diff --git a/media/libjpeg/MOZCHANGES b/media/libjpeg/MOZCHANGES
index f9bc707d3e55be706aeac379b85b933c2a33bd9d..4077ae6ec5afdb5ff960460b5959fd141709ccba 100644
--- a/media/libjpeg/MOZCHANGES
+++ b/media/libjpeg/MOZCHANGES
@@ -48,6 +48,10 @@ To upgrade to a new revision of libjpeg-turbo, do the following:
$ hg addremove
+== January 6, 2020 (libjpeg-turbo v2.0.4 166e34213e4f4e2363ce058a7bcc69fd03e38b76 2019-12-31) ==
+
+* Updated to v2.0.4 release.
+
== September 5, 2019 (libjpeg-turbo v2.0.3 5db6a6819d0f904e0b58f34ae928fea234adb1a0 2019-09-04) ==
* Updated to v2.0.3 release.
diff --git a/media/libjpeg/README.md b/media/libjpeg/README.md
index c61b85564401bda6d7b817bd4d86f47cbab58a51..e7ff743a471727b5acda7f6db7f40b463e71de2a 100644
--- a/media/libjpeg/README.md
+++ b/media/libjpeg/README.md
@@ -1,14 +1,14 @@
Background
==========
-libjpeg-turbo is a JPEG image codec that uses SIMD instructions (MMX, SSE2,
-AVX2, NEON, AltiVec) to accelerate baseline JPEG compression and decompression
-on x86, x86-64, ARM, and PowerPC systems, as well as progressive JPEG
-compression on x86 and x86-64 systems. On such systems, libjpeg-turbo is
-generally 2-6x as fast as libjpeg, all else being equal. On other types of
-systems, libjpeg-turbo can still outperform libjpeg by a significant amount, by
-virtue of its highly-optimized Huffman coding routines. In many cases, the
-performance of libjpeg-turbo rivals that of proprietary high-speed JPEG codecs.
+libjpeg-turbo is a JPEG image codec that uses SIMD instructions to accelerate
+baseline JPEG compression and decompression on x86, x86-64, ARM, PowerPC, and
+MIPS systems, as well as progressive JPEG compression on x86 and x86-64
+systems. On such systems, libjpeg-turbo is generally 2-6x as fast as libjpeg,
+all else being equal. On other types of systems, libjpeg-turbo can still
+outperform libjpeg by a significant amount, by virtue of its highly-optimized
+Huffman coding routines. In many cases, the performance of libjpeg-turbo
+rivals that of proprietary high-speed JPEG codecs.
libjpeg-turbo implements both the traditional libjpeg API as well as the less
powerful but more straightforward TurboJPEG API. libjpeg-turbo also features
@@ -145,14 +145,14 @@ supported and which aren't.
#### Fully supported
-- **libjpeg: IDCT scaling extensions in decompressor**<br>
+- **libjpeg API: IDCT scaling extensions in decompressor**<br>
libjpeg-turbo supports IDCT scaling with scaling factors of 1/8, 1/4, 3/8,
1/2, 5/8, 3/4, 7/8, 9/8, 5/4, 11/8, 3/2, 13/8, 7/4, 15/8, and 2/1 (only 1/4
and 1/2 are SIMD-accelerated.)
-- **libjpeg: Arithmetic coding**
+- **libjpeg API: Arithmetic coding**
-- **libjpeg: In-memory source and destination managers**<br>
+- **libjpeg API: In-memory source and destination managers**<br>
See notes below.
- **cjpeg: Separate quality settings for luminance and chrominance**<br>
@@ -184,14 +184,14 @@ means of quality improvement. The reader is invited to peruse the research at
but it is the general belief of our project that these features have not
demonstrated sufficient usefulness to justify inclusion in libjpeg-turbo.
-- **libjpeg: DCT scaling in compressor**<br>
+- **libjpeg API: DCT scaling in compressor**<br>
`cinfo.scale_num` and `cinfo.scale_denom` are silently ignored.
