eliben

/* Minimal declarations for CUDA support.  Testing purposes only. */

#define __constant__ __attribute__((constant))
#define __device__ __attribute__((device))
#define __global__ extern "C" __attribute__((global))
#define __host__ __attribute__((host))
#define __shared__ __attribute__((shared))
#define __launch_bounds__(...) __attribute__((launch_bounds(__VA_ARGS__)))
#define __forceinline__ __attribute__((always_inline))

jboner

Latency Comparison Numbers (~2012)
----------------------------------
L1 cache reference                           0.5 ns
Branch mispredict                            5   ns
L2 cache reference                           7   ns                      14x L1 cache
Mutex lock/unlock                           25   ns
Main memory reference                      100   ns                      20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy             3,000   ns        3 us
Send 1K bytes over 1 Gbps network       10,000   ns       10 us
Read 4K randomly from SSD*             150,000   ns      150 us          ~1GB/sec SSD