From 4248b7be03b88499262913023215722d76ca21c1 Mon Sep 17 00:00:00 2001 From: lkcl Date: Thu, 4 May 2023 19:28:58 +0100 Subject: [PATCH] --- openpower/sv/mv.swizzle.mdwn | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/openpower/sv/mv.swizzle.mdwn b/openpower/sv/mv.swizzle.mdwn index efa246d07..75cc582d2 100644 --- a/openpower/sv/mv.swizzle.mdwn +++ b/openpower/sv/mv.swizzle.mdwn @@ -247,18 +247,18 @@ zero because there is no encoding space to select between -1, 0 and 1, and # Pack/Unpack Mode: It is possible to apply Pack and Unpack to Vectorised -swizzle moves, and these instructions are of EXTRA type -`RM-2P-1S1D-PU`. The interaction requires specific explanation +swizzle moves. The interaction requires specific explanation because it involves the separate SUBVLs (with destination SUBVL being separate). Key to understanding is that the source and destination SUBVL be "outer" loops instead of inner loops, exactly as in [[sv/remap]] Matrix mode, under the control -of `PACK_en` and `UNPACK_en`. +of `SVSTATE.PACK` and `SVSTATE.UNPACK`. Illustrating a "normal" SVP64 operation with `SUBVL!=1` (assuming no elwidth overrides): +``` def index(): for i in range(VL): for j in range(SUBVL): @@ -266,9 +266,11 @@ Illustrating a for idx in index(): operation_on(RA+idx) +``` For a separate source/dest SUBVL (again, no elwidth overrides): +``` # yield an outer-SUBVL or inner VL loop with SUBVL def index_dest(outer): if outer: @@ -290,6 +292,7 @@ For a separate source/dest SUBVL (again, no elwidth overrides): for i in range(VL): for j in range(SUBVL): .... +``` "yield" from python is used here for simplicity and clarity. The two Finite State Machines for the generation of the source -- 2.30.2