Tenstorrent Ascalon-X veclibm benchmarks
| function | scalar libc fp64/cycle | RVV veclibm fp64/cycle | speedup |
| exp | 0.074551 | 0.123260 | 1.65x |
| exp2 | 0.080206 | 0.113898 | 1.42x |
| expm1 | 0.031066 | 0.088274 | 2.84x |
| log | 0.064868 | 0.093449 | 1.44x |
| log10 | 0.025500 | 0.089728 | 3.52x |
| log2 | 0.053159 | 0.094031 | 1.77x |
| log1p | 0.025457 | 0.101784 | 4.00x |
| sqrt | 0.038458 | 0.469859 | 12.22x |
| cbrt | 0.019960 | 0.092887 | 4.65x |
| sin | 0.037988 | 0.092807 | 2.44x |
| cos | 0.046597 | 0.089751 | 1.93x |
| tan | 0.036433 | 0.059818 | 1.64x |
| asin | 0.024479 | 0.076888 | 3.14x |
| acos | 0.023895 | 0.070666 | 2.96x |
| atan | 0.062279 | 0.052780 | 0.85x |
| sinh | 0.019565 | 0.064454 | 3.29x |
| cosh | 0.030657 | 0.079009 | 2.58x |
| tanh | 0.018533 | 0.065529 | 3.54x |
| asinh | 0.011699 | 0.049604 | 4.24x |
| acosh | 0.034480 | 0.046607 | 1.35x |
| atanh | 0.011936 | 0.079012 | 6.62x |
| erf | 0.060170 | 0.047986 | 0.80x |
| erfc | 0.046640 | 0.034307 | 0.74x |
| tgamma | 0.010754 | 0.018737 | 1.74x |
| lgamma | 0.021356 | 0.014150 | 0.66x |