nihui/ncnn - ncnn - 开源协同云脑生态支撑系统

Commit Graph

Author	SHA1	Message	Date
nihui	e49f0226e1	multi-threading rnn/lstm/gru with openmp (#3834 )	4 years ago
nihui	02a7e64e18	optimize x86 winograd input transform transpose (#3818 ) * optimize x86 winograd input transform transpose * x86 sse2/avx optimization for convolution winograd23/43 pack1	4 years ago
Yoh	2a05c69cdd	fix x86 unaryop bug on gcc-4.4 (#3838 )	4 years ago
nihui	f48d45209b	binaryop type specialization (#3830 )	4 years ago
nihui	bf64d8f1ec	fix winograd function name (#3820 )	4 years ago
陸言	2161ab2a0c	Edit _bias128 in scale_x86.cpp for useless if (#3821 )	4 years ago
nihui	c16cac2678	update glslang, fix system glslang include path (#3819 )	4 years ago
nihui	9e11dac7d1	simpleomp with libgomp abi (#3816 )	4 years ago
nihui	f79073c182	update how-to-build doc for raspberrypi and d1	4 years ago
nihui	3a827434a9	optimize arm sgemm convolution condition (#3806 )	4 years ago
nihui	5cdb7f6617	make compiler optimization happy with loop (#3799 )	4 years ago
tpoisonooo	6fd801b6d7	feat(src/layer): add vision_transformer benchmark (#3730 ) * feat(src/layer): add vision_transformer benchmark and relative layer * refactor(testutil.h): add para for RandomMat	4 years ago
Xavier Hsinyuan	29b6a32ac0	RVV: follow intrinsic doc, replace vfredsum_* with vfredusum_* (#3790 ) * RVV: follow intrinsic doc, vfredusum -> vfredsum * C906: change toolchains for vfredusum * RVV: test compiler for vfredusum_vs_*	4 years ago
村长大人	c697e988b0	fixbug: linux-arm-hisiv500 load mem "Bus error" (#3779 )	4 years ago
jasonZhang	663b42e0d2	add tanh avx512 optimize (#3770 )	4 years ago
nihui	f9c1787de9	implement einsum layer and pnnx conversion (#3768 )	4 years ago
jasonZhang	c34e305902	Add SSE&AVX optimized for tan (#3765 )	4 years ago
nihui	ee6402553c	layernorm for vector and mat along w, pnnx convnext end2end test (#3764 )	4 years ago
nihui	b516485528	update ci qemu (#3756 ) * update ci qemu * update rvv qemu args * fix bus error on armv7 * apply downstream qemu patches	4 years ago
jasonZhang	e62d674e5d	Add unittest and SSE&AVX optimized for BNLL (#3759 )	4 years ago
Yoh	bf1109c10b	fix elempack16 bug (#3728 )	4 years ago
Xavier Hsinyuan	cea2aff3bb	RVV Optimized erfc and GELU (#3726 ) * RVV optimized GELU(fp32) and erfc(fp32)	4 years ago
jasonZhang	98e35ded36	arm neon optimization for arcsin/arccos pack4 (#3725 )	4 years ago
jasonZhang	8e2e4db3f4	arm neon optimization for tan pack4 (#3722 ) Co-authored-by: jasonZhang892 <jasonZhang892@users.noreply.github.com>	4 years ago
nihui	50fa6d39c0	enable fp16a for mali t760 v2	4 years ago
nihui	7600270430	create uop in spirv-1 mode for vulkan 1.0 compatibility (#3721 )	4 years ago
nihui	a061871c1c	use getauxval since android api 18 (#3718 )	4 years ago
nihui	a14acbc6dd	pnnx save ncnn bin with fp16 storage (#3715 )	4 years ago
nihui	0623f94eca	arm neon optimization for softmax (#3713 )	4 years ago
nihui	0ea327b557	x86 sse/avx/avx512 optimization for softmax (#3712 )	4 years ago
nihui	9826f3dbf8	shader include vulkan activation, workaround for moltenvk tanh half4 issue (#3711 )	4 years ago
nihui	eadb2381dd	force fp32 accumulator for global pooling (#3708 )	4 years ago
nihui	715a248aab	reduce armv7 inline assembly gpr constraint count, fix armhf build (#3707 )	4 years ago
nihui	a0b9e8c143	fix build x86 avx512 source with old gcc (#3705 )	4 years ago
tpoisonooo	5b1bd0f78a	style(src/layer/x86): fix build warning (#3699 )	4 years ago
nihui	b051b6d8cd	apply code-format changes	4 years ago
nihui	c0822fa3b4	sanitize batchnorm divide by zero error, mips msa optimization for batchnorm	4 years ago
nihui	090ac68de5	use msa no signal compare	4 years ago
nihui	337bed7029	copy_make_border border reflect type	4 years ago
nihui	131f3d1323	x86 avx512 optimization for convolution winograd pack16to1 and deconvolution family, increase simpleomp argv count (#3694 ) * convolution winograd pack16to1 * x86 deconvolution and deconvolutiondepthwise * simpleomp allow 32 arguments * drop shadow variable workaround * less winograd test error	4 years ago
nihui	3d169b3237	x86 avx512 optimization (#3691 ) * convolution sgemm pack16to1 * convolution sgemm pack4to16 * eltwise avx512	4 years ago
nihui	9298d05e86	split convolution winograd transform input output (#3688 )	4 years ago
nihui	32560f47de	detect more baseline avx512 flags (#3687 )	4 years ago
nihui	dadc640c66	x86 avx512 optimization (#3581 ) * unified relu avx512 * unifed clip avx512 * unaryop avx512 * sigmoid avx512 * binaryop avx512 * padding convolution avx512 * convolutiondepthwise avx512 * innerproduct avx512 * reshape avx512 * slice avx512 * hardsigmoid hardswish avx512 * swish avx512 * pooling avx512 * crop avx512 * convolution sgemm pack16 * convolution 3x3 winograd pack16 * interp avx512 * convolution sgemm pack1to16 * convolution sgemm pack16to8 * convolution sgemm pack8to16 * convolution sgemm pack16to4 * fix vulkan permute pack8 * fix vulkan convolution gemm pack8to1	4 years ago
nihui	a9c59bb93c	add -mavx512bw flag for avx512 build (#3671 )	4 years ago
nihui	be7cae2bef	mips msa optimization for convolutiondepthwise innerproduct int8 (#3679 )	4 years ago
nihui	4eb279ce26	add loongson mmi compiler header, less msa prefetch distance (#3678 )	4 years ago
nihui	c09d7b3591	mips msa optimization for convolution int8 (#3675 ) * basic mips msa optimization for convolution int8 * mips msa optimization for convolution int8 gemm * mips msa optimization for convolution int8 winograd pack8to4/pack8to1 * mention msa maddv/msubv intrinsics bug	4 years ago
nihui	72c467d1d9	mips msa optimization for quantize dequantize requantize (#3672 )	4 years ago
WuJinxuan	e984f9f40d	add multiheadattention arm (#3667 ) * add:multiheadattention_arm * pass the test in local * add omp * return naive Co-authored-by: EdVince <EdVince@users.noreply.github.com>	4 years ago

1 2 3 4 5 ...

1523 Commits (e49f0226e156e47400bb696ceb29f41b10ed20cf)