nihui

#include <malloc.h>

// call malloc_trim(0);
static double get_memory_resident()
{
    unsigned long size;
    unsigned long resident;
    unsigned long share;
 unsigned long text;

nihui

// g++ mul.cpp -o mul -mmsa -mloongson-mmi -O3
// https://github.com/Tencent/ncnn/blob/master/src/layer/mips/loongson_mmi.h

// root@ls2k:~/ncnn/build# ./quant 
// mul_s8x8      385.743
// mul_s8x8_mmi  611.364
// mul_s8x8_msa  173.241
// -66 2 0 4 10 18 28 40

nihui

// g++ -mfma -mf16c -mavx512f -mavx512vnni -mavx512vl

#include <immintrin.h>

#include <stdio.h>

static void print(const __m512& _x)
{
    __attribute__((aligned(64)))
    float a[16];

nihui

#include <torch/script.h>

int main()
{
    c10::InferenceMode guard(true);
    torch::NoGradGuard no_grad;

    torch::jit::Module mod2 = torch::jit::load("stylegan.pt");
    mod2.eval();

nihui

#include <stdio.h>

// ncnn
#include <c_api.h>

/** test.param content

7767517
3 3
Input       in0     0 1 input0

nihui

$ git push
remote: Support for password authentication was removed on August 13, 2021. Please use a personal access token instead.
remote: Please see https://github.blog/2020-12-15-token-authentication-requirements-for-git-operations/ for more information.
fatal: 'https://github.com/nihui/ncnn.git/' 鉴权失败

$ git remote -v
origin https://github.com/nihui/ncnn.git (fetch)

nihui

from http.server import HTTPServer, SimpleHTTPRequestHandler
import ssl, os
os.system("openssl req -nodes -x509 -newkey rsa:4096 -keyout key.pem -out cert.pem -days 365 -subj '/CN=mylocalhost'")
port = 8888
httpd = HTTPServer(('0.0.0.0', port), SimpleHTTPRequestHandler)
httpd.socket = ssl.wrap_socket(httpd.socket, keyfile='key.pem', certfile="cert.pem", server_side=True)
print(f"Server running on https://0.0.0.0:{port}")
httpd.serve_forever()

nihui

曾经有一天（只需要做一次）

• github 上点 fork 按钮 fork 到 https://github.com/nihui/ncnn.git
• git clone https://github.com/nihui/ncnn.git

配置下 upstream 同步位置（只需要做一次）

• cd ncnn
• git remote add upstream https://github.com/Tencent/ncnn.git

我不 PR，就像让 https://github.com/nihui/ncnn.git 的内容和 upstream 一模一样，就像刚 fork 时候的那样子，不要落后了

• cd ncnn

nihui

Detail behind NCNN's factory pattern

NCNN adopts the factory pattern to create the layers of a nueral network. It's also the way the well-known library Caffe takes. It differs from Caffe in the implementation of the registry table. On one hand, the Caffe registry is populated in runtime as the side effect of initializion of global variable (which is a popular way for library initialization). On the other hand, the NCNN registry is determined in compile time. The registry is generated in a brilliant way using CMake instead of a hand-crafted table. NCNN's approach provides several benefits compared to Caffe's approach.

First, it's suitable for building a static library. When building a static library, the linker will strip any unused global variable to minimize the size of the library. This makes sense but it also strips the global variable which need to be inintialized to insert te layer creator into the registry. Tricky linker flags and related instrutions are required to resolve this issue. By creating

nihui

Model	Image Size	Target Size	Block Size	Total Time(sec)	GPU Memory(MB)
models-cunet	200x200	400x400	400/200/100	0.93/0.30/0.33	615/615/173
models-cunet	400x400	800x800	400/200/100	0.78/0.71/0.78	2408/615/174
models-cunet	1000x1000	2000x2000	400/200/100	3.16/3.21/3.53	2416/618/175
models-cunet	2000x2000	4000x4000	400/200/100	11.40/11.98/13.86	2420/669/193
models-cunet	4000x4000	8000x8000	400/200/100	44.33/47.15/54.76	2452/644/197
models-upconv_7_anime_style_art_rgb	200x200	400x400	400/200/100	0.16/0.16/0.15	459/459/119
models-upconv_7_anime_style_art_rgb	400x400	800x800	400/200/100	0.43/0.37/0.37	1741/460/119
models-upconv_7_anime_style_art_rgb	1000x1000	2000x2000	400/200/100	1.62/1.59/1.67	1764/462/120