Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
H
hpvm-release
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
llvm
hpvm-release
Commits
0ecdfa61
Commit
0ecdfa61
authored
4 years ago
by
Hashim Sharif
Browse files
Options
Downloads
Patches
Plain Diff
Adding list of porting changes required (docs)
parent
ce17ccbb
No related branches found
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
llvm/projects/hpvm-tensor-rt/docs/Changes.md
+63
-0
63 additions, 0 deletions
llvm/projects/hpvm-tensor-rt/docs/Changes.md
with
63 additions
and
0 deletions
llvm/projects/hpvm-tensor-rt/docs/Changes.md
0 → 100644
+
63
−
0
View file @
0ecdfa61
# Header Files Needing Modification
-
llvm/include/IR/IntrisicsVISC.td
*
Add intrinsics here
-
bechmarks/common/include/visc.h - Benchmarks header
*
Include tensor intrinsic declarations
-
Header files for "PROMISE_TARGET" and "CUDNN_TARGET" Hints
*
/include/SupportVISC/DFG2LLVM.h
*
/include/SupportVISC/VISCUtils.h
*
/include/SupportVISC/VISCHint.h
*
# Passes Needing Modification
-
GenVISC
*
Handle Tensor Intrinsics
*
Add Declarations for Intrinsic Functions called (at top)
*
Modify runOnModule to include rules for functions -> intrinsics
-
ClearDFG
*
Incorporate new changes for visc.node.id
# Passes to Move
-
lib/Transforms/DFG2LLVM_CUDNN
-
lib/Transforms/DFG2LLVM_WrapperAPI
-
lib/Transforms/FusedNodesHPVM
**
Changes needed:
-
Modify paths to tensor_runtime.ll
-
Use
`hpvm' instead of `
visc' intrinsics
# Projects to Move
-
hpvm-tensor-rt
*
Make sure to not move 'tuner_results' and 'model_params' subdirectories
-
gpu_profiler
-
soc_simlator
-
Keras (wait on it)
# Build System
-
Add rules to /lib/Transforms/CMakeLists.txt
-
Add rules to /llvm/projects/CmakeLists.txt
-
Automate the generation of 'tensor_runtime.ll
`
-
Add CUDNN, CUDA paths to the template environment setup file
-
Move to using Cmake-3.17 (earlier 3.15)
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment