Juan Fumero

Driver Updates for Fedora and CentOS 7

16

Hi all, any reason why the driver updates for OpenCL and LevelZero pre-builts for Fedora and CentOS 7 have stopped? We used to get almost every week a new version...

OpenCL profile timers and non-blocking calls, wrong values?

3

I am trying to get a simple example with Zero-Copy working for the Intel Integrated graphics. See code: https://github.com/jjfumero/opencl-tests/blob/master/saxpyZeroCopyIntelGraphics/saxpy.cpp **When I breakdown the execution to check COPY_IN, KERNEL_TIME and COPY_OUT,...

Improve instructions for integration with IntelliJ

1

**Is your feature request related to a problem? Please describe.** TornadoVM lacks of documentation about how to setup client/user applications to compile and run directly within the IDE. Related issues:...

For example, for the mandelbrot application, there should be only a LAUNCH and STREAM_OUT at the bytecode level. ```java public static void mandelbrot(int size, short[] output) { for (@Parallel int...

[BUG] Multiple conditions evaluation results in wrong code gen

3

**Describe the bug** The generated code omits a condition when having a complex if condition: The result code for OpenCL is as follows: ```c #pragma OPENCL EXTENSION cl_khr_int64_base_atomics : enable...

Add Javadoc and document the examples in TornadoVM

6

Add Javadoc to document the examples in TornadoVM. This affects the packages under the `examples` module: https://github.com/beehive-lab/TornadoVM/tree/master/tornado-examples/src/main/java/uk/ac/manchester/tornado/examples The documentation is at the class-level and it will contain a description of...

Update the existing Javadoc and complete with the latest features in the TornadoVM API. This involves: * TornadoVM API types * TornadoVM Task-Schedule API * TornadoVM Annotations * TornadoVM Runtime...

Develop use-cases for TornadoVM

3

The current version of the TornadoVM repository contains a module with several `examples`. The purpose of this issue is to expand the variety of use cases with more application domains....

[Question] Shared and Host Buffers can offer the same overall performance on Intel Integrated Graphics?

1

I am interested in analyzing the overall performance (end-to-end applications) when using different types of buffer allocation. I wrote this blog-entry for reference: https://jjfumero.github.io/posts/2022/05/overall-performance-of-unified-shared-memory-level-zero/ What I saw was that running...

Relaxed Allocation Limit in Level Zero

9

When playing around with the `ZE_RELAXED_ALLOCATION_LIMITS_EXP_FLAG_MAX_SIZE` flag for buffer allocation I noticed the following: If I request a buffer to be allocated with a size larger than my system allows...