Nahuel Genchi a12ddaa905 fix(shader): round v_fma_f64 once for subnormal operands and results ...

A subnormal operand sent v_fma_f64 to a separate multiply and add, and a
subnormal result was rounded twice: once to 53 bits in the scaled domain
and again by the power-of-two rescale. Both differ from IEEE 754
fusedMultiplyAdd in the last bit.

Subnormal operands are now widened by 2^64 and enter the exact path with
their exponent lowered by 64. The exact path keeps the sign of the residual
between the 53-bit result and the exact sum; when the result lands on a
midpoint of the subnormal grid it is moved one ulp towards the exact sum
before the single final rounding. Normal results are rebuilt by setting
the exponent, so only a subnormal result rounds. v_div_fmas_f64 shares the
path.

2026-10-10 00:38:04 +02:00

..

ARCHITECTURE.md

feat(shader): implement s_swappc_b64 fetch-shader call

2026-10-08 20:05:24 +02:00

BUILD.md

docs(build): note antivirus quarantine of relinker test executables on Windows

2026-10-09 15:56:29 +02:00

CONVENTIONS.md

refactor(docs): separated user and dev in docs + compatibility file

2026-09-28 22:58:17 +03:00

HW_ORACLE.md

feat(hw-oracle): make the group segment size an option

2026-10-09 12:47:59 -03:00

PROGRESS.md

fix(progress): exclude library test fixtures from function counts

2026-10-08 17:30:43 +05:30

TechnicalDebt.md

fix(shader): round v_fma_f64 once for subnormal operands and results

2026-10-10 00:38:04 +02:00