Skip to content

/ iree

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

319 Open 606 Closed
319 Open 606 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels.
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
Explore ways to streamline the model import->compilation process for users compiler/tools enhancement ➕ integrations quality of life 😊
#5591 opened Apr 23, 2021 by ScottTodd
Add Colab notebook showing TensorFlow Lite import process integrations/colab integrations/tensorflow
#5589 opened Apr 23, 2021 by ScottTodd
@not-jenni
Fix lit tests that use iree-flow-transformation-pipeline to dispatching Linalg on tensors version
#5583 opened Apr 23, 2021 by hanhanW
@hanhanW
Spin a bit when more work is known to be coming soon. hal/cpu performance ⚡
#5570 opened Apr 22, 2021 by benvanik
@benvanik
Optimize task stealing code path in task system. hal/cpu performance ⚡
#5569 opened Apr 22, 2021 by benvanik
@benvanik
Identify and fix off-by-one in task scheduler tile sharding. bug 🐞 hal/cpu performance ⚡
#5568 opened Apr 22, 2021 by benvanik
@benvanik
Add task worker flag for whether a wake is pending and mask off if so. hal/cpu performance ⚡
#5567 opened Apr 22, 2021 by benvanik
@benvanik
Add a benchmark tool for executable libraries. codegen/llvm hal/cpu runtime/tools
#5564 opened Apr 22, 2021 by benvanik
@benvanik
1
elf loader segfault on 32-bit android arm bug 🐞 platform/android 🤖
#5561 opened Apr 22, 2021 by GMNGeoffrey
@benvanik @GMNGeoffrey
Teach iree-tf-import more smarts regarding SavedModel handling integrations/tensorflow quality of life 😊
#5556 opened Apr 21, 2021 by antiagainst
@silvasean
[New documentation] Decide on category naming discussion 💬 documentation ✏️ runtime
#5555 opened Apr 21, 2021 by ScottTodd
4
Support lowering mhlo.select_and_scatter to linalg codegen
#5553 opened Apr 21, 2021 by asaadaldien
@asaadaldien @hanhanW
1
Collapse multi-dimensional tile loops that don't do anything. codegen/vmvx performance ⚡
#5550 opened Apr 21, 2021 by benvanik
@benvanik @antiagainst
@asaadaldien @MaheshRavishankar
18
Lower vectors into VMVX. codegen/vmvx performance ⚡
#5549 opened Apr 21, 2021 by benvanik
@benvanik @asaadaldien @MaheshRavishankar
Get work distribution working properly for VMVX (and others). codegen codegen/vmvx
#5548 opened Apr 21, 2021 by benvanik
@benvanik @asaadaldien
Upstream improvements for scf.for folding on loop ranges. codegen/vmvx good first issue 🌱 help wanted performance ⚡
#5547 opened Apr 21, 2021 by benvanik
Implement the F32/F64 VM instruction extensions. codegen/vmvx runtime/vm
#5546 opened Apr 21, 2021 by benvanik
@benvanik
Add a few dedicated bytecode->module shims for faster calls. codegen/vmvx performance ⚡ runtime/vm
#5545 opened Apr 21, 2021 by benvanik
@benvanik
Add fused VM ops for common sequences of addressing arithmetic. codegen/vmvx performance ⚡ runtime/vm
#5544 opened Apr 21, 2021 by benvanik
@benvanik
1
Use AttributeInterface to mark attributes that should be serialized by the VM for runtime reflection. cleanup 🧹 compiler
#5543 opened Apr 21, 2021 by benvanik
Add type checks to iree_vm_value_t getters cleanup 🧹 runtime/vm
#5542 opened Apr 21, 2021 by simon-camp
DispatchLinalgOnTensorsPass doesn't work for generic ops that have multiple outputs codegen compiler
#5538 opened Apr 20, 2021 by hanhanW
@MaheshRavishankar
1
Enable vectorizing linalg.generic with reduction semantics codegen
#5537 opened Apr 20, 2021 by asaadaldien
@asaadaldien @MaheshRavishankar @ThomasRaoux
2
Some mhlo.reduce_window ops should be legalized to element-wise operation codegen
#5535 opened Apr 20, 2021 by hanhanW
Add support for lowering 3D pooling ops to Linalg codegen
#5534 opened Apr 20, 2021 by hanhanW
ProTip! Mix and match filters to narrow down what you’re looking for.