Uh oh!
There was an error while loading. Please reload this page.
Math: Library: Add the hifi4 exponential function - #6801
Conversation
3ed16a6 to
131fc13Compare
lgirdwood
left a comment
There was a problem hiding this comment.
@andrula-song@singalsu pls review
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Extra blanks after ae_int64 *. You could also avoid this function proto with move of mul_s64() here.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
declare variables in the begin of function
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Declare all variables in the beginning
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Can you compare qt directly to integer constant without need for qt_temp?
There was a problem hiding this comment.
qt temp = qt; is used to prevent the following error in the event that (qt < CONVERG_ERROR)
no operator overload defined for binary operator '<' (operand types 'ae_int64' (aka '_TIE_xt_hifi2_ae_int64') 'long long')
can you please suggest clean approach.
Uh oh!
There was an error while loading. Please reload this page.
51bc618 to
3465959Compare3465959 to
a771b4aCompare
ShriramShastry
left a comment
There was a problem hiding this comment.
Thank you for looking at the code.
I incorporated the proposal and expressed my opinion.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
qt temp = qt; is used to prevent the following error in the event that (qt < CONVERG_ERROR)
no operator overload defined for binary operator '<' (operand types 'ae_int64' (aka '_TIE_xt_hifi2_ae_int64') 'long long')
can you please suggest clean approach.
a771b4a to
8eab8d6Comparelgirdwood
commented
Jan 4, 2023
@ShriramShastry btw, whats the speedup here vs generic C version ? |
9533b89 to
cacde9dCompareUh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
This unrelated change could be in another commit with title indicating improvement of cmocka test coverage. I assume the old test with 256 points would work with hifi4 version too.
cacde9d to
954d65fCompareUh oh!
There was an error while loading. Please reload this page.
04ebea6 to
b4c6345Compare
kv2019i
left a comment
There was a problem hiding this comment.
Code looks ready to go, but the Kconfig addition/rename needs clarification. See comment inline.
Uh oh!
There was an error while loading. Please reload this page.
ShriramShastry
commented
Jun 12, 2023
Kconfig, is enabled or disabled by below code, In the moment, it is disabled, to enable make default config EXP_FIXED |
b4c6345 to
751f887CompareShriramShastry
commented
Jun 12, 2023
Done !! Renamed |
kv2019i
left a comment
There was a problem hiding this comment.
Thanks @ShriramShastry , looks good now.
ShriramShastry
commented
Jun 14, 2023
Thank you. Is there any other unresolved issue that needs to be addressed? |
kv2019i
commented
Jun 14, 2023
@cujomalainey Ok to proceed with this? You still have a requested-changes pending. |
cujomalainey
commented
Jun 14, 2023
I'll re-review today |
cujomalainey
commented
Jun 15, 2023
looks like my comment is still open, would be nice to get it fixed but i won't block on it |
The 32-bit HiFi4 exponential library function has an accuracy of 1e-4, a unit in last place error of 5.60032793, and output ranges from 0.0067379470 to 148.4131591026 for inputs from -5 to +5 (Q4.28) (Q9.23). Signed-off-by: ShriramShastry <malladi.sastry@intel.com>
ShriramShastry
commented
Jun 15, 2023
Done !! |
The 32-bit HiFi4 exponential library function has an accuracy of 1e-4, a unit in last place error of 5.60032793, and output ranges from 0.0067379470 to 148.4131591026 for inputs from -5 to +5 (Q4.28) (Q9.23).
Signed-off-by: ShriramShastry malladi.sastry@intel.com