3

我正在尝试如何在 numba 中使用 cuda。但是，在 numba 中发生了一些我不明白的事情。这是我的代码

from numba import cuda
@cuda.jit
def matmul(A, B, C):
"""Perform square matrix multiplication of C = A * B
"""
d=cuda.local.array((3,3),dtype=numba.float64)
i, j = cuda.grid(2)
if i < C.shape[0] and j < C.shape[1]:
    tmp = 0.
    for k in range(A.shape[1]):
        tmp += A[i, k] * B[k, j]
    C[i, j] = tmp

这是我为使用 numba.cuda 进行测试而自定义的矩阵函数。在运行测试之前，我还在以下代码中加载了数组：

import numpy as np
a=np.random.rand(2000,2000)
b=np.random.rand(2000,2000)
c=np.empty((2000,2000))
a1=cuda.to_device(a)
b1=cuda.to_device(b)
c1=cuda.to_device(c)

然后我使用以下代码进行实验：

from time import time
count =0
start=time()
for i in range(2000):
  matmul[(256,256),(16,16)](a1,b1,c1)
  count +=1
  print(count)

for 循环在前 1028 次运行中运行良好。但是它在第 1029 次运行时给了我一个错误，错误消息如下：

在此处输入图像描述

在此处输入图像描述

这是我从 numba.cuda 调用的 cuda 信息

from numba import cuda
gpu = cuda.get_current_device()
print("name = %s" % gpu.name)
print("maxThreadsPerBlock = %s" % str(gpu.MAX_THREADS_PER_BLOCK))
print("maxBlockDimX = %s" % str(gpu.MAX_BLOCK_DIM_X))
print("maxBlockDimY = %s" % str(gpu.MAX_BLOCK_DIM_Y))
print("maxBlockDimZ = %s" % str(gpu.MAX_BLOCK_DIM_Z))
print("maxGridDimX = %s" % str(gpu.MAX_GRID_DIM_X))
print("maxGridDimY = %s" % str(gpu.MAX_GRID_DIM_Y))
print("maxGridDimZ = %s" % str(gpu.MAX_GRID_DIM_Z))
print("maxSharedMemoryPerBlock = %s" % 
str(gpu.MAX_SHARED_MEMORY_PER_BLOCK))
print("asyncEngineCount = %s" % str(gpu.ASYNC_ENGINE_COUNT))
print("canMapHostMemory = %s" % str(gpu.CAN_MAP_HOST_MEMORY))
print("multiProcessorCount = %s" % str(gpu.MULTIPROCESSOR_COUNT))
print("warpSize = %s" % str(gpu.WARP_SIZE))
print("unifiedAddressing = %s" % str(gpu.UNIFIED_ADDRESSING))
print("pciBusID = %s" % str(gpu.PCI_BUS_ID))
print("pciDeviceID = %s" % str(gpu.PCI_DEVICE_ID))

输出是：

名称 = b'GeForce GTX 1050 Ti'

maxThreadsPerBlock = 1024

maxBlockDimX = 1024

maxBlockDimY = 1024

maxBlockDimZ = 64

maxGridDimX = 2147483647

maxGridDimY = 65535

maxGridDimZ = 65535

maxSharedMemoryPerBlock = 49152

asyncEngineCount = 2

canMapHostMemory = 1

多处理器计数 = 6

扭曲大小 = 32

统一寻址 = 1

pciBusID = 3

pciDeviceID = 0

4

0 回答 0