422
edits
Changes
GPU
,→Integer Instruction Throughput
* INT64
: Current In general GPU [https://en.wikipedia.org/wiki/Processor_register registers] and Vector-[https://en.wikipedia.org/wiki/Arithmetic_logic_unit ALUs] are 32 bit wide and have to emulate 64 bit integer operations.
* INT8
: Some architectures offer higher throughput with lower precision. They quadruple the INT8 or octuple the INT4 throughput.
