Commits · 6e6e7f3aaf8c61abc4dbd8f56b9f2e7faa7bfcd4 · gaoqiong / MIGraphX

06 Nov, 2019 1 commit
- Comment out clang args for now · 6e6e7f3a
  Paul authored Nov 06, 2019
  
  6e6e7f3a
05 Nov, 2019 1 commit
- Improve static analysis · daa86f8c
  Paul authored Nov 05, 2019
  
  daa86f8c
04 Nov, 2019 2 commits

Use multi_index for reductions (#400) · 3e0496fb

Paul Fultz II authored Nov 04, 2019

* Add functions to do multi-index for local strides as well

* Formatting

* Use same multi-index path for block_reduce

* Formatting

* Use multi-index calc in reduce

* Formatting

* Fix warning

* Fix compiler warning

* Disable some tidy checks

3e0496fb

Fix accuraccy issue in resnet50 (#395) · 78c83426

Paul Fultz II authored Nov 04, 2019

* Fix bug in eliminate_concat

* Formatting

* Skip context_free operators

* Formatting

* Fix unit test

* Formatting

78c83426

30 Oct, 2019 1 commit

Enable scheduler for 1 stream (#399) · ca17bcd6

Paul Fultz II authored Oct 30, 2019

* Enable scheduler for 1 stream

* Formatting

* Improve performance of sorting

* Formatting

* Adjust the weight calculation

* Formatting

* Simplify formula

* Formatting

* Avoid division by zero

* Fix scheduler test

* Check for either 1 or 2

* Check for waits when order may change

* Formatting

ca17bcd6

28 Oct, 2019 1 commit
- Sort instruction in perf report by time (#398) · 9799d373
  Paul Fultz II authored Oct 28, 2019
  
  9799d373
25 Oct, 2019 2 commits

Cpu conv softmax simplify impl (#397) · 522da00b

Shucai Xiao authored Oct 25, 2019

* simplify cpu implementation of the convolution, softmax, and logsoftmax

* clang format

* fix cppcheck error

* improve code coverage

522da00b

Support initializer not in inputs (#396) · 1f4f6d44

Shucai Xiao authored Oct 25, 2019

* support onnx file with initializer data not an input

* fix format

* fix review comments and format issue

* format

* reorder alphabetically

1f4f6d44

24 Oct, 2019 1 commit

Pad calculation fix for nasnet (#393) · 1bacc1df

kahmed10 authored Oct 24, 2019

* fix pad calc

* simplify ceil calc and remove extra vars

* change dilation calculation, add tests

* formatting

* formatting

1bacc1df

21 Oct, 2019 1 commit
- Print graph from the driver (#389) · 23124b09
  Paul Fultz II authored Oct 21, 2019
```
* Print graph from the driver

* Formatting
```
  23124b09
16 Oct, 2019 3 commits

Flatten nested concats (#391) · 50e6d5eb
Paul Fultz II authored Oct 16, 2019
```
* Flatten nested concats

* Formatting

* Rename tests
```
50e6d5eb
remove binaries replaced by driver (#388) · 756c5908
kahmed10 authored Oct 16, 2019
```
* remove binaries replaced by driver

* remove source files

* add back env var
```
756c5908

Fuse the add of two convolutions (#386) · 65ea9194

Paul Fultz II authored Oct 16, 2019

* Fuse convolution adds

* Formatting

* Fuse more 1x1 convs

* Add some tests

* Formatting

* Add test for 1x1

* Add verification for add-conv fusions

* Fix stride calculation

* Formatting

* Add more tests

* Rename tests

65ea9194

15 Oct, 2019 2 commits
- Add more shape operators that can be nops (#390) · 5f2767aa
  Paul Fultz II authored Oct 15, 2019
```
* Add more shape operators that can be nops

* Dont remove pooling
```
  5f2767aa
- Use 32-bit integers for index calculations on the gpu (#387) · 193a3b7c
  Paul Fultz II authored Oct 15, 2019
```
* use 32bit integers for indices

* Formatting

* Update more index types

* Formatting
```
  193a3b7c
10 Oct, 2019 1 commit
- Accelerate calculating conflict table (#382) · dc23d605
  Shucai Xiao authored Oct 10, 2019
```
* accelerate conflict table computation

* removed an unnecessary comma
```
  dc23d605
09 Oct, 2019 1 commit

