IDWT 5x3: generalize SSE2 version for AVX2

Thanks to our macros that abstract SSE use, the functions can use
AVX2 when available (at compile time)

This brings an extra 23% speed improvement on bench_dwt in 64bit builds
with AVX2 compared to SSE2.

1 files changed, 8 insertions, 0 deletions

diff --git a/src/lib/openjp2/opj_malloc.h b/src/lib/openjp2/opj_malloc.h
index c8c2fc2d..7503c28d 100644
--- a/src/lib/openjp2/opj_malloc.h
+++ b/src/lib/openjp2/opj_malloc.h
@@ -72,6 +72,14 @@ void * opj_aligned_realloc(void *ptr, size_t size);
 void opj_aligned_free(void* ptr);
 
 /**
+Allocate memory aligned to a 32 byte boundary
+@param size Bytes to allocate
+@return Returns a void pointer to the allocated space, or NULL if there is insufficient memory available
+*/
+void * opj_aligned_32_malloc(size_t size);
+void * opj_aligned_32_realloc(void *ptr, size_t size);
+
+/**
 Reallocate memory blocks.
 @param m Pointer to previously allocated memory block
 @param s New size in bytes