Commits · 4de739d23ee5c53bb9cdf832d66cc2542ef90d5d · gaoqiong / MIGraphX

27 Feb, 2020 1 commit
- Bump version · 4de739d2
  Paul authored Feb 27, 2020
  
  4de739d2
12 Feb, 2020 1 commit
- Changing HIP dependency from hip_hcc to hip-hcc, to accommodate the name change for HIP in ROCm 3.0 · 79bfafc1
  Radha Srimanthula authored Dec 10, 2019
  
  79bfafc1
16 Dec, 2019 1 commit
- Fix c++ documentaion · cd6e312c
  Paul authored Dec 16, 2019
  
  cd6e312c
14 Dec, 2019 1 commit
- Add documentation for python · 9b9d1418
  Paul authored Dec 13, 2019
  
  9b9d1418
28 Nov, 2019 1 commit
- Package driver · 7c35bf11
  Paul authored Nov 27, 2019
  
  7c35bf11
27 Nov, 2019 1 commit

Add support for builtin models in the driver (#404) · b0aef8c8

Paul Fultz II authored Nov 27, 2019

* Add experimental support for c++ output

* Format

* Fix syntax errors

* Add resnet50 model

* Formatting

* Add inceptionv3 model

* Formatting

* Add alexnet

* Formatting

* Fix name of pooling mode

* Formatting

* Fix tidy issues

* Ignore driver directory

* Show accetable values

b0aef8c8

20 Nov, 2019 3 commits
- Simplify target functions · 08779d55
  Paul authored Nov 20, 2019
  
  08779d55
- Formatting · 6a8cef34
  Paul authored Nov 20, 2019
  
  6a8cef34
- Auto generate fallback code in type-erasure · a40d1b1d
  Paul authored Nov 20, 2019
  
  a40d1b1d
18 Nov, 2019 1 commit

Improve concat gather (#402) · 0045d0b7

Shucai Xiao authored Nov 18, 2019

* improve gather implementation to handle negative input indices

* clang format

* clang format

* improve concat to support neg axis input

* clang format

* fix cppcheck error

* clang format

* code cleanup

* clang format

* fix review comments

* clang format

0045d0b7

17 Nov, 2019 1 commit
- Update version · d10628ee
  Paul authored Nov 16, 2019
  
  d10628ee
15 Nov, 2019 1 commit

Add option to do offload copying automatically (#403) · 81b0ff5d

Paul Fultz II authored Nov 15, 2019

* Add compiler options

* Add copy operators

* Formatting

* Use run_passes in tests

* Formatting

* Use run_pass in schedule test

* Formatting

* Add compile_options to get_passes in target

* Formatting

* Offload copy option

* Formatting

* Copy using pinned memory

* Formatting

* Improve performance of gpu copying

* Formatting

* Dont copy

* Formatting

* Always make an extra copy

* Formatting

* Remove unused write op

* Add missing include

* Remove copy_to_gpu function in python api

* Make offload copy disabled by default on C++

* Formatting

* Fix tidy issues

* Formatting

* Fix namespace

* Fix python tests

* Turn clang format off since its broken

* Fix compile error on gcc 5

* Remove commented code

81b0ff5d

14 Nov, 2019 1 commit

Add Split op (#401) · e814cffb

kahmed10 authored Nov 14, 2019

* fix pad calc

* simplify ceil calc and remove extra vars

* workatound for nasnet

* formatting

* add split and tests

* formatting

* fix cppcheck and clang-tidy

* fix clang tidy

* refactor to use vector of instruction_ref, add UNDEBUG to clang tidy

* formatting

* fix comment code

* fix comments and tidy

* formatting

* fix syntax error

* fix tidy

* remove namespace comment

e814cffb

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 1 commit
- Fix test · c8192195
  Paul authored Sep 20, 2019
  
  c8192195