From 7ef6d7b36ca34eb4adef6f9780b0953d51643bb7 Mon Sep 17 00:00:00 2001
From: Yann Collet <yann.collet.73@gmail.com>
Date: Wed, 5 May 2021 10:04:03 -0700
Subject: [PATCH] deeper prefetching pipeline for decompressSequencesLong

pipeline increased from 4 to 8 slots.
This change substantially improves decompression speed when there are long distance offsets.
example with enwik9 compressed at level 22 :
gcc-9 : 947 -> 1039 MB/s
clang-10: 884 -> 946 MB/s

I also checked the "cold dictionary" scenario,
and found a smaller benefit, around ~2%
(measurements are more noisy for this scenario).
---
 lib/decompress/zstd_decompress_block.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/decompress/zstd_decompress_block.c b/lib/decompress/zstd_decompress_block.c
index b980339a..5419724d 100644
--- a/lib/decompress/zstd_decompress_block.c
+++ b/lib/decompress/zstd_decompress_block.c
@@ -1254,9 +1254,9 @@ ZSTD_decompressSequencesLong_body(
 
     /* Regen sequences */
     if (nbSeq) {
-#define STORED_SEQS 4
+#define STORED_SEQS 8
 #define STORED_SEQS_MASK (STORED_SEQS-1)
-#define ADVANCED_SEQS 4
+#define ADVANCED_SEQS STORED_SEQS
         seq_t sequences[STORED_SEQS];
         int const seqAdvance = MIN(nbSeq, ADVANCED_SEQS);
         seqState_t seqState;