1.Previous
3.Next

void fft1D_1024 (__global float2 *in, __global float2 *out, __local float *sMemx, __local float *sMemy) { int tid = get_local_id(0); int blockIdx = get_group_id(0) * 1024 + tid; float2 data[16];

// starting index of data to/from global memory in = in + blockIdx; out = out + blockIdx;

globalLoads(data, in, 64); // coalesced global reads fftRadix16Pass(data); // in-place radix-16 pass twiddleFactorMul(data, tid, 1024, 0);

// local shuffle using local memory

1.Previous
3.Next