News for hackers. Stuff that matters.
Re:Reverse-engineering the Yamaha DX7 synthesizer's sound ch... by RossBencina on Friday January 12, 2024 @07:13PM (#38975937)
Historically, float to integer conversions in C on x86 were very slow due to the compiler reconfiguring the FPU rounding mode for each conversion.
Re:Reverse-engineering the Yamaha DX7 synthesizer's sound ch... by raphlinus on Friday January 12, 2024 @07:57PM (#38976265)
Historically yes. This is most definitely not true since processors had SSE3 (~2004), using the FISTTP instruction, or I think you can also use the packed float to integer instructions like CVTTPS2PI as far back as SSE (1999).