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.
6 lines
315 B
Plaintext
6 lines
315 B
Plaintext
// op_imgt / uniform wave index: 2-10% slower here (paired gfx1200 replay), old address form kept
|
|
// d4r-build-flags: -DPWIN_NO_IMGT -DPWIN_PLAIN_WV
|
|
// NG = 8 (32 waves per window): faster on gfx1200 in paired replay (local k9060xt-opt v3)
|
|
#include "pwin_wide.h"
|
|
WIDE_ENCODER(dltss_pwin_enc4_layer, 4, 128, 160, 8)
|