With FP16_OVFL=1 the hardware writes an f16 result that would round to
infinity as the largest finite value of that sign, unless a source
operand is infinite. v_div_fixup_f16 keeps the infinity it writes for a
zero denominator or an infinite numerator. Measured on RDNA2 (gfx1036)
at IEEE=0 and IEEE=1 with f16 denormals kept and flushed.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The template allocated a fixed 4 KiB of LDS, so kernels with immediate
offsets past it could not run. --lds (Python lds) sets the group segment
size in bytes, up to 64 KiB, with 4096 as the default.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
BREAKING CHANGE: CLI and Python callers must supply all seven float
controls. Add clamp, rounding and FP16 overflow settings so hardware
measurements cannot silently use an unintended mode.
Refs #981
ale
Muhammad Umair
Adrià Franch