hash160 << <3, BLOCK_SIZE >> >(dev_pattern, dev_out, dev_nonce);
same error
Topic: c++ problem (Read 156 times)
<<>> is an extension to C++ to launch CUDA kernels, it is perfectly valid in CUDA code
https://medium.com/analytics-vidhya/cuda-compute-unified-device-architecture-part-2-f3841c25375e
https://medium.com/analytics-vidhya/cuda-compute-unified-device-architecture-part-2-f3841c25375e
CUDA I don't know
So the only error is that extra space and should have been
Code:
hash160 <<< 3, BLOCK_SIZE >>>(dev_pattern, dev_out, dev_nonce);
??Or also Visual Studio doesn't handle this well or is missing something?
That Medium page also tells (yeah, that guy was installing on Linux) about CUDA Toolkit and so on.
The space doesn't matter, Visual Studio autocorrects it to <<
<<>> is an extension to C++ to launch CUDA kernels, it is perfectly valid in CUDA code
https://medium.com/analytics-vidhya/cuda-compute-unified-device-architecture-part-2-f3841c25375e
https://medium.com/analytics-vidhya/cuda-compute-unified-device-architecture-part-2-f3841c25375e
CUDA I don't know
So the only error is that extra space and should have been
Code:
hash160 <<< 3, BLOCK_SIZE >>>(dev_pattern, dev_out, dev_nonce);
??Or also Visual Studio doesn't handle this well or is missing something?
That Medium page also tells (yeah, that guy was installing on Linux) about CUDA Toolkit and so on.
I solved everything but there is still one small problem
hash160 << < 3, BLOCK_SIZE >> >(dev_pattern, dev_out, dev_nonce);
hash160 << < 3, BLOCK_SIZE >> >(dev_pattern, dev_out, dev_nonce);
<<< works in java, not in C++
<< < needs something in between (a bitwise shift maybe and then a comparison?)
But, since in the first post we have
Code:
__global__ void hash160(char *pattern, unsigned char *out, uint32_t *nonce)
you seem to be calling that void function, hence I would comment that erroneous line (at least for now) and put instead:
Code:
hash160(dev_pattern, dev_out, dev_nonce);
I have difficulties to understand what you aim for with a code you cannot even read.
<<
https://medium.com/analytics-vidhya/cuda-compute-unified-device-architecture-part-2-f3841c25375e
I solved everything but there is still one small problem
hash160 << < 3, BLOCK_SIZE >> >(dev_pattern, dev_out, dev_nonce);
hash160 << < 3, BLOCK_SIZE >> >(dev_pattern, dev_out, dev_nonce);
<< < needs something in between (a bitwise shift maybe and then a comparison?)
But, since in the first post we have
__global__ void hash160(char *pattern, unsigned char *out, uint32_t *nonce)
you seem to be calling that void function, hence I would comment that erroneous line (at least for now) and put instead:
hash160(dev_pattern, dev_out, dev_nonce);
It seems that I was wrong, sorry, see below.
yes but it doesn't change anything
When you created the project, did you create it as a CUDA project so it uses the CUDA compiler?
I solved everything but there is still one small problem
hash160 << < 3, BLOCK_SIZE >> >(dev_pattern, dev_out, dev_nonce);
in red probleme
hash160 << < 3, BLOCK_SIZE >> >(dev_pattern, dev_out, dev_nonce);
in red probleme
Where that code come from, seems that you only copy and paste part of some code.
The variables that you are refering don't exist:
blockIdx, blockDim and threadIdx aren't declared anywhere.
Regards!
The variables that you are refering don't exist:
Code:
uint32_t index = blockIdx.x * blockDim.x + threadIdx.x;
blockIdx, blockDim and threadIdx aren't declared anywhere.
Regards!
I installed openssl but nothing works
Those are probably just warnings because Visual Studio doesn't always know about internal CUDA variables. The main issue is that it can't find your OpenSSL header file, that's what's blocking the compile.
Code:
#include
#include
#include
#include
#include
#include
#define BLOCK_SIZE 1024
__global__ void hash160(char *pattern, unsigned char *out, uint32_t *nonce)
{
uint32_t index = blockIdx.x * blockDim.x + threadIdx.x;
unsigned char hash[SHA256_DIGEST_LENGTH];
char str[64];
for (int i = 0; i < 9; i++) {
str[i] = pattern[i];
}
for (uint32_t i = *nonce; i < UINT32_MAX; i += gridDim.x * blockDim.x) {
sprintf(&str[9], "%08x", i);
SHA256((const unsigned char*)str, strlen(str), hash);
RIPEMD160(hash, SHA256_DIGEST_LENGTH, &out[index * 20]);
if (out[index * 20] == 0x00 && out[index * 20 + 1] == 0x00) {
// Found a match!
