Various links

Intrinsics

Intel intrinsics Guide

GPU docs

AMD decoder ring for engineering vs marketing names

Debugging OpenCL kernel under POCL

https://portablecl.org/docs/html/debug.html

Bloom filter calculator

https://hur.st/bloomfilter/?n=128&p=64&m=&k=

LOP3.LUT or vpternlog calculator

https://www.officedaytime.com/simd512e/simdimg/ternlogcalc.html

CUDA best practices

https://docs.nvidia.com/cuda/cuda-c-best-practices-guide/index.html

Most of it applies to OpenCL too. The "memory optimizations" chapter is a good read.