How to use the flags to enable\disable L1 Cache of GPU on Windows?

Accelerated Computing CUDA CUDA Programming and Performance
1

I am new to Cuda.

I have read through GPU books that one can disable L1 cache at compile time adding the flag -Xptxas -dlcm=cg to nvcc for all memory operations using nvcc. Also,the L1 cache can also be explicitly enabled with the flag -Xptxas -dlcm = ca.

I do not know how to write these commands in command prompt on windows.

2

These flags should be used during code compilation,

Enable: nvcc -Xptxas -dlcm=ca test.cu
Disbable: nvcc -Xptxas -dlcm=cg test.cu