c1e168fdbe
+ Microarchitecture optimizations + 64-bit support + Xilinx FPGA support + LLVM-16 support + Refactoring and quality control fixes minor update minor update minor update minor update minor update minor update cleanup cleanup cache bindings and memory perf refactory minor update minor update hw unit tests fixes minor update minor update minor update minor update minor update minor udpate minor update minor update minor update minor update minor update minor update minor update minor updates minor updates minor update minor update minor update minor update minor update minor update minor updates minor updates minor updates minor updates minor update minor update
22 lines
687 B
Common Lisp
22 lines
687 B
Common Lisp
__kernel void DotProduct (__global float* a, __global float* b, __global float* c, int iNumElements)
|
|
{
|
|
// find position in global arrays
|
|
int iGID = get_global_id(0);
|
|
|
|
// bound check (equivalent to the limit on a 'for' loop for standard/serial C code
|
|
//printf("%d, %d\n", iGID, iNumElements);
|
|
if (iGID >= iNumElements)
|
|
{
|
|
return;
|
|
}
|
|
|
|
// process
|
|
int iInOffset = iGID << 2;
|
|
c[iGID] = a[iInOffset] * b[iInOffset]
|
|
+ a[iInOffset + 1] * b[iInOffset + 1]
|
|
+ a[iInOffset + 2] * b[iInOffset + 2]
|
|
+ a[iInOffset + 3] * b[iInOffset + 3];
|
|
//float cc = c[iGID];
|
|
|
|
//printf("c[%d]=%f\n", iGID, cc);
|
|
} |