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.
7 lines
332 B
Plaintext
7 lines
332 B
Plaintext
// CU mode: the waves of a window share one L0 cache (1-6% faster here; slower in the wide layers)
|
|
// QKV chains two at a time (K-race port): -3% on top of op_imgt (paired gfx1200 replay, exact)
|
|
// d4r-build-flags: -mcumode -DPWIN_QKV_SPLIT
|
|
#define PWIN_F32ACC
|
|
#include "pwin_layer.h"
|
|
PWIN_ENCODER(dltss_pwin_enc2_layer, 2, 64, 96)
|