update decoder hot loop alignment

This seems to bring an additional ~+1.2% decompression speed
on average across 10 compilers x 6 scenarios.

diff --git a/lib/decompress/zstd_decompress_block.c b/lib/decompress/zstd_decompress_block.c
index 90acc855ff051fd913bcba75655dfaf27901bed1..a8ba8d8bb121fe2180b8ec20a223ea608ed4b06f 100644 (file)
--- a/lib/decompress/zstd_decompress_block.c
+++ b/lib/decompress/zstd_decompress_block.c
@@ -1161,6 +1161,8 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
          *
          *   https://gist.github.com/terrelln/9889fc06a423fd5ca6e99351564473f4
          */
+        __asm__(".p2align 6");
+        __asm__("nop");
         __asm__(".p2align 5");
         __asm__("nop");
         __asm__(".p2align 4");