Skip to content

apache/tvm

main
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
21 branches 21 tags
Code

Latest commit

@MasterJH5574
MasterJH5574 [MetaSchedule] PostProc not rewriting unroll for purely spatial block (…
8714656 Apr 17, 2023
[MetaSchedule] PostProc not rewriting unroll for purely spatial block (… 
…#14642)

This PR adds a behavior to the MetaSchedule post-processor
RewriteParallelVectorizeUnroll, so that it does not annotate spatial
blocks with the unroll annotation.

This is because the optimization for spatial blocks (standalone in a
GPU kernel, for example) can be done by purely thread binding. As a
result, annotating loop unrolling for spatial blocks does not help.
In some case where the unroll factor is very large (e.g., 512 or 1024),
unrolling the spatial blocks will consume much time during the kernel
compilation and introduces unnecessary overhead.

Therefore, we turn off the behavior of unrolling spatial blocks.
8714656

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
.github
[ci] Disable Windows-Static-Runtime (#13951)
February 10, 2023 12:31
3rdparty
[microTVM]Add MLPerfTiny test harness (#14309)
March 22, 2023 14:31
apps
[AutoTVM] New rank-binary loss_type for the new xgboost >= 2.0.0 beha…
April 11, 2023 08:23
ci
fix: deploy ci (#14607)
April 13, 2023 16:23
cmake
[BYOC] DNNL C_SRC Fix (#14267)
March 10, 2023 17:33
conda
Update to v0.13.dev0 (#14544)
April 9, 2023 12:46
configs
[TVMC] Add --config argument for config files (#11012)
April 19, 2022 11:50
docker
[CI] Add JAX deps in Dockerfiles (#14550)
April 12, 2023 10:18
docs
[Docs] Fix typo in the Vitis AI Integration docs (#14585)
April 11, 2023 13:40
gallery
[AutoTVM] New rank-binary loss_type for the new xgboost >= 2.0.0 beha…
April 11, 2023 08:23
golang
Fix typo in golang sample (#13476)
November 28, 2022 19:35
include/tvm
[TIR][Hexagon] Use the "target" value in T.func_attr for VTCM limit (#…
April 13, 2023 14:16
jvm
[tvm4j] Fix tvm4j build on MacOS (#13370)
November 15, 2022 12:35
licenses
[Profiler] Allow user to flush L2 cache in time_evalutor function f…
January 10, 2023 10:17
python
Fix bug about wrong attribute name (#14636)
April 16, 2023 12:50
rust
Expose attrs argument of "ir.IRModule" to Rust bindings
April 6, 2023 19:39
src
[MetaSchedule] PostProc not rewriting unroll for purely spatial block (…
April 17, 2023 12:01
tests
[MetaSchedule] PostProc not rewriting unroll for purely spatial block (…
April 17, 2023 12:01
vta
[AutoTVM] New rank-binary loss_type for the new xgboost >= 2.0.0 beha…
April 11, 2023 08:23
web
Update to v0.13.dev0 (#14544)
April 9, 2023 12:46
.asf.yaml
[skip ci][ci][docker] Add cross compilation libs (#13800)
January 17, 2023 15:02
.clang-format
add .clang-format (#2395)
January 8, 2019 13:08
.gitattributes
[ci] Split Jenkinsfile into platform-specific jobs (#13300)
December 6, 2022 13:52
.gitignore
[tir] Add line level debug info (#13012)
January 6, 2023 16:03
.gitmodules
[TOOL][NATIVE] Android native application for deploy and run (#13791)
January 24, 2023 16:11
.pre-commit-config.yaml
[CI] make pre-commit hooks to run on every push instead of every comm…
August 31, 2021 15:42
CMakeLists.txt
[microTVM]Refactor crt_config.h header file generation (#13955)
February 15, 2023 15:29
CONTRIBUTORS.md
[COMMUNITY] Sunghyun Park -> Reviewer (#14622)
April 14, 2023 13:59
KEYS
[COMMUNITY] Add new key for release signing (#14105)
February 23, 2023 13:03
LICENSE
[TOOL][NATIVE] Android native application for deploy and run (#13791)
January 24, 2023 16:11
Makefile
Fix make format (#11197)
May 2, 2022 15:58
NEWS.md
[ci] Lint for trailing newlines and spaces (#13058)
October 18, 2022 23:36
NOTICE
Update to 0.10.0 (#12190)
July 27, 2022 13:04
README.md
[Tutorial] Fix formatting, grammar, dead link (#9281)
October 23, 2021 09:17
conftest.py
[CI] Deduplicate and clean XML test reports (#12332)
August 8, 2022 11:40
mypy.ini
[ci] Lint for trailing newlines and spaces (#13058)
October 18, 2022 23:36
pyproject.toml
[Diagnostics][Relay][InferType] Refactor InferType to work on whole m…
October 9, 2020 11:44
version.py
Update to v0.13.dev0 (#14544)
April 9, 2023 12:46
Open Deep Learning Compiler Stack License Getting Started Contribute to TVM Acknowledgement

README.md

Open Deep Learning Compiler Stack

Documentation | Contributors | Community | Release Notes

Build Status WinMacBuild

Apache TVM is a compiler stack for deep learning systems. It is designed to close the gap between the productivity-focused deep learning frameworks, and the performance- and efficiency-focused hardware backends. TVM works with deep learning frameworks to provide end to end compilation to different backends.

License

TVM is licensed under the Apache-2.0 license.

Getting Started

Check out the TVM Documentation site for installation instructions, tutorials, examples, and more. The Getting Started with TVM tutorial is a great place to start.

Contribute to TVM

TVM adopts apache committer model, we aim to create an open source project that is maintained and owned by the community. Check out the Contributor Guide.

Acknowledgement

We learned a lot from the following projects when building TVM.

  • Halide: Part of TVM's TIR and arithmetic simplification module originates from Halide. We also learned and adapted some part of lowering pipeline from Halide.
  • Loopy: use of integer set analysis and its loop transformation primitives.
  • Theano: the design inspiration of symbolic scan operator for recurrence.

About

Open deep learning compiler stack for cpu, gpu and specialized accelerators

tvm.apache.org/

Topics

javascript machine-learning performance deep-learning metal compiler gpu vulkan opencl tensor spirv rocm tvm

Resources

Readme

License

Apache-2.0 license

Code of conduct

Code of conduct

Security policy

Security policy

Stars

9.4k stars

Watchers

383 watching

Forks

3k forks
Report repository

Releases 13

Apache TVM v0.11.1 Latest
Mar 9, 2023
+ 12 releases

Packages

No packages published

Contributors 806

+ 795 contributors

Languages