F3 - fsqrt (square root)
F4 - fexp2 (2^x)
F5 - flog2
- F6 - fsin
- F7 - fcos
+ F6 - fsin1pi
+ F7 - fcos1pi
F9 - fatan_pt1
These in FP32 and FP16 only: no FP32 hardware, at all.
AMD's R600 GPU (R600\_Instruction\_Set\_Architecture.pdf) and the
RDNA ISA (RDNA\_Shader\_ISA\_5August2019.pdf, Table 22, Section 6.3) have:
- COS (appx)
+ COS2PI (appx)
EXP2
LOG (IEEE754)
RECIP
RSQRT
SQRT
- SIN (appx)
+ SIN2PI (appx)
AMD RDNA has F16 and F32 variants of all the above, and also has F64
variants of SQRT, RSQRT and RECIP. It is interesting that even the