Commit 10466ee1 authored by Umang Yadav's avatar Umang Yadav
Browse files

add into docs

parent ec71b64c
......@@ -54,6 +54,14 @@ Runs reference and CPU or GPU implementations and checks outputs for consistency
Tolerance for RMS error (Default: 0.001)
.. option:: --atol [double]
Tolerance for elementwise absolute error (Default: 0.001)
.. option:: --rtol [double]
Tolerance for elementwise relative error (Default: 0.001)
.. option:: -i, --per-instruction
Verify each instruction
......
......@@ -56,6 +56,8 @@ See below for a comprehensive list of commands and option arguments, as well as
| --fp16 | Quantize for fp16 |
| --int8 | Quantize for int8 |
| --rms_tol | Tolerance for the RMS error |
| --atol | Tolerance for elementwise absolute error |
| --rtol | Tolerance for elementwise relative error |
| --per-instruction \| -i | Verify each instruction |
| --reduce \| -r | Reduce program and verify |
| --iterations \| -n | Number of iterations to run for perf report |
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment