Coding Mistake Made Intel GPUs 100X Slower in Ray Tracing

Rate this post


Intel Linux GPU driver builders have launched an replace that ends in an enormous 100X enhance in ray tracing efficiency. That is one thing to be celebrated, after all. Nonetheless, on the flip facet, the driving force was 100X slower than it ought to have been due to a reminiscence allocation oversight. The information comes amid experiences that Intel’s delivery drivers for its Arc GPUs are fraught with points in Home windows which might be akin to “[…]dwelling in the course of a minefield – thoughts you, whereas enjoying drunk.” The corporate has additionally admitted that Arc efficiency is sub-par with older APIs, like DX11, in Home windows. 

Linux-centric information website Phoronix experiences {that a} repair merged into the open-source Intel Mesa Vulkan driver was carried out by Intel Linux graphics driver engineering stalwart Lionel Landwerlin on Thursday. The developer wryly commented that the merge request, which already landed in Mesa 22.2, would ship “Like a 100x (not joking) enchancment.” Intel has been engaged on Vulkan raytracing assist since late 2020, however this repair is best late than by no means.

(Picture credit score: Future)

Even readers who aren’t (driver) builders will in all probability be capable to perceive the problem with the earlier code. Normally, the Vulkan driver would guarantee momentary reminiscence used for Vulkan raytracing work can be in native reminiscence, i.e., the very quick graphics reminiscence onboard the discrete GPU.


Supply hyperlink