Force-Inline ZSTD_insertAndFindFirstIndex_internal()

Without this, gcc was declining to inline the function in `ZSTD_noDict` mode,
resulting in a ~10% slowdown.

diff --git a/lib/compress/zstd_lazy.c b/lib/compress/zstd_lazy.c
index 5d32c78b8516bbf743de30de1e43787ddad5c139..33acf687eccfcc35ba1113c6880ff9be1ea64ac1 100644 (file)
--- a/lib/compress/zstd_lazy.c
+++ b/lib/compress/zstd_lazy.c
@@ -447,7 +447,7 @@ static size_t ZSTD_BtFindBestMatch_extDict_selectMLS (
 
 /* Update chains up to ip (excluded)
    Assumption : always within prefix (i.e. not within extDict) */
-static U32 ZSTD_insertAndFindFirstIndex_internal(
+FORCE_INLINE_TEMPLATE U32 ZSTD_insertAndFindFirstIndex_internal(
                         ZSTD_matchState_t* ms,
                         const ZSTD_compressionParameters* const cParams,
                         const BYTE* ip, U32 const mls)