sci-ml / XNNPACK

library of floating-point neural network inference operators

Official package sites : https://github.com/google/XNNPACK/ ·

v2024.11.08-r1 :: 0 :: gentoo

Modified
License
MIT
Keywords
~amd64
USE flags
assembly jit memopt sparse static-libs test

v2024.02.29-r1 :: 0 :: gentoo

Modified
License
MIT
Keywords
~amd64
USE flags
assembly jit memopt sparse static-libs test

General

assembly
Build with assembly micro-kernels
jit
Build with JIT micro-kernels
memopt
Build with optimized memory allocation scheme
sparse
Build with graph rewriting for sparse inference
static-libs
Build static versions of dynamic libraries as well
test
Enable dependencies and/or preparations necessary to run tests (usually controlled by FEATURES=test but can be toggled independently)

dev-libs / FXdiv : Division via fixed-point multiplication by inverse

dev-libs / cpuinfo : CPU INFOrmation library

dev-libs / pthreadpool : Portable and efficient thread pool implementation

sci-ml / FP16 : conversion to/from half-precision floating point formats

dev-libs / cpuinfo : CPU INFOrmation library

dev-libs / pthreadpool : Portable and efficient thread pool implementation

sci-ml / caffe2 : A deep learning framework

953467
sci-ml/XNNPACK-2024.11.08-r1 - f16-avgpool-9p8x-minmax-f16c-c8.c: error: dereferencing type-punned pointer will break strict-aliasing rules [-Werror=strict-aliasing]
Repository mirror & CI · gentoo
Merge updates from master
Alfredo Tupone · gentoo
sci-ml/XNNPACK: better fix src_test
Signed-off-by: Alfredo Tupone <tupone@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Alfredo Tupone · gentoo
sci-ml/*: mv dev-libs/FP16 to sci-ml
Signed-off-by: Alfredo Tupone <tupone@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Alfredo Tupone · gentoo
sci-ml/*: mv sci-libs/XNNPACK to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org>