[all-commits] [llvm/llvm-project] c375ec: [flang] Use a "double-double" accumulator in SUM

[Peter Klausler via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c375ec86132984bc3915323fbe3f8c71f4d5503f
      https://github.com/llvm/llvm-project/commit/c375ec86132984bc3915323fbe3f8c71f4d5503f
  Author: peter klausler <pklausler at nvidia.com>
  Date:   2021-06-16 (Wed, 16 Jun 2021)

  Changed paths:
    M flang/runtime/sum.cpp

  Log Message:
  -----------
  [flang] Use a "double-double" accumulator in SUM

Use a "double-double" accumulator, a/k/a Kahan summation,
in the SUM intrinsic in the runtime for real & complex.
This seems to be the best-recommended technique for reducing
error, as opposed to the initial implementation of SUM's
distinct accumulators for positive and negative items.

Differential Revision: https://reviews.llvm.org/D104338