Use CLZ compiler intrinsic for Windows/Arm builds
The __builtin_clz() compiler intrinsic was already used in the C Huffman
encoders when building libjpeg-turbo for Arm CPUs using a GCC-compatible
compiler. This commit modifies the C Huffman encoders so that they also
use__builtin_clz() when building for Arm CPUs using Visual Studio +
Clang, as well as the equivalent _CountLeadingZeros() compiler intrinsic
when building for Arm CPUs using Visual C++.
In addition to making the C Huffman encoders faster on Windows/Arm, this
also prevents jpeg_nbits_table from being included in Windows/Arm builds,
thus saving 128 KB of memory.
diff --git a/jchuff.c b/jchuff.c
index 8ea48b8..e2d5772 100644
--- a/jchuff.c
+++ b/jchuff.c
@@ -44,15 +44,19 @@
* flags (this defines __thumb__).
*/
-/* NOTE: Both GCC and Clang define __GNUC__ */
-#if defined(__GNUC__) && (defined(__arm__) || defined(__aarch64__))
+#if defined(__arm__) || defined(__aarch64__) || defined(_M_ARM) || \
+ defined(_M_ARM64)
#if !defined(__thumb__) || defined(__thumb2__)
#define USE_CLZ_INTRINSIC
#endif
#endif
#ifdef USE_CLZ_INTRINSIC
+#if defined(_MSC_VER) && !defined(__clang__)
+#define JPEG_NBITS_NONZERO(x) (32 - _CountLeadingZeros(x))
+#else
#define JPEG_NBITS_NONZERO(x) (32 - __builtin_clz(x))
+#endif
#define JPEG_NBITS(x) (x ? JPEG_NBITS_NONZERO(x) : 0)
#else
#include "jpeg_nbits_table.h"
diff --git a/jcphuff.c b/jcphuff.c
index b6fd10d..3be92b2 100644
--- a/jcphuff.c
+++ b/jcphuff.c
@@ -6,6 +6,7 @@
* libjpeg-turbo Modifications:
* Copyright (C) 2011, 2015, 2018, 2021, D. R. Commander.
* Copyright (C) 2016, 2018, Matthieu Darbois.
+ * Copyright (C) 2020, Arm Limited.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*
@@ -51,15 +52,19 @@
* flags (this defines __thumb__).
*/
-/* NOTE: Both GCC and Clang define __GNUC__ */
-#if defined(__GNUC__) && (defined(__arm__) || defined(__aarch64__))
+#if defined(__arm__) || defined(__aarch64__) || defined(_M_ARM) || \
+ defined(_M_ARM64)
#if !defined(__thumb__) || defined(__thumb2__)
#define USE_CLZ_INTRINSIC
#endif
#endif
#ifdef USE_CLZ_INTRINSIC
+#if defined(_MSC_VER) && !defined(__clang__)
+#define JPEG_NBITS_NONZERO(x) (32 - _CountLeadingZeros(x))
+#else
#define JPEG_NBITS_NONZERO(x) (32 - __builtin_clz(x))
+#endif
#define JPEG_NBITS(x) (x ? JPEG_NBITS_NONZERO(x) : 0)
#else
#include "jpeg_nbits_table.h"
