"Windows ain't done 'til Lotus won't run."
Intel's “Cripple AMD” Function
11–12 of 12 posts
Re: Intel's “Cripple AMD” Function
#12It's interesting how this is still a major issue today, Last month I learned about the Matlab AMD crippling issue. With the workaround AMD performance on a 3960x increased by 30%. "[...] the Intel MKL uses a discriminative CPU Dispatcher that does not use efficient codepath according to SIMD support by the CPU, but based on the result of a vendor string query. If the CPU is from AMD, the MKL does not use SSE3-SSE4 or…
Wasn’t there a lawsuit about the ICC doing this a few years ago?