Fix bug in bert accuraccy (#385) · a797f890

Paul Fultz II authored Oct 09, 2019

* Fix bug in bert accuraccy

* Formatting

* add another test

* Fix add and overflow

* Formatting

* Fix bug in shape_for_each

* Use front instead of iterator

* Use result.front()

* Split add_unary files

* Formatting

* Fix incorrect last index

* Remove comment

* Inline function

* Fix carry check

* Fix metadata errors

* Formatting

* Reflow

* Reflow

a797f890

07 Oct, 2019 1 commit

Replace divisions for index calculation with multiplies (#380) · a625f7b4

Paul Fultz II authored Oct 07, 2019

* Implement fast-div for index calculations

* Formatting

* Use fast_div for broadcasts

* Formatting

* Add remiander function

* Compute mult-index using lens instead of strides

* Formatting

* Simplify equation

* Formatting

a625f7b4

04 Oct, 2019 1 commit

Add_clip fusion (#370) · 1398bcc1

kahmed10 authored Oct 04, 2019

* initial testing of add_clip fusion

* formatting

* clipped relu fusion

* formatting

* remove some executables, add fusion test

* formatting

* remove clipped_relu code

* fix clang-tidy

* revert changes to cmake files

* remove fusion from weight map

* formatting

* fix syntax error

* formatting

* fix syntax error

* fix syntax error

* formatting

1398bcc1

03 Oct, 2019 2 commits

bug_fix_for_gemm_copy (#378) · 84a3f56e

Shucai Xiao authored Oct 03, 2019

* fixed a bug related to removing gemm copy

* clang format

* fix review comments

* clang format

* fix unit test failure

* fix review comments

* clang format

84a3f56e

Improve contiguous and concat performance (#368) · 9b55685c

Paul Fultz II authored Oct 03, 2019

* Add env to trace nary device functions

* Formatting

* Improve contiguous and concat performance

* Formatting

* Remove unused variable

* Formatting

* Fix gpu tests

* Formatting

* Add more test for transposed concat

* Formatting

* Compute offset and not index

* Compute multi-index once

* Formatting

* Fix transposed inputs

* Formatting

* Use product order for comparisons of hip_array

* Formatting

* Add missing s parameter

* Formatting

* Dont invert permutation

* Fix tidy warnings

* Formatting

* Remove incorrect license

* Use a single integer for stride

* Formatting

* Fix tidy issue

9b55685c

02 Oct, 2019 1 commit

Yapf hook (#369) · 47b05b0c

kahmed10 authored Oct 02, 2019

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

* test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

* # This is a combination of 3 commits.
# The first commit's message is:
# This is a combination of 2 commits.
# The first commit's message is:

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

test hook

# This is the 2nd commit message:

test hook

# This is the 2nd commit message:

test hook

# This is the 3rd commit message:

test hook

* fix format

* fix format

* ignore doc dir

* fix regex

* fix jenkins error

* exclude another dir

* formatting test_array

* fix version of yapf

* test hook

* formatting

* reinclude dirs

47b05b0c

30 Sep, 2019 1 commit
- Split clang release job · 2036dfe2
  Paul authored Sep 30, 2019
  
  2036dfe2
27 Sep, 2019 1 commit

Ceil floor operators (#375) · 7d06cdbd

Shucai Xiao authored Sep 27, 2019

* add two operators ceil and floor

* clang format

* add unit test for the ceil and floor operators

* remove unintended code

7d06cdbd

26 Sep, 2019 1 commit
- Fix exception thrown when compiling inceptionv4 (#367) · 7cc3243c
  Paul Fultz II authored Sep 26, 2019
```
* Fix compiler crash in TF inceptionv4

* Formatting

* Remove else
```
  7cc3243c
25 Sep, 2019 1 commit

Reduce_min/max operators (#363) · 3962c2ad

Shucai Xiao authored Sep 25, 2019

* first version of refactoring reduce operators.

