This implements the trivial change needed to move back from the hip{Something}_{x, y, z} macros to the natural CUDA syntax of Something.{x, y, z}. This is contained in lines 384-404 in hip_runtime.h. All of the other changes have to do with changing unit tests to use this syntax. The macros are retained for backwards compatibility.

This commit is contained in:
Alex Voicu
2017-11-19 01:54:12 +00:00
والد 85975e719d
کامیت cffd0e14eb
60فایلهای تغییر یافته به همراه270 افزوده شده و 248 حذف شده
@@ -34,7 +34,7 @@ THE SOFTWARE.
__global__ void vectorAdd(hipLaunchParm lp, float *Ad, float *Bd) {
HIP_DYNAMIC_SHARED(float, sBd);
int tx = hipThreadIdx_x;
int tx = threadIdx.x;
for(int i=0;i<LEN/64;i++) {
sBd[tx + i * 64] = Ad[tx + i * 64] + 1.0f;
Bd[tx + i * 64] = sBd[tx + i * 64];