NASP/cuda-samples
60
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-04-02 23:55:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

Bug 5970525: Update a minor issue of Samples/0_Introduction/fp16ScalarProduct

Browse Source
This commit is contained in:
Shawn Zeng 2026-03-11 16:22:10 +08:00
parent e32d17e67e
commit 722c5dd069
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct.cu
View File

@ -94,7 +94,7 @@ scalarProductKernel_intrinsics(half2 const *const a, half2 const *const b, float
shArray[threadIdx.x] = __float2half2_rn(0.f); shArray[threadIdx.x] = __float2half2_rn(0.f);
half2 value = __float2half2_rn(0.f); half2 value = __float2half2_rn(0.f);
for (int i = threadIdx.x + blockDim.x + blockIdx.x; i < size; i += stride) { for (int i = threadIdx.x + blockDim.x * blockIdx.x; i < size; i += stride) {
value = __hfma2(a[i], b[i], value); value = __hfma2(a[i], b[i], value);
} }
@ -118,7 +118,7 @@ scalarProductKernel_native(half2 const *const a, half2 const *const b, float *co
half2 value(0.f, 0.f); half2 value(0.f, 0.f);
shArray[threadIdx.x] = value; shArray[threadIdx.x] = value;
for (int i = threadIdx.x + blockDim.x + blockIdx.x; i < size; i += stride) { for (int i = threadIdx.x + blockDim.x * blockIdx.x; i < size; i += stride) {
value = a[i] * b[i] + value; value = a[i] * b[i] + value;
} }