From 3a72b38b23564e2036eb537c120e2fe0c41d49ba Mon Sep 17 00:00:00 2001 From: lkcl Date: Sun, 16 Apr 2023 10:41:13 +0100 Subject: [PATCH] --- openpower/sv/remap.mdwn | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/openpower/sv/remap.mdwn b/openpower/sv/remap.mdwn index df8837db5..7e66568a7 100644 --- a/openpower/sv/remap.mdwn +++ b/openpower/sv/remap.mdwn @@ -107,6 +107,8 @@ hold the partial results). ## Basic principle +The following illustrates why REMAP was added. + * normal vector element read/write of operands would be sequential (0 1 2 3 ....) * this is not appropriate for (e.g.) Matrix multiply which requires @@ -120,6 +122,9 @@ hold the partial results). * Matrix Schedules are not at all restricted to power-of-two boundaries making it unnecessary to have for example specialised 3x4 transpose instructions of other Vector ISAs. +* DCT and FFT REMAP are RADIX-2 limited but this is the case in existing Packed/Predicated + SIMD ISAs anyway (and Bluestein Convolution is typically deployed to + solve that). Only the most commonly-used algorithms in computer science have REMAP support, due to the high cost in both the ISA and in hardware. For -- 2.30.2