You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "MasterJH5574 (via GitHub)" <gi...@apache.org> on 2023/07/05 07:07:45 UTC
[GitHub] [tvm] MasterJH5574 opened a new pull request, #15236: [TIR][Schedule] Scoped CacheRead/Write producing compact region
MasterJH5574 opened a new pull request, #15236:
URL: https://github.com/apache/tvm/pull/15236
This PR enhances CacheRead/Write so that when a cache operation is performed under an inner block, the generated cache buffer will have the shape as compact as possible, by region consumption analysis.
The motivation of this change comes from the needs of dynamic shape TIR scheduling, in which case we may isolate a "static shape" internal block using blockize, and do further scheduling inside the internal block. For such cases, the current CacheRead/Write inside the static-shape block will still produce dynamic-shape cache buffers, which is not ideal for analysis and subsequent scheduling.
One thing that worths noting is that, to ensure the IR correctness after inserting the cache block, we will only compact the cache buffer when all the consumer blocks of the read buffer (for CacheRead) or the write buffer (for CacheWrite) are children blocks of the cache block insertion location. Otherwise we will insist allocating the full-size cache buffer.
Co-authored-by: Bohan Hou <sp...@gmail.com>
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] tvm-bot commented on pull request #15236: [TIR][Schedule] Scoped CacheRead/Write producing compact region
Posted by "tvm-bot (via GitHub)" <gi...@apache.org>.
tvm-bot commented on PR #15236:
URL: https://github.com/apache/tvm/pull/15236#issuecomment-1621157019
<!---bot-comment-->
Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from [Reviewers](https://github.com/apache/incubator-tvm/blob/master/CONTRIBUTORS.md#reviewers) by @-ing them in a comment.
<!--bot-comment-ccs-start-->
* cc @Hzfengsy, @junrushao, @quic-sanirudh, @shingjan <sub>See [#10317](https://github.com/apache/tvm/issues/10317) for details</sub><!--bot-comment-ccs-end-->
<sub>Generated by [tvm-bot](https://github.com/apache/tvm/blob/main/ci/README.md#github-actions)</sub>
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] MasterJH5574 commented on a diff in pull request #15236: [TIR][Schedule] Scoped CacheRead/Write producing compact region
Posted by "MasterJH5574 (via GitHub)" <gi...@apache.org>.
MasterJH5574 commented on code in PR #15236:
URL: https://github.com/apache/tvm/pull/15236#discussion_r1252642354
##########
src/tir/schedule/primitive.h:
##########
@@ -105,7 +105,7 @@ TVM_DLL std::vector<int64_t> SamplePerfectTile(
* The sampled tile size will be partitioned into two parts. The second part has a guarantee
* that their extent's product have a factor of `innerpart_factor`. The first part is loops at
* [0, partition_pos); the second part is loops at [partition_pos, n) and we will have
- * `innerpart_factor` | \prod_{l=partition_pos}^{n-1} l.extent
+ * `innerpart_factor` | prod_{l=partition_pos}^{n-1} l.extent
Review Comment:
Updating this since Clang will warn
```
1 warning generated.
In file included from /home/ruihangl/tvm/src/tir/schedule/primitive/for_kind.cc:19:
In file included from /home/ruihangl/tvm/src/tir/schedule/primitive/../utils.h:49:
/home/ruihangl/tvm/src/tir/schedule/primitive/.././primitive.h:108:26: warning: unknown command tag name [-Wdocumentation-unknown-command]
* `innerpart_factor` | \prod_{l=partition_pos}^{n-1} l.extent
^~~~~~
```
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] junrushao commented on a diff in pull request #15236: [TIR][Schedule] Scoped CacheRead/Write producing compact region
Posted by "junrushao (via GitHub)" <gi...@apache.org>.
junrushao commented on code in PR #15236:
URL: https://github.com/apache/tvm/pull/15236#discussion_r1252649643
##########
src/tir/schedule/primitive/cache_read_write.cc:
##########
@@ -242,22 +246,48 @@ Block MakeCacheStage(const BufferRegion& cache_region, CacheStageInfo* info,
for (const Range& axis_range : cache_region->region) {
Var loop_var("ax" + std::to_string(loop_vars.size()), axis_range->extent.dtype());
loop_vars.push_back(loop_var);
- iter_values.push_back(axis_range->min + loop_var);
+ iter_values.push_back(cache_full_region ? (axis_range->min + loop_var) : loop_var);
}
// block variables
Array<IterVar> block_vars;
// block access region for read/write buffers
- Region access_region;
+ Region read_access_region, write_access_region;
// indices used in block body
- Array<PrimExpr> access_indices;
+ Array<PrimExpr> read_access_indices, write_access_indices;
Review Comment:
nit: split them into multiple lines
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] tqchen merged pull request #15236: [TIR][Schedule] Scoped CacheRead/Write producing compact region
Posted by "tqchen (via GitHub)" <gi...@apache.org>.
tqchen merged PR #15236:
URL: https://github.com/apache/tvm/pull/15236
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org