From: lkcl Date: Fri, 16 Sep 2022 09:49:26 +0000 (+0100) Subject: (no commit message) X-Git-Tag: opf_rfc_ls005_v1~407 X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=32b4c1471dbc2dd6875affdce511afcee2154a9f;p=libreriscv.git --- diff --git a/openpower/sv/rfc/ls001.mdwn b/openpower/sv/rfc/ls001.mdwn index e4ce2014f..d958e41a8 100644 --- a/openpower/sv/rfc/ls001.mdwn +++ b/openpower/sv/rfc/ls001.mdwn @@ -407,11 +407,14 @@ into `sv.bc`: it became CISC-like in its complexity and was quickly reverted. [REMAP](https://libre-soc.org/openpower/sv/remap) is extremely advanced but brings features already present in other -DSPs and Supercomputing ISAs. Normally (without these features) -algorithms are are costly or +DSPs and Supercomputing ISAs. The usual sequential progression +through elements is pushed through a hardware-defined +*fully Deterministic* +"remapping". Normally (without REMAP) +algorithms are costly or convoluted to implement. They are typically implemented as hard-coded fully loop-unrolled assembler which is often -auto-generated by specialist dedicated tools, or written +auto-generated by specialist tools, or written entirely by hand. All REMAP Schedules *including Indexed* are 100% Deterministic from their point of declaration, @@ -438,6 +441,9 @@ REMAP Schedules, such as Complex Number FFTs. * **Parallel Reduction** REMAP, performs an automatic map-reduce using *any suitable scalar operation*. +Note that predication is possible on REMAP but is hard to use effectively. +It is often best to make copies of data (`VCOMPRESS`) then apply REMAP. + \newpage{} # Scalar Operations