1. Rebased concatenation optimization.#11087
Closed
shtinsa wants to merge 204 commits intoapache:mainfrom
Closed
Conversation
2. Workaround to reslolve issue with tvm.tir.expr.SizeVar added
Add the `configs` directory to be part of the installed version of TVM in the setuptools configuration, and introduce a new function to load the `configs` directory from the right paths both when TVM is locally installed for development, as well as, when it is installed as a package.
* Fix bug allowing microTVM to be used with Arduino version v0.20 and
above (see changes to _parse_connected_boards) and adds relevant unit
tests.
* Only perform version check when calling build or flash (things that
actually require arduino-cli), and adds relevant unit tests.
* Only raise a warning if the arduino-cli version present is below the
min version (previously any version other than v0.18 would cause an
error).
* Change version comparison to use version.check, like the rest of TVM
…anspose (apache#10952) * Support input scale and zp of 1-element vector in qnn.conv2d_transpose * Lint
* support Pool layout is CHW * fix lint test * change the if condition
Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
…che#11080) * [RPC] Don't use existence of USE_HEXAGON_SDK as enablement check Use USE_HEXAGON to check if Hexagon support is enabled or not. This fixes apache#11059. * Restart CI
Retrigger CI. Address issues. Retrigger CI.
Previously, the size of the memory which should be allocated was calculated as multiplication width on height. It doesn't work well in case when one texture has big size in height and the next one big size in width. We tried to reuse the allocated memory and every time when the next texture with big size was used we reallocated the previous one. It has huge impact on the performance. Now we check two dimensions independently. So, in this case we will check both dimensions and it helps us to avoid the situation with cyclic memory reallocation.
* unary op for resize2d and test * renamed test * added log in quantized form * black'd some files * changed suggested commentary
…11060) * [TVMScript] Allow `val = buf[index]` without type annotation Other instances of `var = expr` were previously allowed without requiring a type annotation, by using the dtype of the expression as the dtype of `var`. This behavior didn't work for `buf[index]` expressions, which are internally represented as `BufferSlice` python objects, and only converted to `BufferLoad` primexprs when used as an expression. This commit adds a `dtype` property to `BufferSlice`, allowing `buf[index]` to be used in a let statement without a type annotation. * Reverted a wider change Automatically adding a type annotation to Var if it could be determined from the dtype let the unit test directly compare the annotated and unannotated versions of buffer load. Unfortunately, it also broke 54 unrelated tests, so that change is removed from this PR.
* [TIR] StmtFunctor RenewDefs In this PR, I introduce a StmtFunctor `RenewDefs` for deep copy all definition nodes in PrimFunc (including Var, Buffer, and IterVar). This functor can create a new PrimFunc with the same behavior as the old one but contains different Nodes. This Functor may help TIR fusion or inline multiple PrimFuncs * add ut * address comments * address comments * lint * lint
* Check if the requested memory info is defined before using it. * Address review comment to add warning when MemoryInfo for scope is undefined.
* [ROOFLINE] Roofline analysis over RPC Run roofline analysis on remote devices if requested. Peak flops and peak bandwidth estimation are done on the remote device. * allocate testing arrays directly on device and randomly fill * forgot to include remote * lower flops ratio, machine may be using multiple threads * forgot fill
- Fix issue where `CMAKE_C[XX]_COMPILER` isn't propagated into the build configuration for `x86_tvm_runtime_rpc`.
* Add USMP tests * Address Chris comments * Address Chris comment on assert * trigger
…che#11290) * [FRONTEND][PYTORCH] Support fo nn.SiLU added * torch.bool added to torch convert_torch_dtype_map
* add relay.f.frontend.fm_oneflow support cnns * support cuda * fix mobilenetv2 and reviews * fix: model without meta info * support eager and yolo, add test * fix: license * add: tutorials * fix: support new graph * fix some comments * refine * fix concat op convert bug * refine * refine * change cuda to cpu * fix bug * fix ci error in tvm * fix pylint check * delete useless file * add skimage package in docker * fix ci error * fix bug * add oneflow fronted test in ci * merge conflict * fix tutorial * try to find error in ci * revert * merge conflict * black oneflow * Delete from_oneflow.py * restruct oneflow fronted * support vision-transformer * black format * update black version and reformat * fix ci error * fix doc error * fix gpu fronted test failed Co-authored-by: hhhfccz <hjk1938927583@163.com>
This PR allowed users to set logging level without giving a logger config. Previous implementation hard-coded `logging.INFO` as the default logging level and requires a logger config to change it. Now the logging level and handlers can be inherited from the current `tvm.meta_schedule` logger setting.
* support represent ramp as index slice in tvmscript * fix testcase's comment, check slice lanes instead of extent
* fix cast from bfloat16 * fix cast to bfloat16 test as well * clean up comments * lint * add comment Co-authored-by: Margaret Qian <mqian@octoml.ai>
…on' bug of roi_align (apache#11322)
…pe (apache#11076) * support ConvTranspose explicitly specified output_shape * fix unit test case * fix lint test * retest * fix code error * fix lint test * update test * retest * fix test onnx official tests
Signed-off-by: Alexander Peskov <peskovnn@gmail.com>
…pache#11255) * [TIR] Propogate storage scope of undefined vars in SplitHostDevice. * Test global.texture for input, output, and intermediate buffers.
…apache#11317) * [TIR] Support affine expressions as indices in reverse compute inline * fix trivial iterators
Co-authored-by: Yuanjing Shi <yuanjing@octoml.ai> Co-authored-by: Yuanjing Shi <yuanjing@octoml.ai>
shtinsa
force-pushed
the
sshtin/concat_opt_rebased
branch
from
705f65e to
5a2cfea
Compare
areusch
added
needs-triage
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from Reviewers by @ them in the pull request thread.