News for hackers. Stuff that matters.
Re:Raspberry Pi 4 achieves Vulkan 1.1 conformance, gets GPU ... by my123 on Saturday October 30, 2021 @01:49PM (#29050789)
A fully compliant Vulkan implementation for M1 would come with very surprising performance cliffs for a developer.

One of them: https://github.com/KhronosGroup/MoltenVK/issues/1244

Re:Raspberry Pi 4 achieves Vulkan 1.1 conformance, gets GPU ... by WithinReason on Saturday October 30, 2021 @02:03PM (#29050924)
And also potential optimisations that are not possible in other GPUs:

https://developer.apple.com/documentation/metal/gpu_features...

Re:Raspberry Pi 4 achieves Vulkan 1.1 conformance, gets GPU ... by monocasa on Saturday October 30, 2021 @02:21PM (#29051076)
That's pretty common for TBDRs. The tile is rendered into a fixed size on chip buffer, and the driver has to split the tile into multiple passes to fit all of the render target data for nutty amounts of data coming out of the shader. PowerVR works the same way (completely unsurprisingly).
Re:Raspberry Pi 4 achieves Vulkan 1.1 conformance, gets GPU ... by fulafel on Saturday October 30, 2021 @05:18PM (#29052372)
Re:Raspberry Pi 4 achieves Vulkan 1.1 conformance, gets GPU ... by zamadatix on Saturday October 30, 2021 @02:26PM (#29051120)
It'd be surprising if an architecture had 0 such surprises and did everything Vulkan allows without any special performance considerations vs another architecture.