[llvm-dev] LLVM GPU News Issue #10, April 16 2021

Jakub (Kuba) Kuderski via llvm-dev llvm-dev at lists.llvm.org
Sat Apr 17 13:51:03 PDT 2021

Hi folks,

The 10th issue of LLVM GPU News, a bi-weekly newsletter on all
the GPU things under the LLVM umbrella, is now available at <

I also pasted the content below, in case you prefer to read in your email



# LLVM GPU News Issue #10, April 16 2021
Authors: Jakub Kuderski, Lei Zhang, Johannes Doerfert

Welcome to LLVM GPU News, a bi-weekly newsletter on all the GPU things
under the LLVM umbrella.
This issue covers the period from April 2 to April 15 2021.

We welcome your feedback and suggestions. Let us know if we missed anything
interesting, or want us to bring attention to your (sub)project, revisions
under review, or proposals. Please see the bottom of the page for details
on how to submit suggestions and contribute.

## Industry News and Conference Talks

*  Nvidia's GPU Technology Conference (GTC) was [live this week](
*  Registration for the SIGGRAPH 2021 conference (virtual, August 9-13) [is
*  Vulkan 1.2.175 has been published. New notable extensions include [video
encode and decode](
https://www.khronos.org/blog/an-introduction-to-vulkan-video). You can
share your feedback under the [Vulkan Video GitHub issue](
*  Heterogeneous Parallel Virtual Machine (HPVM) v1.0 has been [released](
https://lists.llvm.org/pipermail/llvm-dev/2021-April/149693.html). HPVM is
a retargetable compiler infrastructure that targets CPUs, GPUs, FPGAs, and
accelerators. This release is based on LLVM 9.0.

##  LLVM and Clang

### Discussions

### Commits

*  The work on supporting AMDGPU GFX90* continues:
   -  GFX90a memory model [got updated](https://reviews.llvm.org/D100070).
This includes documentation changes.
   -  GFX90a code path will [reject assembly using the `scc` bit](
   -  GFX90c code object v2 [is added](https://reviews.llvm.org/D100126)
for backwards compatibility.
*  NVPTX learned to [avoid some copying](https://reviews.llvm.org/D99979)
in function argument lowering.
*  CUDA/HIP option `-fcuda-flush-denormals-to-zero` [has been renamed](
https://reviews.llvm.org/D99688) to `-fgpu-flush-denormals-to-zero`.


### Discussions

### Commits

*  SPIR-V conversion now [allows](https://reviews.llvm.org/D100059)
explicitly controlling bitwidth emulation for bitwidth unsupported in the
target environment.
*  A few fixes [landed](https://reviews.llvm.org/D100335) in SPIR-V
conversion to [handle](https://reviews.llvm.org/D100337) dynamic ranked
`memref` better.
*  A few utility functions are [added]( https://reviews.llvm.org/D99725) in
SPIR-V conversion for creating push constant blocks.
*  Boolean `memref`s are now properly [handled](
https://reviews.llvm.org/D99724) when converting to SPIR-V.

## OpenMP (Target Offloading)

### Discussions

*  Kai Plociennik is asking about creating a [static library containing
OpenMP offloading](
https://lists.llvm.org/pipermail/llvm-dev/2021-April/149870.html) code.
There are no replies as of writing.

### Commits

## External Compilers

### LLPC

### Mesa

* Support for LLVM 8, 9, and 10 [has been dropped](
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10199) in the
`amd` compiler. This allows for a code cleanup, these versions do not
support RDNA2.

### SYCL

Jakub Kuderski
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20210417/72b0cefb/attachment.html>

More information about the llvm-dev mailing list