summaryrefslogtreecommitdiffstats
path: root/src/3rdparty/libjpeg/src/jcphuff.c
diff options
context:
space:
mode:
Diffstat (limited to 'src/3rdparty/libjpeg/src/jcphuff.c')
-rw-r--r--src/3rdparty/libjpeg/src/jcphuff.c70
1 files changed, 39 insertions, 31 deletions
diff --git a/src/3rdparty/libjpeg/src/jcphuff.c b/src/3rdparty/libjpeg/src/jcphuff.c
index 8c4efaf16c..5006b67075 100644
--- a/src/3rdparty/libjpeg/src/jcphuff.c
+++ b/src/3rdparty/libjpeg/src/jcphuff.c
@@ -4,8 +4,10 @@
* This file was part of the Independent JPEG Group's software:
* Copyright (C) 1995-1997, Thomas G. Lane.
* libjpeg-turbo Modifications:
- * Copyright (C) 2011, 2015, 2018, D. R. Commander.
- * Copyright (C) 2016, 2018, Matthieu Darbois.
+ * Copyright (C) 2011, 2015, 2018, 2021-2022, D. R. Commander.
+ * Copyright (C) 2016, 2018, 2022, Matthieu Darbois.
+ * Copyright (C) 2020, Arm Limited.
+ * Copyright (C) 2021, Alex Richardson.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*
@@ -20,7 +22,6 @@
#include "jinclude.h"
#include "jpeglib.h"
#include "jsimd.h"
-#include "jconfigint.h"
#include <limits.h>
#ifdef HAVE_INTRIN_H
@@ -43,23 +44,28 @@
* memory footprint by 64k, which is important for some mobile applications
* that create many isolated instances of libjpeg-turbo (web browsers, for
* instance.) This may improve performance on some mobile platforms as well.
- * This feature is enabled by default only on ARM processors, because some x86
+ * This feature is enabled by default only on Arm processors, because some x86
* chips have a slow implementation of bsr, and the use of clz/bsr cannot be
* shown to have a significant performance impact even on the x86 chips that
- * have a fast implementation of it. When building for ARMv6, you can
+ * have a fast implementation of it. When building for Armv6, you can
* explicitly disable the use of clz/bsr by adding -mthumb to the compiler
* flags (this defines __thumb__).
*/
/* NOTE: Both GCC and Clang define __GNUC__ */
-#if defined(__GNUC__) && (defined(__arm__) || defined(__aarch64__))
+#if (defined(__GNUC__) && (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"
@@ -76,11 +82,11 @@ typedef struct {
/* Pointer to routine to prepare data for encode_mcu_AC_first() */
void (*AC_first_prepare) (const JCOEF *block,
const int *jpeg_natural_order_start, int Sl,
- int Al, JCOEF *values, size_t *zerobits);
+ int Al, UJCOEF *values, size_t *zerobits);
/* Pointer to routine to prepare data for encode_mcu_AC_refine() */
int (*AC_refine_prepare) (const JCOEF *block,
const int *jpeg_natural_order_start, int Sl,
- int Al, JCOEF *absvalues, size_t *bits);
+ int Al, UJCOEF *absvalues, size_t *bits);
/* Mode flag: TRUE for optimization, FALSE for actual data output */
boolean gather_statistics;
@@ -150,14 +156,14 @@ METHODDEF(boolean) encode_mcu_DC_first(j_compress_ptr cinfo,
JBLOCKROW *MCU_data);
