MCPcopy Create free account
hub / github.com/NVIDIA/TensorRT / readFromSmem

Function readFromSmem

plugin/instanceNormalizationPlugin/instanceNormCommon.h:315–320  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

313}
314
315DEVICE_FUNCTION void readFromSmem(float (&x)[2], float const* smem, int32_t idx)
316{
317 float2 tmp = *(float2 const*) &smem[2 * idx];
318 x[0] = tmp.x;
319 x[1] = tmp.y;
320}
321
322DEVICE_FUNCTION void readFromSmem(float (&x)[4], float const* smem, int32_t idx)
323{

Callers 3

parallelSums_16x2Function · 0.85
parallelSums_8x4Function · 0.85
parallelSumsFunction · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected