Skip to content

Instantly share code, notes, and snippets.

"builtin.module"() ({
"func.func"() <{function_type = () -> (), sym_name = "main"}> ({
%0 = "mps.placeholder"() : () -> tensor<10x128xf32>
%1 = "mps.placeholder"() : () -> tensor<64x128xf32>
%2 = "mps.constant"() <{value = dense<0> : tensor<si32>}> : () -> tensor<si32>
%3 = "mps.constant"() <{value = dense<1> : tensor<si32>}> : () -> tensor<si32>
%4 = "mps.transpose"(%1, %2, %3) : (tensor<64x128xf32>, tensor<si32>, tensor<si32>) -> tensor<128x64xf32>
%5 = "mps.matmul"(%0, %4) <{transpose_lhs = false, transpose_rhs = false}> : (tensor<10x128xf32>, tensor<128x64xf32>) -> tensor<10x64xf32>
%6 = "mps.placeholder"() : () -> tensor<1x64xf32>
%7 = "mps.add"(%5, %6) : (tensor<10x64xf32>, tensor<1x64xf32>) -> tensor<10x64xf32>
CCV_NNC_GEMM_FORWARD [1]: [3] -> [1] (0)
|-> 1. 0x1438bd420 (0x285d90fc0:0) [2x320] 0.517578 0.953613 -0.921875 ..
|-> 2. 0x1438bd570 (0x285d841c0:0) [1280x320] -0.001888 0.001598 0.001110 ..
|-> 3. 0x1438bd5e0 (0x285d84280:0) [1280] -0.019775 0.008278 0.010788 ..
|<- 1. 0x1438a0000 (0x285da5600:0) [2x1280] 0.044556 -0.020798 0.078064 ..
CCV_NNC_SWISH_FORWARD [2]: [1] -> [1] (0)
|-> 1. 0x1438a0000 (0x285da5600:0) [2x1280] 0.044556 -0.020798 0.078064 ..
|<- 1. 0x1438a0000 (0x285da5600:0) [2x1280] 0.022781 -0.010292 0.040558 ..
CCV_NNC_GEMM_FORWARD [3]: [3] -> [1] (0)
|-> 1. 0x1438a0000 (0x285da5600:0) [2x1280] 0.022781 -0.010292 0.040558 ..
#!/usr/bin/env python
import argparse
import subprocess
import os
import re
import json
def read_version(version):
ver = re.compile('Using\s([\w\_\-]+)\s\(([\d\.]+)\)')
load("@bazel_tools//tools/build_defs/repo:git.bzl", "git_repository")
load("@bazel_tools//tools/build_defs/repo:http.bzl", "http_file")
git_repository(
name = "build_bazel_rules_apple",
remote = "https://github.com/bazelbuild/rules_apple.git",
commit = "524ea38c7c1f8a14bdea812f499aea7c5d3d1e13",
shallow_since = "1585159204 -0700"
)
static void taskcudaresume(cudaStream_t stream, cudaError_t status, void* userdata)
{
task_t* const task = (task_t*)userdata;
pthread_mutex_lock(&task->schd->mutex);
addtask(task->schd, task);
--task->schd->count.suspend;
pthread_cond_signal(&task->schd->cv);
pthread_mutex_unlock(&task->schd->mutex);
}
@liuliu
liuliu / task.c
Last active May 20, 2022 07:02
#include <stdio.h>
#include <stdint.h>
#include <stdlib.h>
#include <ucontext.h>
#include <pthread.h>
#include "nnc/gpu/ccv_nnc_compat.h"
union ptr_splitter {
void *ptr;
uint32_t part[2];
#!/usr/bin/env python
import argparse
import subprocess
import plistlib
import os
import xml.etree.ElementTree as ET
TEAM = '___YOUR_TEAM_ID__'
#!/usr/bin/env python
import argparse
import os
VARIANTS = [
'prod',
'debug',
]
// automatically generated by the FlatBuffers compiler, do not modify
import FlatBuffers
public enum MyGame {
public enum Sample {
public enum Color: Int8, Enum {
public typealias T = Int8
public static var byteSize: Int { return MemoryLayout<Int8>.size }
// automatically generated by the FlatBuffers compiler, do not modify
import FlatBuffers
public enum MyGame {
public enum Sample {
public enum Color: Int8, Enum {
public typealias T = Int8
public static var byteSize: Int { return MemoryLayout<Int8>.size }