[prev in list] [next in list] [prev in thread] [next in thread] 

List:       llvm-commits
Subject:    [PATCH] D28508: [NVPTX] Implement NVPTXTargetLowering::getSqrtEstimate.
From:       escha via Phabricator via llvm-commits <llvm-commits () lists ! llvm ! org>
Date:       2017-01-31 23:31:58
Message-ID: 5ea74e11c8849567ca95fff4a460c8c5 () localhost ! localdomain
[Download RAW message or body]

escha added a comment.

That really surprises me that it's faster! I would expect SFU functions like \
RCP/RSQRT to dwarf the cost of a multiply, especially for double.

Also, do be careful that rcp(rsqrt(x)) and x * rsqrt(x) have different precisions \
under some implementations (because fmul is 0.5 ULP, while rcp/rsqrt may be as low as \
2.5 ULP each).


Repository:
  rL LLVM

https://reviews.llvm.org/D28508



_______________________________________________
llvm-commits mailing list
llvm-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits


[prev in list] [next in list] [prev in thread] [next in thread]