We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Add OpenMP hints for mixed threads mode from issue 3187
moved issue 665 (sparse matrix/vector support) to a faq entry
Mention the ELF offset/address bug from binutils 2.38 ld
Add NO_AVX2 build hint for OSX Docker Desktop/xhyve (issues 2194 and 2244)
Bump up AVX-512 devtoolset because of identified packaging issues
Bump up required devtoolset version for AVX-512 intrinsics.
Add Xen to the existing entry for QEMU/KVM based on issue 3445
Updated Faq (markdown)
Oops
Use actual small headings to fix... weird bullet indent shit
Add workaround for building with CMAKE on OSX
Add help for cpuid recognition failure
Add entry about compile-time NUM_THREADS setting (issue 2678)
Add note about (not) compiling with -fbounds-check (ticket 2657)
Add entry about problems caused by using the raw cblas.h (issue 2593)
Convert the ARMV8 big.little tidbit to a separate topic and update it with more details from the issue ticket
Add suggestion for speed problems on big.little systems from issue 2589
Add entry for powersaving modes on ARM boards (from issue 2540)
Add solution for programs that look for libblas.so/liblapack.so
Updated multithreading section to introduce option USE_LOCKING (issue 2164)
Add note about generic QEMU CPUID clashing with existing P2(MMX)
Fix typos in previous commit
Add note about using OpenBLAS with CUDA_HPL 2.3 from issue #909
Add note about changed library names for update-alternatives on Debian/Ubuntu
Done with #2089
Add link to Pete Warden blog article on GEMM rather than just deep-linking to a diagram from it
Add brief general usage information from issue 1925
Add small note on AVX512 for CentOS/RHEL section.