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.
42 lines
1.5 KiB
Python
42 lines
1.5 KiB
Python
#!/usr/bin/env python3
|
|
"""Decorate every float conversion of a SPIR-V module NoContraction, so the driver keeps it.
|
|
|
|
usage: spv_exact_convert.py IN.spv [OUT.spv]
|
|
|
|
RADV folds float(float16_t(x)) back to x unless the conversions are marked exact; glslang's `precise` does not reach
|
|
conversions. With the decoration a binary16 rounding is two instructions (engine/rr/rr_exact.glsl, RR_EXACT_CONVERT)
|
|
instead of three with an opaque zero OR-ed into the bits.
|
|
"""
|
|
import struct
|
|
import sys
|
|
|
|
OP_DECORATE, OP_FCONVERT, NO_CONTRACTION = 71, 115, 42
|
|
|
|
|
|
def main():
|
|
src = sys.argv[1]
|
|
dst = sys.argv[2] if len(sys.argv) > 2 else src
|
|
data = open(src, 'rb').read()
|
|
words = list(struct.unpack(f'<{len(data) // 4}I', data))
|
|
if words[0] != 0x07230203:
|
|
sys.exit(f'{src}: not SPIR-V')
|
|
insts, i = [], 5
|
|
while i < len(words):
|
|
count = words[i] >> 16
|
|
insts.append((words[i] & 0xffff, words[i:i + count]))
|
|
i += count
|
|
ids = [w[2] for op, w in insts if op == OP_FCONVERT]
|
|
first_type = next(k for k, (op, _) in enumerate(insts) if 19 <= op <= 39) # annotations end where types begin
|
|
out = list(words[:5])
|
|
for k, (op, w) in enumerate(insts):
|
|
if k == first_type:
|
|
for result in ids:
|
|
out += [3 << 16 | OP_DECORATE, result, NO_CONTRACTION]
|
|
out += w
|
|
open(dst, 'wb').write(struct.pack(f'<{len(out)}I', *out))
|
|
print(f'{dst}: {len(ids)} conversions marked exact')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|