodeGen generates br instruction only when the type is i1. #2381
Fix incorrect intermediate results in debug mode. #2520
Fix for SSD full GPU support and SSD tutorial update. #2510
Fix LLVM CodeGen br instruction accept not-i1 type issue. #2381
Fixed constant folding for mod operation in CanonicalSimplify. #2487
Fix missing reduction init predicates. #2249
Fix for quantize. #2573
fix storage_rewrite bug when input is big. #2580

Contributors

Code reviewers

@tqchen
@liangfu quantization, relay, topi, frontend
@zhiics relay, runtime, frontend
@nhynes quantization, rust
@Huyuwei frontend
@yzhliu relay, frontend, perf
@xqdan hybrid script, tvm/lang
@ZihengJiang relay
@vinx13 relay/pass, topi
@masahi relay/pass, frontend, doc, topi
@grwlf frontend, topi, relay, quantization
@tmoreau89 vta, relay, backend, runtime
@kazum frontend
@nishi-t frontend, topi
@PariksheetPinjari909 frontend
@jroesch relay, frontend, doc
@srkreddy1238 relay/op, frontend
@siju-samuel relay/op, frontend
@junrushao1994 relay
@icemelon9 relay, perf, tvm/lang, codegen
@ajtulloch relay, frontend
@alex-weaver relay
@kevinthesun hybrid script, topi, relay
@Laurawly topi
@were hybrid script, topi
@FrozenGene frontend, topi, relay/pass
@eqy relay, topi, runtime, rust
@zhreshold frontend, relay/op
@merrymercy relay/op, topi, runtime, frontend
@derisavi-huawei symbolic integers

Code contributions

@tqchen tvm
@vinx13 relay/pass, topi
@siju-samuel topi, relay/op
@merrymercy autotvm, topi, relay/pass
@srkreddy1238 relay/op, frontend/tf
@MarisaKirisame relay
@slyubomirsky relay, docs
@jroesch relay
@nhynes rust
@wweic docs, relay/pass
@yzhliu perf, frontend
@zhiics relay/pass, relay/op, runtime
@were hybrid script
@icemelon9 perf, relay/pass, relay/op
@joshpoll relay, docs
@sgrechanik-h codegen
@kazum frontend/keras, topi
@masahi relay/op, docs
@FrozenGene perf, frontend/tf
@liangdzou docs
@junrushao1994 relay/op
@eqy autotvm, runtime
@apivovarov docs
@ajtulloch runtime, nnpack
@kevinthesun relay/op, perf
@ZihengJiang relay/pass, quantization
@hlu1 nnpack, frontend/caffe2
@lixiaoquan nnvm
@imorinaga frontend/mxnet
@liangfu topi, docs
@xqdan codegen
@PariksheetPinjari909 frontend/darknet
@alexeyr frontend/tensorflow
@Rasterer topi
@yangchen-MS codegen
@anijain2305 relay/op
@grwlf topi
@Huyuwei topi, frontend/keras
@denis0x0D runtime/trace, relay/pass
@Mutinifni codegen
@derisavi relay/pass
@tmoreau89 vta
@Laurawly topi, perf
@zhreshold frontend, topi
@kun-zh codegen
@reminisce relay/op
@ehsanmok rust
@cnuernber perf
@cowanmeg topi, codegen
@yuruofeifei topi

roadmap

Source

ZihengJiang

👍16 🎉5 🚀1

Most helpful comment

@yzhliu the rust frontend is _almost_ ready. It'll probably take a few days of concerted effort to get it ready to merge, but I think it'll make it in time.

nhynes on 28 Jan 2019

👍3 🎉1

All 18 comments

Thanks to everyone who have pushed to last release cycle in the past months. We would like to propose the release of v0.5 on Jan 28th.

We encourage everyone in the community to put their weights to review and vote the release. @dmlc/tvm-team

Please reply this thread on

Things that we missed in the release note
Bugfixes that need to be included in this release

ZihengJiang on 17 Jan 2019

👍1

We have brought the initial support for sparse tensor computation in TOPI (see #1289), though it would be migrated to use hybrid script instead of IR builder in the future.

liangfu on 18 Jan 2019

Hoping to make the rust frontend ready for this release.

ehsanmok on 18 Jan 2019

👍2

We have new frontend TFLite support (see #2365 ).

FrozenGene on 24 Jan 2019

👍3

Pending PR for this release:

Required: #2507 #2476
Good to have: #2508 #2493 #2510 #2292

@ehsanmok as we're approaching the due, do we have chance to get the rust frontend in?

yzhliu on 28 Jan 2019

👍3

BugFix:
[LLVM CodeGen] Solve LLVM CodeGen br instruction accept not-i1 type issue #2381 . It could solve conv2d+ PRelu crash issue on ARM CPU. We have met two threads report this issue on the forum: https://discuss.tvm.ai/t/compile-failure-after-successfull-auto-tune/1561 and https://discuss.tvm.ai/t/debug-failed-to-export-library-with-llvm-on-arm-cpu-when-using-prelu/1006/4

FrozenGene on 28 Jan 2019

👍1

@yzhliu it should be ready if the last issue with CI build resolves quickly and there's no other requested changes which seems there's none.
cc: @nhynes

ehsanmok on 28 Jan 2019

@yzhliu the rust frontend is _almost_ ready. It'll probably take a few days of concerted effort to get it ready to merge, but I think it'll make it in time.

nhynes on 28 Jan 2019

👍3 🎉1

@ZihengJiang Bug fix for SSD full GPU support and SSD tutorial update #2510 could be added to the list.

Thanks to everyone who have pushed to last release cycle in the past months. We would like to propose the release of v0.5 on Jan 28th.

We encourage everyone in the community to put their weights to review and vote the release. @dmlc/tvm-team

Please reply this thread on

Things that we missed in the release note

Bugfixes that need to be included in this release

Laurawly on 1 Feb 2019

@Laurawly @FrozenGene added. Given the current status of the rust frontend, I will add it to the 0.5 release announcement. @nhynes @ehsanmok

ZihengJiang on 2 Feb 2019

👍3

@ZihengJiang The link of TFLite is refered to CoreML, correct link should be #2365

FrozenGene on 2 Feb 2019

@FrozenGene Thanks, my bad. Fixed.

yzhliu on 2 Feb 2019

2477 Can you also add this PR?

were on 14 Feb 2019

👍1

@ZihengJiang @yzhliu would you mind keeping us updated about the release? we've long passed the voting deadline but it's still open!

ehsanmok on 15 Feb 2019

Hey @ehsanmok , sorry about this. We are working on the release https://github.com/dmlc/tvm/pull/2604. One thing is that it would be better to have several bug-fix PRs in the 0.5 release like #2495 #2573 #2580 , which will lead to dismatch with the voted commit number. We are discussing whether we should have another round of vote. @tqchen @yzhliu

ZihengJiang on 15 Feb 2019

I would suggest to start another voting thread and keep that open for two days