tarantool / luajit / 12789057277

93%

tarantool/master: 93%

Build Type

push

github

Committed by Buristan

Commit Message

Disable FMA by default. Use -Ofma or jit.opt.start("+fma") to enable.

See the discussion in the corresponding ticket for the rationale.

(cherry picked from commit de2e1ca9d)

For the modulo operation, the arm64 VM uses `fmsub` [1] instruction,
which is the fused multiply-add (FMA [2]) operation (more precisely,
multiply-sub). Hence, it may produce different results compared to the
unfused one. This patch fixes the behaviour by using the unfused
instructions by default. However, the new JIT optimization flag (fma) is
introduced to make it possible to take advantage of the FMA
optimizations.

Sergey Kaplun:
* added the description and the test for the problem

[1]: https://developer.arm.com/documentation/dui0801/g/A64-Floating-point-Instructions/FMSUB
[2]: https://en.wikipedia.org/wiki/Multiply%E2%80%93accumulate_operation

Part of tarantool/tarantool#10709

Coverage Stats

5693 of 6032 branches covered (94.38%)

Branch coverage included in aggregate %.

3 of 3 new or added lines in 1 file covered. (100.0%)

8 existing lines in 3 files now uncovered.

21709 of 23437 relevant lines covered (92.63%)

2917207.35 hits per line