https://github.com/NVIDIA/cuda-samples/tree/master/Samples/UnifiedMemoryPerf
Unified and other CUDA Memories Performance
该示例演示了使用带/不带提示的统一内存矩阵乘法内核以及其他类型的内存（例如零拷贝缓冲区，可分页，分页锁定的内存，在单个GPU上执行同步和异步传输）的性能比较:
UMhint UMhntAs UMeasy 0Copy MemCopy CpAsync CpHpglk CpPglAs
"UMhint", // Managed Memory With Hints
"UMhntAs", // Managed Memory With_Hints Async
"UMeasy", // Managed_Memory with No Hints
"0Copy", // Zero Copy
"MemCopy", // USE HOST PAGEABLE AND DEVICE_MEMORY
"CpAsync", // USE HOST PAGEABLE AND DEVICE_MEMORY ASYNC
"CpHpglk", // USE HOST PAGELOCKED AND DEVICE MEMORY
"CpPglAs" // USE HOST PAGELOCKED AND DEVICE MEMORY ASYNC
测试结果：
-
(Dell Precision 5520) Device 0: "Quadro M1200" （Maxwell cc5.0）
Quadro M1200
-Jetson Xavier capability 7.2 （Volta）
- (机械革命S1)：mx150（Pascal）
