23 lines
989 B
Plaintext
23 lines
989 B
Plaintext
// fast numerics: intermediate activations f16 (no FP8 re-quantisation), f32 accumulation through GEMM chains
|
|
// RX 7700 XT: memory-clause scheduling at the 192 VGPR cap; byte-identical to the default build, gfx1101 only.
|
|
// SWIN_PACKED_RESIDUAL (residual kept as already-rounded halves until the output projection): byte-identical,
|
|
// -1.6% on the captured dec2 launch (0.768 -> 0.756 ms, 3 alternating reps of 100); enc1/enc2/dec1/tube: no gain
|
|
// d4r-build-flags-gfx1101: -mllvm -misched=gcn-max-memory-clause -DSWIN_PACKED_RESIDUAL
|
|
#define SWIN_NO_Q8
|
|
#define SWIN_F32ACC
|
|
#ifndef SWIN_MAX_VGPR
|
|
#define SWIN_MAX_VGPR 192
|
|
#endif
|
|
#ifndef SWIN_MLP_R
|
|
#define SWIN_MLP_R(NW) 2
|
|
#endif
|
|
// RDNA4 native FP8 builds use the token-lane block (swin_tok.h); -DSWIN_NO_TOKEN_LANES keeps swin_block.h
|
|
#ifndef SWIN_NO_TOKEN_LANES
|
|
#define SWIN_TOKEN_LANES
|
|
#endif
|
|
#include "swin_block.h"
|
|
#ifndef SWIN_NW
|
|
#define SWIN_NW 8
|
|
#endif
|
|
SWIN_MODULE_W(rrlite_dec2_4x4, 96, 4, SWIN_NW, 0, false, CommonParams, 128)
|