Forwarded from Phoronix
Phoronix
New "SCALE" Software Allows Natively Compiling CUDA Apps For AMD GPUs
While there have been various efforts like HIPIFY to help in translating CUDA source code to portable C++ code for AMD GPUs and then the previously-AMD-funded ZLUDA to allow CUDA binaries to run on AMD GPUs via a drop-in replacement to CUDA libraries, there's…
一个存在的世界
https://www.phoronix.com/review/amd-zen5-avx-512-9950x/7 这下AMD成真完全态512了
如何评价5GHz的512b AVX512 pipeline
一个存在的世界
Photo
The L1 BTB has 16K entries and predicts with zero
prediction bubbles for direct calls, same-target indirect branches, conditional, and unconditional
direct branches, and a two-cycle bubble for returns and multiple-target indirect branches.
??
prediction bubbles for direct calls, same-target indirect branches, conditional, and unconditional
direct branches, and a two-cycle bubble for returns and multiple-target indirect branches.
??