Starefossen

Sessions

New Session

• tmux new [-s name] [cmd] (:new) - new session

Switch Session

• tmux ls (:ls) - list sessions
• tmux switch [-t name] (:switch) - switches to an existing session

understeer

Latency Comparison Numbers
--------------------------
L1 cache reference/hit                       1.5 ns                      4 cycles
Floating-point add/mult/FMA operation        1.5 ns                      4 cycles
L2 cache reference/hit                       5   ns                      12 ~ 17 cycles
Branch mispredict                            6   ns                      15 ~ 20 cycles
L3 cache hit (unshared cache line)          16   ns                      42 cycles
L3 cache hit (shared line in another core)  25   ns                      65 cycles
Mutex lock/unlock                           25   ns
L3 cache hit (modified in another core)     29   ns                      75 cycles

wangg12

from graphviz import Digraph
from torch.autograd import Variable
import torch


def make_dot(var, params=None):
    if params is not None:
        assert isinstance(params.values()[0], Variable)
        param_map = {id(v): k for k, v in params.items()}

Stonesjtu

import gc

import torch

## MEM utils ##
def mem_report():
    '''Report the memory usage of the tensor.storage in pytorch
    Both on CPUs and GPUs are reported'''

    def _mem_report(tensors, mem_type):

pbamotra

def logsigsoftmax(logits):
    """
    Computes sigsoftmax from the paper - https://arxiv.org/pdf/1805.10829.pdf
    """
    max_values = torch.max(logits, 1, keepdim = True)[0]
    exp_logits_sigmoided = torch.exp(logits - max_values) * torch.sigmoid(logits)
    sum_exp_logits_sigmoided = exp_logits_sigmoided.sum(1, keepdim = True)
    log_probs = logits - max_values + torch.log(torch.sigmoid(logits)) - torch.log(sum_exp_logits_sigmoided)
    return log_probs

telegraphic

import pycuda.driver as cuda
import pycuda.autoinit
from pycuda.compiler import SourceModule
import numpy as np

def compute_xcorr_cpu(d):
    dc = d.astype('float32').view('complex64')
    dc = dc.transpose((0,2,3,1)).copy()
    xcorr_cpu = np.einsum('...i,...j', dc,  np.conj(dc)).view('float32').astype('int32').sum(axis=-4)
    return xcorr_cpu

mcarilli

# This isn't supposed to run as a bash script, i named it with ".sh" for syntax highlighting.

# https://developer.nvidia.com/nsight-systems
# https://docs.nvidia.com/nsight-systems/profiling/index.html

# My preferred nsys (command line executable used to create profiles) commands
#
# In your script, write
# torch.cuda.nvtx.range_push("region name")
# ...