METHODDEF(void) encode_mcu_AC_first_prepare
(const JCOEF *block, const int *jpeg_natural_order_start, int Sl, int Al,
- JCOEF *values, size_t *zerobits);
+ UJCOEF *values, size_t *zerobits);
METHODDEF(boolean) encode_mcu_AC_first(j_compress_ptr cinfo,
JBLOCKROW *MCU_data);
METHODDEF(boolean) encode_mcu_DC_refine(j_compress_ptr cinfo,
JBLOCKROW *MCU_data);
METHODDEF(int) encode_mcu_AC_refine_prepare
(const JCOEF *block, const int *jpeg_natural_order_start, int Sl, int Al,
- JCOEF *absvalues, size_t *bits);
+ UJCOEF *absvalues, size_t *bits);
METHODDEF(boolean) encode_mcu_AC_refine(j_compress_ptr cinfo,
JBLOCKROW *MCU_data);
METHODDEF(void) finish_pass_phuff(j_compress_ptr cinfo);
@@ -169,24 +175,26 @@ INLINE
METHODDEF(int)
count_zeroes(size_t *x)
{
- int result;
#if defined(HAVE_BUILTIN_CTZL)
+ int result;
result = __builtin_ctzl(*x);
*x >>= result;
#elif defined(HAVE_BITSCANFORWARD64)
+ unsigned long result;
_BitScanForward64(&result, *x);
*x >>= result;
#elif defined(HAVE_BITSCANFORWARD)
+ unsigned long result;
_BitScanForward(&result, *x);
*x >>= result;
#else
- result = 0;
+ int result = 0;
while ((*x & 1) == 0) {
++result;
*x >>= 1;
}
#endif
- return result;
+ return (int)result;
}
@@ -266,7 +274,7 @@ start_pass_phuff(j_compress_ptr cinfo, boolean gather_statistics)
entropy->count_ptrs[tbl] = (long *)
(*cinfo->mem->alloc_small) ((j_common_ptr)cinfo, JPOOL_IMAGE,
257 * sizeof(long));
- MEMZERO(entropy->count_ptrs[tbl], 257 * sizeof(long));
+ memset(entropy->count_ptrs[tbl], 0, 257 * sizeof(long));
} else {
/* Compute derived values for Huffman table */
/* We may do this more than once for a table, but it's not expensive */
@@ -575,8 +583,8 @@ encode_mcu_DC_first(j_compress_ptr cinfo, JBLOCKROW *MCU_data)
continue; \
/* For a negative coef, want temp2 = bitwise complement of abs(coef) */ \
temp2 ^= temp; \
- values[k] = temp; \
- values[k + DCTSIZE2] = temp2; \
+ values[k] = (UJCOEF)temp; \
+ values[k + DCTSIZE2] = (UJCOEF)temp2; \
zerobits |= ((size_t)1U) << k; \
} \
}
@@ -584,7 +592,7 @@ encode_mcu_DC_first(j_compress_ptr cinfo, JBLOCKROW *MCU_data)
METHODDEF(void)
encode_mcu_AC_first_prepare(const JCOEF *block,
const int *jpeg_natural_order_start, int Sl,
- int Al, JCOEF *values, size_t *bits)
+ int Al, UJCOEF *values, size_t *bits)
{
register int k, temp, temp2;
size_t zerobits = 0U;
@@ -657,9 +665,9 @@ encode_mcu_AC_first(j_compress_ptr cinfo, JBLOCKROW *MCU_data)
register int nbits, r;
int Sl = cinfo->Se - cinfo->Ss + 1;
int Al = cinfo->Al;
- JCOEF values_unaligned[2 * DCTSIZE2 + 15];
- JCOEF *values;
- const JCOEF *cvalue;
+ UJCOEF values_unaligned[2 * DCTSIZE2 + 15];
+ UJCOEF *values;
+ const UJCOEF *cvalue;
size_t zerobits;
size_t bits[8 / SIZEOF_SIZE_T];
@@ -672,7 +680,7 @@ encode_mcu_AC_first(j_compress_ptr cinfo, JBLOCKROW *MCU_data)
emit_restart(entropy, entropy->next_restart_num);
