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.
34 lines
1.1 KiB
Python
34 lines
1.1 KiB
Python
#!/usr/bin/env python3
|
|
"""Append the RDNA3 (RR_GFX11) widened copy of a native stage's weight file and print its f16 element offset (W_WIDE).
|
|
|
|
usage: widen_weights.py WEIGHTS.bin [OUT.bin] (default: in place)
|
|
|
|
Element W_WIDE + j of the file's f16 view is byte j of the original image as ZLUDA widens an FP8 operand on gfx11
|
|
(rr_gfx11.glsl): the magnitude at bits 7..14, the sign at bit 15, the NaN code with bit 14 set too, i.e. the binary16
|
|
of value * 2^-8. Bytes that are not FP8 (tables, binary16 data) are widened as well and never read. W_WIDE is the
|
|
original size rounded up to 512 bytes, halved.
|
|
"""
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import numpy as np
|
|
|
|
|
|
def widen(image):
|
|
b = np.frombuffer(image, np.uint8).astype(np.uint16)
|
|
mag = b & 0x7f
|
|
mag = mag | ((mag + 1) & 0x80)
|
|
return ((mag << 7) | ((b & 0x80) << 8)).astype('<u2').tobytes()
|
|
|
|
|
|
def main():
|
|
src = Path(sys.argv[1]); dst = Path(sys.argv[2]) if len(sys.argv) > 2 else src
|
|
image = src.read_bytes()
|
|
base = (len(image) + 511) // 512 * 512
|
|
dst.write_bytes(image + bytes(base - len(image)) + widen(image))
|
|
print(base // 2)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|