*nonce = i;
break;
}
}
}
int main()
{
char pattern[10] = "1abcdefg"; // 9 characters pattern
// Allocate memory on the host
unsigned char *out = new unsigned char[3 * 20];
uint32_t *nonce = new uint32_t;
*nonce = 0;
// Allocate memory on the device
char *dev_pattern;
unsigned char *dev_out;
uint32_t *dev_nonce;
cudaMalloc((void**)&dev_pattern, 10);
cudaMalloc((void**)&dev_out, 3 * 20);
cudaMalloc((void**)&dev_nonce, sizeof(uint32_t));
// Copy input data to the device
cudaMemcpy(dev_pattern, pattern, 10, cudaMemcpyHostToDevice);
cudaMemcpy(dev_out, out, 3 * 20, cudaMemcpyHostToDevice);
cudaMemcpy(dev_nonce, nonce, sizeof(uint32_t), cudaMemcpyHostToDevice);
// Launch the kernel
hash160 << < 3, BLOCK_SIZE >> >(dev_pattern, dev_out, dev_nonce);
// Copy output data from the device
cudaMemcpy(out, dev_out, 3 * 20, cudaMemcpyDeviceToHost);
cudaMemcpy(nonce, dev_nonce, sizeof(uint32_t), cudaMemcpyDeviceToHost);
// Print the results
for (int i = 0; i < 3; i++) {
std::cout << "Address " << i + 1 << ": " << std::setbase(16);
for (int j = 0; j < 20; j++) {
std::cout << std::setw(2) << std::setfill('0') << (int)out[i * 20 + j];
}
std::cout << std::endl;
}
std::cout << "Nonce: " << *nonce << std::endl;
// Free memory
delete[] out;
delete nonce;
cudaFree(dev_pattern);
cudaFree(dev_out);
cudaFree(dev_nonce);
return 0;
}
#include
#include
#include
#include
#include
#define BLOCK_SIZE 1024
__global__ void hash160(char *pattern, unsigned char *out, uint32_t *nonce)
{
uint32_t index = blockIdx.x * blockDim.x + threadIdx.x;
unsigned char hash[SHA256_DIGEST_LENGTH];
char str[64];
for (int i = 0; i < 9; i++) {
str[i] = pattern[i];
}
for (uint32_t i = *nonce; i < UINT32_MAX; i += gridDim.x * blockDim.x) {
sprintf(&str[9], "%08x", i);
SHA256((const unsigned char*)str, strlen(str), hash);
RIPEMD160(hash, SHA256_DIGEST_LENGTH, &out[index * 20]);
if (out[index * 20] == 0x00 && out[index * 20 + 1] == 0x00) {
// Found a match!
*nonce = i;
break;
}
}
}
int main()
{
char pattern[10] = "1abcdefg"; // 9 characters pattern
// Allocate memory on the host
unsigned char *out = new unsigned char[3 * 20];
uint32_t *nonce = new uint32_t;
*nonce = 0;
// Allocate memory on the device
char *dev_pattern;
unsigned char *dev_out;
uint32_t *dev_nonce;
cudaMalloc((void**)&dev_pattern, 10);
cudaMalloc((void**)&dev_out, 3 * 20);
cudaMalloc((void**)&dev_nonce, sizeof(uint32_t));
// Copy input data to the device
cudaMemcpy(dev_pattern, pattern, 10, cudaMemcpyHostToDevice);
cudaMemcpy(dev_out, out, 3 * 20, cudaMemcpyHostToDevice);
cudaMemcpy(dev_nonce, nonce, sizeof(uint32_t), cudaMemcpyHostToDevice);
// Launch the kernel
hash160 << < 3, BLOCK_SIZE >> >(dev_pattern, dev_out, dev_nonce);
// Copy output data from the device
cudaMemcpy(out, dev_out, 3 * 20, cudaMemcpyDeviceToHost);
cudaMemcpy(nonce, dev_nonce, sizeof(uint32_t), cudaMemcpyDeviceToHost);
// Print the results
for (int i = 0; i < 3; i++) {
std::cout << "Address " << i + 1 << ": " << std::setbase(16);
for (int j = 0; j < 20; j++) {
std::cout << std::setw(2) << std::setfill('0') << (int)out[i * 20 + j];
}
std::cout << std::endl;
}
std::cout << "Nonce: " << *nonce << std::endl;
// Free memory
delete[] out;
delete nonce;
cudaFree(dev_pattern);
cudaFree(dev_out);
cudaFree(dev_nonce);
return 0;
}
blockIdx.x * blockDim.x + threadIdx.x undefinited why
Jump to: