Search help

Note: Searching from the top-level index page will search all documents. Searching from a specific document will search only that document.

Find an exact phrase: Wrap your search phrase in "" (double quotes) to only get results where the phrase is exactly matched. For example "PyTorch for the IPU" or "replicated tensor sharding"
Prefix query: Add an * (asterisk) at the end of any word to indicate a prefix query. This will return results containing all words with the specific prefix. For example tensor*

Fuzzy search: Use ~N (tilde followed by a number) at the end of any word for a fuzzy search. This will return results that are similar to the search word. N specifies the “edit distance” (fuzziness) of the match. For example Polibs~1
Words close to each other: ~N (tilde followed by a number) after a phrase (in quotes) returns results where the words are close to each other. N is the maximum number of positions allowed between matching words. For example "ipu version"~2
Logical operators. You can use the following logical operators in a search:
- + signifies AND operation
- | signifies OR operation
- - negates a single word or phrase (returns results without that word or phrase)
- () controls operator precedence

5.10. PopLibs

3.3.0

New features

Added new popops ops to support the PyTorch Geometric SplineConv operator:
- SplineBasis
- SplineWeighting
Added new popops element-wise unary operation nearbyint.

Bug Fixes

Allow users to compile IPU executables larger than 32 GiB. The size was originally limited as a sanity check and predated large systems where it is now possible to exceed this limit.

Other improvements

None

Known issues

None

Compatibility changes

None

3.2.0

New features

Added new popops elementwise unary operation exp2 (power of 2).

Bug Fixes

Fixed issue with static sparse MatMul that returned incorrect values for a specific mask.
Accurate cast of quarter to and from float for the Mk2 architecture used in the IPU-M2000 and Bow-2000.

Other improvements

Optimize performance of Cholesky factorisation.
Updates to the PopLibs API documentation

Known issues

None

Compatibility changes

None