There is no technical reason why DCT scaling could not be supported when
emulating the libjpeg v7+ API/ABI, but without the SmartScale extension (see
below), only scaling factors of 1/2, 8/15, 4/7, 8/13, 2/3, 8/11, 4/5, and
8/9 would be available, which is of limited usefulness.
-- **libjpeg: SmartScale**<br>
+- **libjpeg API: SmartScale**<br>
`cinfo.block_size` is silently ignored.
SmartScale is an extension to the JPEG format that allows for DCT block
sizes other than 8x8. Providing support for this new format would be
@@ -204,7 +204,7 @@ demonstrated sufficient usefulness to justify inclusion in libjpeg-turbo.
interest in providing this feature would be as a means of supporting
additional DCT scaling factors.
-- **libjpeg: Fancy downsampling in compressor**<br>
+- **libjpeg API: Fancy downsampling in compressor**<br>
`cinfo.do_fancy_downsampling` is silently ignored.
This requires the DCT scaling feature, which is not supported.
@@ -252,8 +252,8 @@ building libjpeg-turbo. This will restore the pre-1.3 behavior, in which
libjpeg v8 API/ABI.
On Un*x systems, including the in-memory source/destination managers changes
-the dynamic library version from 62.1.0 to 62.2.0 if using libjpeg v6b API/ABI
-emulation and from 7.1.0 to 7.2.0 if using libjpeg v7 API/ABI emulation.
+the dynamic library version from 62.2.0 to 62.3.0 if using libjpeg v6b API/ABI
+emulation and from 7.2.0 to 7.3.0 if using libjpeg v7 API/ABI emulation.
Note that, on most Un*x systems, the dynamic linker will not look for a
function in a library until that function is actually used. Thus, if a program
@@ -329,7 +329,7 @@ in a way that makes the rest of the libjpeg infrastructure happy, so it is
necessary to use the slow Huffman decoder when decompressing a JPEG image that
has restart markers. This can cause the decompression performance to drop by
as much as 20%, but the performance will still be much greater than that of
-libjpeg. Many consumer packages, such as PhotoShop, use restart markers when
+libjpeg. Many consumer packages, such as Photoshop, use restart markers when
generating JPEG images, so images generated by those programs will experience
this issue.
diff --git a/media/libjpeg/jchuff.c b/media/libjpeg/jchuff.c
index 526203e3db73b688ed67c900b0f80f59da953bcc..cb05055d99207bc3a610cc9db415a7b3ea6583bc 100644
--- a/media/libjpeg/jchuff.c
+++ b/media/libjpeg/jchuff.c
@@ -43,8 +43,8 @@
*/
/* NOTE: Both GCC and Clang define __GNUC__ */
-#if defined __GNUC__ && (defined __arm__ || defined __aarch64__)
-#if !defined __thumb__ || defined __thumb2__
+#if defined(__GNUC__) && (defined(__arm__) || defined(__aarch64__))
+#if !defined(__thumb__) || defined(__thumb2__)
#define USE_CLZ_INTRINSIC
#endif
#endif
@@ -432,7 +432,7 @@ dump_buffer(working_state *state)
* scanning order-- 1, 8, 16, etc.), then this will produce an encoded block
* larger than 200 bytes.
