From 913c9e5f17abb03a6da5c9fdcc3d9e136a0f91db Mon Sep 17 00:00:00 2001 From: lkcl Date: Tue, 5 Oct 2021 20:35:05 +0100 Subject: [PATCH] --- 3d_gpu/architecture/dynamic_simd/repl.mdwn | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/3d_gpu/architecture/dynamic_simd/repl.mdwn b/3d_gpu/architecture/dynamic_simd/repl.mdwn index a97460554..5e8e40e4a 100644 --- a/3d_gpu/architecture/dynamic_simd/repl.mdwn +++ b/3d_gpu/architecture/dynamic_simd/repl.mdwn @@ -8,22 +8,22 @@ on the partition mask. Take a PartitionedSignal and a repeat quantity of 2: - partition: p p p (3 bits) - a : AAA3 AAA2 AAA1 AAA0 (32 bits) + partition: p p p (3 bits) + a : A3 A2 A1 A0 (32 bits) When the partitions are 32-bit, the output is: - partition: p p p (3 bits) - out : AAA3 AAA2 AAA1 AAA0 AAA3 AAA2 AAA1 AAA0 (64 bits) + partition: p p p (3 bits) + out : A3 A2 A1 A0 A3 A2 A1 A0 (64 bits) When 2x16, the top half of A is replicated, and likewise the lower: - partition: p p p (3 bits) - out : AAA3 AAA2 AAA3 AAA2 AAA1 AAA0 AAA1 AAA0 (64 bits) + partition: p p p (3 bits) + out : A3 A2 A3 A2 A1 A0 A1 A0 (64 bits) Finally when 4x8, each byte is concatenated: - partition: p p p (3 bits) - out : AAA3 AAA3 AAA2 AAA2 AAA1 AAA1 AAA0 AAA0 (64 bits) + partition: p p p (3 bits) + out : A3 A3 A2 A2 A1 A1 A0 A0 (64 bits) -- 2.30.2