VOL-1921 - updated to use go mod
Change-Id: I8d5187fa91fa619494f972bc29d3bd61e5be3a82
diff --git a/vendor/github.com/DataDog/zstd/zstd_internal.h b/vendor/github.com/DataDog/zstd/zstd_internal.h
index 31f756a..81b16ea 100644
--- a/vendor/github.com/DataDog/zstd/zstd_internal.h
+++ b/vendor/github.com/DataDog/zstd/zstd_internal.h
@@ -34,7 +34,6 @@
#endif
#include "xxhash.h" /* XXH_reset, update, digest */
-
#if defined (__cplusplus)
extern "C" {
#endif
@@ -193,19 +192,72 @@
* Shared functions to include for inlining
*********************************************/
static void ZSTD_copy8(void* dst, const void* src) { memcpy(dst, src, 8); }
+
#define COPY8(d,s) { ZSTD_copy8(d,s); d+=8; s+=8; }
+static void ZSTD_copy16(void* dst, const void* src) { memcpy(dst, src, 16); }
+#define COPY16(d,s) { ZSTD_copy16(d,s); d+=16; s+=16; }
+
+#define WILDCOPY_OVERLENGTH 8
+#define VECLEN 16
+
+typedef enum {
+ ZSTD_no_overlap,
+ ZSTD_overlap_src_before_dst,
+ /* ZSTD_overlap_dst_before_src, */
+} ZSTD_overlap_e;
/*! ZSTD_wildcopy() :
* custom version of memcpy(), can overwrite up to WILDCOPY_OVERLENGTH bytes (if length==0) */
-#define WILDCOPY_OVERLENGTH 8
-MEM_STATIC void ZSTD_wildcopy(void* dst, const void* src, ptrdiff_t length)
+MEM_STATIC FORCE_INLINE_ATTR DONT_VECTORIZE
+void ZSTD_wildcopy(void* dst, const void* src, ptrdiff_t length, ZSTD_overlap_e ovtype)
{
+ ptrdiff_t diff = (BYTE*)dst - (const BYTE*)src;
const BYTE* ip = (const BYTE*)src;
BYTE* op = (BYTE*)dst;
BYTE* const oend = op + length;
- do
- COPY8(op, ip)
- while (op < oend);
+
+ assert(diff >= 8 || (ovtype == ZSTD_no_overlap && diff < -8));
+ if (length < VECLEN || (ovtype == ZSTD_overlap_src_before_dst && diff < VECLEN)) {
+ do
+ COPY8(op, ip)
+ while (op < oend);
+ }
+ else {
+ if ((length & 8) == 0)
+ COPY8(op, ip);
+ do {
+ COPY16(op, ip);
+ }
+ while (op < oend);
+ }
+}
+
+/*! ZSTD_wildcopy_16min() :
+ * same semantics as ZSTD_wilcopy() except guaranteed to be able to copy 16 bytes at the start */
+MEM_STATIC FORCE_INLINE_ATTR DONT_VECTORIZE
+void ZSTD_wildcopy_16min(void* dst, const void* src, ptrdiff_t length, ZSTD_overlap_e ovtype)
+{
+ ptrdiff_t diff = (BYTE*)dst - (const BYTE*)src;
+ const BYTE* ip = (const BYTE*)src;
+ BYTE* op = (BYTE*)dst;
+ BYTE* const oend = op + length;
+
+ assert(length >= 8);
+ assert(diff >= 8 || (ovtype == ZSTD_no_overlap && diff < -8));
+
+ if (ovtype == ZSTD_overlap_src_before_dst && diff < VECLEN) {
+ do
+ COPY8(op, ip)
+ while (op < oend);
+ }
+ else {
+ if ((length & 8) == 0)
+ COPY8(op, ip);
+ do {
+ COPY16(op, ip);
+ }
+ while (op < oend);
+ }
}
MEM_STATIC void ZSTD_wildcopy_e(void* dst, const void* src, void* dstEnd) /* should be faster for decoding, but strangely, not verified on all platform */