* clang format

* refactor the gpu implemantation of the reduce_mean operator

* clang format

* refactor gpu implementation of the resuce_sum operator

* fix cpp check error

* fix cppcheck error

* fix cppcheck error

* fix review comments

* clang format

* fix a jenkin error

* fixed review comments

* clang format

* fix review comments

* clang format

* fix review comments

* clang format

* add implemenation of reduce_min and reduce_max

* clang format

* add unit test for reduce_min/max operator

* clang format

* add more unit tests

* clang format

* fix review comments

3962c2ad

20 Sep, 2019 2 commits
- Fix test · c8192195
  Paul authored Sep 20, 2019
  
  c8192195
- Merge branch 'develop' into tests · 20b1d690
  Paul authored Sep 20, 2019
  
  20b1d690
19 Sep, 2019 1 commit
- Disable fusion when winograd is used except for 3x3 (#364) · ba729cfc
  Paul Fultz II authored Sep 19, 2019
```
* Disable fusion when winograd is used except for 3x3

* Formatting
```
  ba729cfc
18 Sep, 2019 2 commits

Add rule to check for incorrect lambda attributes · 7221e973
Paul authored Sep 18, 2019

7221e973

Remove gemm copy and simplify rocblas call (#356) · a0f9b785

Shucai Xiao authored Sep 18, 2019

* Remove extra copy in gemm

* combine rocblas gemm call

* clang format

* fix a bug in calling rocblas function

* clang format'

* backup of temporary changes

* clang format

* unify the gemm call to avoid multiple gpu implemantation

* clang format

* remove unnecessary code

* backup temp changes

* clang format

* fix cppcheck error

* code backup

* clang format

* remove unnecessary synchronization function

* clang format

* fix bugs

* clang format

* more optimization related to gemm

* clang format

* code cleanup

* implementation that can achieves better performance

* clang format

* temp changes to try performance

* clang format

* revert to previous commits

* fixed review comments

* clang format

* fix review comments

a0f9b785

16 Sep, 2019 4 commits

Add flags to driver to run quantization (#361) · f445d962
Paul Fultz II authored Sep 16, 2019
```
* Add flags to quantize in driver

* Formatting

* Fix compile error
```
f445d962
Add fusions for sigmoid and tanh (#354) · ef5e7ce0
kahmed10 authored Sep 16, 2019
```
* add tests, fix bug in ternary op

* formatting

* uncomment fusion
```
ef5e7ce0
Move all binaries into the same directory (#357) · 01615379
Paul Fultz II authored Sep 16, 2019

01615379

Refactor reduce ops (#350) · 307c40cd

Shucai Xiao authored Sep 16, 2019

* first version of refactoring reduce operators.

* clang format

* refactor the gpu implemantation of the reduce_mean operator

* clang format

* refactor gpu implementation of the resuce_sum operator

* fix cpp check error

* fix cppcheck error

* fix cppcheck error

* fix review comments

* clang format

* fix a jenkin error

* fixed review comments

* clang format

* fix review comments

* clang format

* fix review comments

* clang format

307c40cd

10 Sep, 2019 1 commit
- rename test_gpu_miopen (#355) · 87528938
  kahmed10 authored Sep 10, 2019
```
* rename test_gpu_miopen

* remove gpu prefix
```
  87528938
05 Sep, 2019 2 commits
- Merge branch 'develop' into so-version · 51bd00b3
  Paul authored Sep 05, 2019
  
  51bd00b3
- Merge pull request #352 from ROCmSoftwarePlatform/int8_quant_bugs · b4f11615
  mvermeulen authored Sep 05, 2019
```
int8_quantization bug fix related to imagenet models
```
  b4f11615
04 Sep, 2019 2 commits
- remove log info · daeb193f
  Shucai Xiao authored Sep 04, 2019
  
  daeb193f
- clang format · 1a628d7e
  Shucai Xiao authored Sep 04, 2019
  
  1a628d7e