Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
24 changes: 24 additions & 0 deletions .clang-tidy
Original file line number Diff line number Diff line change
Expand Up @@ -71,16 +71,32 @@
# -modernize-type-traits
# -performance-avoid-endl
#
# TODO Code Quality WORKAROUND ROCm 6.2
# -readability-container-size-empty
# -bugprone-inc-dec-in-conditions
# -readability-avoid-nested-conditional-operator
# -performance-enum-size
# -readability-redundant-member-init
# -bugprone-multi-level-implicit-pointer-conversion
# -clang-analyzer-optin.core.EnumCastOutOfRange
# -cppcoreguidelines-macro-to-enum
# -cppcoreguidelines-owning-memory
# -readability-avoid-return-with-void-value
# -bugprone-unused-local-non-trivial-variable
#
Checks: >-
*,
-abseil-*,
-altera-*,
-android-cloexec-fopen,
-bugprone-easily-swappable-parameters,
-bugprone-exception-escape,
-bugprone-inc-dec-in-conditions,
-bugprone-lambda-function-name,
-bugprone-macro-parentheses,
-bugprone-multi-level-implicit-pointer-conversion,
-bugprone-narrowing-conversions,
-bugprone-unused-local-non-trivial-variable,
-bugprone-use-after-move,
-cert-env33-c,
-cert-err33-c,
Expand All @@ -90,6 +106,7 @@ Checks: >-
-cert-msc51-cpp,
-clang-analyzer-alpha.core.CastToStruct,
-clang-analyzer-cplusplus.NewDeleteLeaks,
-clang-analyzer-optin.core.EnumCastOutOfRange,
-clang-analyzer-optin.performance.Padding,
-clang-diagnostic-extern-c-compat,
-clang-diagnostic-unused-command-line-argument,
Expand All @@ -100,11 +117,13 @@ Checks: >-
-cppcoreguidelines-avoid-magic-numbers,
-cppcoreguidelines-explicit-virtual-functions,
-cppcoreguidelines-init-variables,
-cppcoreguidelines-macro-to-enum,
-cppcoreguidelines-macro-usage,
-cppcoreguidelines-misleading-capture-default-by-value,
-cppcoreguidelines-missing-std-forward,
-cppcoreguidelines-narrowing-conversions,
-cppcoreguidelines-non-private-member-variables-in-classes,
-cppcoreguidelines-owning-memory,
-cppcoreguidelines-prefer-member-initializer,
-cppcoreguidelines-pro-bounds-array-to-pointer-decay,
-cppcoreguidelines-pro-bounds-constant-array-index,
Expand Down Expand Up @@ -168,11 +187,15 @@ Checks: >-
-modernize-concat-nested-namespaces,
-modernize-unary-static-assert,
-performance-avoid-endl,
-performance-enum-size,
-readability-avoid-nested-conditional-operator,
-performance-no-automatic-move,
-performance-unnecessary-copy-initialization,
-performance-unnecessary-value-param,
-readability-avoid-return-with-void-value,
-readability-avoid-unconditional-preprocessor-if,
-readability-container-data-pointer,
-readability-container-size-empty,
-readability-convert-member-functions-to-static,
-readability-else-after-return,
-readability-function-cognitive-complexity,
Expand All @@ -182,6 +205,7 @@ Checks: >-
-readability-named-parameter,
-readability-qualified-auto,
-readability-redundant-declaration,
-readability-redundant-member-init,
-readability-redundant-string-init,
-readability-simplify-boolean-expr,
-readability-suspicious-call-argument,
Expand Down
1 change: 1 addition & 0 deletions .gitattributes
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
*.db.bz2 binary
*.db.txt.bz2 binary
*.fdb.txt.bz2 binary
*.kdb.bz2 filter=lfs diff=lfs merge=lfs -text
*.ktn.model binary
2 changes: 1 addition & 1 deletion .github/CODEOWNERS
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
* @JehandadKhan @junliume
* @BrianHarrisonAMD @junliume @BradPepersAMD
# Documentation files
docs/ @ROCm/rocm-documentation
*.md @ROCm/rocm-documentation
Expand Down
67 changes: 67 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1,67 @@
# Compiled Object files
*.slo
*.lo
*.o
*.obj