#ifdef WITH_SIMD
- cvalue = values = (JCOEF *)PAD((size_t)values_unaligned, 16);
+ cvalue = values = (UJCOEF *)PAD((JUINTPTR)values_unaligned, 16);
#else
/* Not using SIMD, so alignment is not needed */
cvalue = values = values_unaligned;
@@ -806,7 +814,7 @@ encode_mcu_DC_refine(j_compress_ptr cinfo, JBLOCKROW *MCU_data)
zerobits |= ((size_t)1U) << k; \
signbits |= ((size_t)(temp2 + 1)) << k; \
} \
- absvalues[k] = (JCOEF)temp; /* save abs value for main pass */ \
+ absvalues[k] = (UJCOEF)temp; /* save abs value for main pass */ \
if (temp == 1) \
EOB = k + koffset; /* EOB = index of last newly-nonzero coef */ \
} \
@@ -815,7 +823,7 @@ encode_mcu_DC_refine(j_compress_ptr cinfo, JBLOCKROW *MCU_data)
METHODDEF(int)
encode_mcu_AC_refine_prepare(const JCOEF *block,
const int *jpeg_natural_order_start, int Sl,
- int Al, JCOEF *absvalues, size_t *bits)
+ int Al, UJCOEF *absvalues, size_t *bits)
{
register int k, temp, temp2;
int EOB = 0;
@@ -860,7 +868,7 @@ encode_mcu_AC_refine_prepare(const JCOEF *block,
#define ENCODE_COEFS_AC_REFINE(label) { \
while (zerobits) { \
- int idx = count_zeroes(&zerobits); \
+ idx = count_zeroes(&zerobits); \
r += idx; \
cabsvalue += idx; \
signbits >>= idx; \
@@ -917,14 +925,14 @@ METHODDEF(boolean)
encode_mcu_AC_refine(j_compress_ptr cinfo, JBLOCKROW *MCU_data)
{
phuff_entropy_ptr entropy = (phuff_entropy_ptr)cinfo->entropy;
- register int temp, r;
+ register int temp, r, idx;
char *BR_buffer;
unsigned int BR;
int Sl = cinfo->Se - cinfo->Ss + 1;
int Al = cinfo->Al;
- JCOEF absvalues_unaligned[DCTSIZE2 + 15];
- JCOEF *absvalues;
- const JCOEF *cabsvalue, *EOBPTR;
+ UJCOEF absvalues_unaligned[DCTSIZE2 + 15];
+ UJCOEF *absvalues;
+ const UJCOEF *cabsvalue, *EOBPTR;
size_t zerobits, signbits;
size_t bits[16 / SIZEOF_SIZE_T];
@@ -937,7 +945,7 @@ encode_mcu_AC_refine(j_compress_ptr cinfo, JBLOCKROW *MCU_data)
emit_restart(entropy, entropy->next_restart_num);
#ifdef WITH_SIMD
- cabsvalue = absvalues = (JCOEF *)PAD((size_t)absvalues_unaligned, 16);
+ cabsvalue = absvalues = (UJCOEF *)PAD((JUINTPTR)absvalues_unaligned, 16);
#else
/* Not using SIMD, so alignment is not needed */
cabsvalue = absvalues = absvalues_unaligned;
@@ -968,7 +976,7 @@ encode_mcu_AC_refine(j_compress_ptr cinfo, JBLOCKROW *MCU_data)
if (zerobits) {
int diff = ((absvalues + DCTSIZE2 / 2) - cabsvalue);
- int idx = count_zeroes(&zerobits);
+ idx = count_zeroes(&zerobits);
signbits >>= idx;
idx += diff;
r += idx;
@@ -1053,7 +1061,7 @@ finish_pass_gather_phuff(j_compress_ptr cinfo)
/* It's important not to apply jpeg_gen_optimal_table more than once
* per table, because it clobbers the input frequency counts!
*/
- MEMZERO(did, sizeof(did));
+ memset(did, 0, sizeof(did));
for (ci = 0; ci < cinfo->comps_in_scan; ci++) {
compptr = cinfo->cur_comp_info[ci];
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-03 18:19:00 +0000