CUDA

dim3  gridDim  	dimensions of grid
dim3  blockDim 	dimensions of block
uint3 blockIdx 	block index within grid
uint3 threadIdx	thread index within block
int   warpSize 	number of threads in warp

__global__ void kernel( ... ) { ... }

dim3 blocks( nx, ny, nz );           // cuda 1.x has 1D and 2D grids, cuda 2.x adds 3D grids
dim3 threadsPerBlock( mx, my, mz );  // cuda 1.x has 1D, 2D, and 3D blocks

kernel<<< blocks, threadsPerBlock >>>( ... );

__threadfence_block(); 	wait until memory accesses are visible to block
__threadfence();       	wait until memory accesses are visible to block and device
__threadfence_system();	wait until memory accesses are visible to block and device and host (2.x)
__syncthreads();       	wait until all threads reach sync

__device__ float* pointer;
cudaMalloc( (void**) &pointer, size );
cudaFree( pointer );

__constant__ float dev_data[n];
float host_data[n];
cudaMemcpyToSymbol  ( dev_data,  host_data, sizeof(host_data) );  // dev_data  = host_data
cudaMemcpyFromSymbol( host_data, dev_data,  sizeof(host_data) );  // host_data = dev_data

// direction is one of cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost
cudaMemcpy     ( dst_pointer, src_pointer, size, direction );
cudaMemcpyAsync( dst_pointer, src_pointer, size, direction, stream );

// using column-wise notation
// (the CUDA docs describe it for images; a “row” there equals a matrix column)
// _bytes indicates arguments that must be specified in bytes
cudaMemcpy2D     ( A_dst, lda_bytes, B_src, ldb_bytes, m_bytes, n, direction );
cudaMemcpy2DAsync( A_dst, lda_bytes, B_src, ldb_bytes, m_bytes, n, direction, stream );

// cublas makes copies easier for matrices, e.g., less use of sizeof
// copy x => y
cublasSetVector     ( n, elemSize, x_src_host, incx, y_dst_dev,  incy );
cublasGetVector     ( n, elemSize, x_src_dev,  incx, y_dst_host, incy );
cublasSetVectorAsync( n, elemSize, x_src_host, incx, y_dst_dev,  incy, stream );
cublasGetVectorAsync( n, elemSize, x_src_dev,  incx, y_dst_host, incy, stream );

// copy A => B
cublasSetMatrix     ( rows, cols, elemSize, A_src_host, lda, B_dst_dev,  ldb );
cublasGetMatrix     ( rows, cols, elemSize, A_src_dev,  lda, B_dst_host, ldb );
cublasSetMatrixAsync( rows, cols, elemSize, A_src_host, lda, B_dst_dev,  ldb, stream );
cublasGetMatrixAsync( rows, cols, elemSize, A_src_dev,  lda, B_dst_host, ldb, stream );
Also, malloc and free work inside a kernel (2.x), but memory allocated in a kernel must be deallocated in a kernel (not the host). It can be freed in a different kernel, though.

old = atomicAdd ( &addr, value );  // old = *addr;  *addr += value
old = atomicSub ( &addr, value );  // old = *addr;  *addr –= value
old = atomicExch( &addr, value );  // old = *addr;  *addr  = value

old = atomicMin ( &addr, value );  // old = *addr;  *addr = min( old, value )
old = atomicMax ( &addr, value );  // old = *addr;  *addr = max( old, value )

// increment up to value, then reset to 0  
// decrement down to 0, then reset to value
old = atomicInc ( &addr, value );  // old = *addr;  *addr = ((old >= value) ? 0 : old+1 )
old = atomicDec ( &addr, value );  // old = *addr;  *addr = ((old == 0) or (old > val) ? val : old–1 )

old = atomicAnd ( &addr, value );  // old = *addr;  *addr &= value
old = atomicOr  ( &addr, value );  // old = *addr;  *addr |= value
old = atomicXor ( &addr, value );  // old = *addr;  *addr ^= value

// compare-and-store
old = atomicCAS ( &addr, compare, value );  // old = *addr;  *addr = ((old == compare) ? value : old)

int __all   ( predicate );
int __any   ( predicate );
int __ballot( predicate );  // nth thread sets nth bit to predicate

clock_t clock();

// integer index
float tex1Dfetch( texRef, ix );

// float index
float tex1D( texRef, x       );
float tex2D( texRef, x, y    );
float tex3D( texRef, x, y, z );

float tex1DLayered( texRef, x    );
float tex2DLayered( texRef, x, y );

#include <cuda.h>

CUdevice dev;
CUdevprop properties;
char name[n];
int major, minor;
size_t bytes;

cuInit( 0 );  // takes flags for future use
cuDeviceGetCount         ( &cnt );
cuDeviceGet              ( &dev, index );
cuDeviceGetName          ( name, sizeof(name), dev );
cuDeviceComputeCapability( &major, &minor,     dev );
cuDeviceTotalMem         ( &bytes,             dev );
cuDeviceGetProperties    ( &properties,        dev );  // max threads, etc.

#include <cublas_v2.h>

cublasHandle_t handle;
cudaStream_t   stream;

cublasCreate( &handle );
cublasDestroy( handle );
cublasGetVersion( handle, &version );
cublasSetStream( handle,  stream );
cublasGetStream( handle, &stream );
cublasSetPointerMode( handle,  mode );
cublasGetPointerMode( handle, &mode );

cublasDdot ( handle, n, x, incx, y, incy, &result );  // result = ddot( n, x, incx, y, incy );
cublasDaxpy( handle, n, &alpha, x, incx, y, incy );   // daxpy( n, alpha, x, incx, y, incy );