# Precompiled Headers
*.gch
*.pch
*.ipch

# Compiled Dynamic libraries
*.so
*.dylib
*.dll

# Fortran module files
*.mod

# Compiled Static libraries
*.lai
*.la
*.a
*.lib

# Executables
*.exe
*.out
*.app

# vim tags
tags
.tags
.*.swp

# Editors
.vscode

# build-in-source directory

# emacs temporary/backup files
.\#*
\#*\#
*~

# GDB temporary files
.gdb_history
install.dir*

# documentation artifacts
_build/
_images/
_static/
_templates/
_toc.yml
_doxygen/

# JetBrains IDE
.idea/
cmake-build*/
build*/

# Python virtualenv
.venv/

# Python cache
__pycache__/
29 changes: 22 additions & 7 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,24 @@
# Change Log for MIOpen

Full documentation for MIOpen is available [here](https://rocm.docs.amd.com/projects/MIOpen/en/latest/)
## MIOpen 3.3.0 for ROCm 6.3.0
### Added

* [RNN] LSTM fwd
* [Mha] Mask is added for Forward pass
* [GLU] Gated Linear Unit (this is an experimental feature)
* [PReLU] Implemented PReLU bwd (this is an experimental feature)
### Optimized

- MI300 TunaNet Update: CK FWD and WRW Solvers Updated
### Resolved issues

## MIOpen-3.2.0 for ROCm 6.2.0
- Fixed unset stream when calling `hipMemsetAsync`
- Fixed a memory leak issue caused by an incorrect transpose in find 2.0 (see PR #3285 on GitHub)
- Fixed a `memcopy` data race by replacing `hipMemcpy` with `hipMemcpyWithStream`


## MIOpen 3.2.0 for ROCm 6.2.0
### Added
- [Conv] bilinear (alpha beta) solvers
- [Conv] enable bf16 for ck-based solvers
Expand All @@ -12,7 +28,6 @@ Full documentation for MIOpen is available [here](https://rocm.docs.amd.com/proj
- [RNN] multi-stream as default solution.
- TunaNetv2.0 for MI300
- Added adam and amp adam optimizer

### Fixed
- Memory access fault caused by GemmBwdRest
- Context configuration in GetWorkSpaceSize
Expand All @@ -21,7 +36,7 @@ Full documentation for MIOpen is available [here](https://rocm.docs.amd.com/proj
### Performance
- Find: Improve precision of benchmarking

## MIOpen-3.1.0 for ROCm 6.1.0
## MIOpen 3.1.0 for ROCm 6.1.0
### Added
- CK-based 2d/3d convolution solvers to support nchw/ncdhw layout
- Fused solver for Fwd Convolution with Residual, Bias and activation
Expand All @@ -40,7 +55,7 @@ Full documentation for MIOpen is available [here](https://rocm.docs.amd.com/proj
### Removed
- clamping to MAX from CastTensor used in Bwd and WrW convolution

## MIOpen-3.0.0 for ROCm 6.0.0
## MIOpen 3.0.0 for ROCm 6.0.0
- This release adds 3D convolution, enablement of fp8 convolution, NHWC batch norm, RNN padding support. It also removes
INI8x4 support and fix minor issues and bugs.
### Notes
Expand All @@ -63,7 +78,7 @@ INI8x4 support and fix minor issues and bugs.
- Remove INT8x4 support
- Remove target ids from kdb args

## MIOpen-2.21.0 for ROCm 5.7.0
## MIOpen 2.21.0 for ROCm 5.7.0
### Added
- AI Heuristic for Immediate Mode Fallback
- CK group forward convolution integration
Expand All @@ -73,7 +88,7 @@ INI8x4 support and fix minor issues and bugs.
### Changed
- Update fdb data to use solver keys [MI100][MI200]

## MIOpen-2.20.0 for ROCm 5.6.0
## MIOpen 2.20.0 for ROCm 5.6.0
### Added
- AI Based Heuristic for Kernel Parameter Prediction
- LSTM multi-stream solver
Expand All @@ -83,7 +98,7 @@ INI8x4 support and fix minor issues and bugs.
- Winograd kernel failure
- Perf DB updates for gfx908 and gfx90a

## MIOpen-2.19.0 for ROCm 5.5.0
## MIOpen 2.19.0 for ROCm 5.5.0
### Added
- ROCm 5.5 support for gfx1101 (Navi32)
### Changed
Expand Down
Loading