../
allocator.cc
allocator.h
apply_multiplier.cc
apply_multiplier.h
asm_helpers.h
block_map.cc
block_map.h
blocking_counter.cc
blocking_counter.h
check_macros.h
context.cc
context.h
context_get_ctx.cc
context_get_ctx.h
cpu_cache_params.h
cpuinfo.cc
cpuinfo.h
create_trmul_params.h
ctx.cc
ctx.h
ctx_impl.h
denormal.cc
denormal.h
frontend.cc
frontend.h
have_built_path_for.h
have_built_path_for_avx.cc
have_built_path_for_avx2_fma.cc
have_built_path_for_avx512.cc
kernel.h
kernel_arm.h
kernel_arm32.cc
kernel_arm64.cc
kernel_avx.cc
kernel_avx2_fma.cc
kernel_avx512.cc
kernel_common.h
kernel_x86.h
mat.h
matrix.h
mul_params.h
opt_set.h
pack.h
pack_arm.cc
pack_arm.h
pack_avx.cc
pack_avx2_fma.cc
pack_avx512.cc
pack_common.h
pack_x86.h
path.h
performance_advisory.h
platform.h
prepacked_cache.cc
prepacked_cache.h
prepare_packed_matrices.cc
prepare_packed_matrices.h
[+] profiler/
ruy.h
side_pair.h
size_util.h
system_aligned_alloc.cc
system_aligned_alloc.h
thread_pool.cc
thread_pool.h
time.h
trace.h
trmul.cc
trmul.h
trmul_params.h
tune.cc
tune.h
validate.h
wait.cc
wait.h