mmellison

import asyncio
from concurrent import futures
import functools
import inspect
import threading

from grpc import _server

def _loop_mgr(loop: asyncio.AbstractEventLoop):

teamdandelion

7
2
1
0
4
1
4
9
5
9

andersx

// Approximation for EXP(x) -- very fast, but not super accurate
static inline __m256 _mm256_expfaster_ps(const __m256 &q) {

    const __m256 C1 = _mm256_set1_ps(1064872507.1541044f);
    const __m256 C2 = _mm256_set1_ps(12102203.161561485f);

    return _mm256_castsi256_ps(_mm256_cvttps_epi32(_mm256_fmadd_ps(C2, q, C1)));
}

andersx

// Approximation for EXP(x), only valid for -126.0f < x < 0.0f.
static inline __m256 _mm256_expfast_ps(const __m256 &q) {

    const __m256 INVLOG_2 = _mm256_set1_ps(1.442695040f);
    const __m256 BIT_SHIFT = _mm256_set1_ps(8388608);
    const __m256 ONE = _mm256_set1_ps(1.0f);

    const __m256 C1 = _mm256_set1_ps(121.2740838f);
    const __m256 C2 = _mm256_set1_ps(27.7280233f);
    const __m256 C3 = _mm256_set1_ps(4.84252568f);

jboner

Latency Comparison Numbers (~2012)
----------------------------------
L1 cache reference                           0.5 ns
Branch mispredict                            5   ns
L2 cache reference                           7   ns                      14x L1 cache
Mutex lock/unlock                           25   ns
Main memory reference                      100   ns                      20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy             3,000   ns        3 us
Send 1K bytes over 1 Gbps network       10,000   ns       10 us
Read 4K randomly from SSD*             150,000   ns      150 us          ~1GB/sec SSD

hannes-brt

import pyximport
import numpy as np
pyximport.install(setup_args={'include_dirs': np.get_include()})