Thales Sabino

Initial work to add Tensor Cores support in Halide

14

Tensor Cores are programmable cores that perform warp-level matrix-multiply and accumulate operations. It can greatly improve performance of matrix-multiply expressions written in Halide when the hardware is available. This works...

How to use DevicePerfCounterTimeBasedSampling?

10

## Observed Behavior Profiling my application with `CLI_DevicePerfCounterTimeBasedSampling=1` gives me the message `E:[MDAPI]: enable timer mode escape failed MDAPI Helper: OpenIoStream failed 42` ## Desired Behavior I would like to...

Changes to build the examples under MSVC

4

The FindComputeCpp.cmake was updated to the latest version. The download mechanism for the mnist database was changed to use CMake `file` command. The file `smo.hpp` had some incompatibilities with MSVC.

The build instructions mention that the JAVA home variable must be set, but doesn't have any examples > Make sure the environment variable JAVA_HOME is defined and pointing a to...

[BUG] Can't Force Update in Sketcher panel

1

### Contact Details [email protected] ### Description Working on this file I used to press the Force Update button to refresh all the meshes in the scene. Somehow I got CAD...

The filter information layout is broken