ayo
7c5d3c9157
Add native K/M/RR inference engines, HIP kernels, replay and validation harnesses, and Windows DLSS setup and runtime support. Include GPU profiling tools, build and packaging scripts, platform integration patches, and implementation documentation.
10 lines
461 B
Plaintext
10 lines
461 B
Plaintext
// Diagnostic only: all finite OCP e4m3 encodings, including signed zero.
|
|
#include "../../kernels/m/swin_common.h"
|
|
struct PackParams { const half_t* input; uint32_t* output; };
|
|
extern "C" __global__ void fp8_pack_probe(PackParams p) {
|
|
const unsigned lane = blockIdx.x * 32 + threadIdx.x;
|
|
if (lane >= 32) return;
|
|
const auto packed = to_fp8(*(const sop*)(p.input + lane * 8));
|
|
p.output[lane * 2] = packed[0]; p.output[lane * 2 + 1] = packed[1];
|
|
}
|