*/
-#define BUFSIZE (DCTSIZE2 * 4)
+#define BUFSIZE (DCTSIZE2 * 8)
#define LOAD_BUFFER() { \
if (state->free_in_buffer < BUFSIZE) { \
diff --git a/media/libjpeg/jconfig.h b/media/libjpeg/jconfig.h
index 4898e5edd987dcafbaa036751362529164869a6e..3ceec66bc8815a31ce361166ef4f0214f4ac46d7 100644
--- a/media/libjpeg/jconfig.h
+++ b/media/libjpeg/jconfig.h
@@ -5,10 +5,10 @@
#define JPEG_LIB_VERSION 62
/* libjpeg-turbo version */
-#define LIBJPEG_TURBO_VERSION 2.0.0
+#define LIBJPEG_TURBO_VERSION 2.0.4
/* libjpeg-turbo version in integer form */
-#define LIBJPEG_TURBO_VERSION_NUMBER 2000000
+#define LIBJPEG_TURBO_VERSION_NUMBER 2000004
/* Support arithmetic encoding */
/* #undef C_ARITH_CODING_SUPPORTED */
diff --git a/media/libjpeg/jconfigint.h b/media/libjpeg/jconfigint.h
index c07b93c4d31de6dcdbda79006435721680f4d2e0..6d50bede9037b30038f8d45e4afe6ec0feeca028 100644
--- a/media/libjpeg/jconfigint.h
+++ b/media/libjpeg/jconfigint.h
@@ -1,5 +1,5 @@
/* libjpeg-turbo build number */
-#define BUILD "20190905"
+#define BUILD "20191231"
/* Need to use Mozilla-specific function inlining. */
#include "mozilla/Attributes.h"
@@ -9,7 +9,7 @@
#define PACKAGE_NAME "libjpeg-turbo"
/* Version number of package */
-#define VERSION "2.0.3"
+#define VERSION "2.0.4"
/* The size of `size_t', as computed by sizeof. */
#ifdef HAVE_64BIT_BUILD
diff --git a/media/libjpeg/jcphuff.c b/media/libjpeg/jcphuff.c
index 024d3af0fb15a0b2bed2cb51ee12d669f625c870..8c4efaf16cb686d66c831db69d3ff72ec6d2d39f 100644
--- a/media/libjpeg/jcphuff.c
+++ b/media/libjpeg/jcphuff.c
@@ -52,8 +52,8 @@
*/
/* NOTE: Both GCC and Clang define __GNUC__ */
-#if defined __GNUC__ && (defined __arm__ || defined __aarch64__)
-#if !defined __thumb__ || defined __thumb2__
+#if defined(__GNUC__) && (defined(__arm__) || defined(__aarch64__))
+#if !defined(__thumb__) || defined(__thumb2__)
#define USE_CLZ_INTRINSIC
#endif
#endif
diff --git a/media/libjpeg/jfdctint.c b/media/libjpeg/jfdctint.c
index c0391a92beeef9784c91940203a3174f0754aa18..b47c3061ac5693bcbefb657a4b3690cc047bf58f 100644
--- a/media/libjpeg/jfdctint.c
+++ b/media/libjpeg/jfdctint.c
@@ -1,7 +1,7 @@
/*
* jfdctint.c
*
- * This file was part of the Independent JPEG Group's software.
+ * This file was part of the Independent JPEG Group's software:
* Copyright (C) 1991-1996, Thomas G. Lane.
* libjpeg-turbo Modifications:
* Copyright (C) 2015, D. R. Commander.
diff --git a/media/libjpeg/jidctint.c b/media/libjpeg/jidctint.c
index 55573429f1ae319b4f0b29921b2a65b076a6075b..98425d5fd083f22c09d84b213c623753826c5093 100644
--- a/media/libjpeg/jidctint.c
+++ b/media/libjpeg/jidctint.c
@@ -1,7 +1,7 @@
/*
* jidctint.c
*
- * This file was part of the Independent JPEG Group's software.
+ * This file was part of the Independent JPEG Group's software:
* Copyright (C) 1991-1998, Thomas G. Lane.
* Modification developed 2002-2009 by Guido Vollbeding.
* libjpeg-turbo Modifications:
diff --git a/media/libjpeg/jidctred.c b/media/libjpeg/jidctred.c
index 1ff352f875ffafdc8d38987e216d7830acb906b2..1dd65a94d975176c4ab6cda797a971f8eac9875f 100644
--- a/media/libjpeg/jidctred.c
+++ b/media/libjpeg/jidctred.c
@@ -1,7 +1,7 @@
/*
* jidctred.c
*
- * This file was part of the Independent JPEG Group's software.
+ * This file was part of the Independent JPEG Group's software:
* Copyright (C) 1994-1998, Thomas G. Lane.
* libjpeg-turbo Modifications:
* Copyright (C) 2015, D. R. Commander.
diff --git a/media/libjpeg/simd/arm64/jsimd_neon.S b/media/libjpeg/simd/arm64/jsimd_neon.S
index 93472efcf91d00b152a4de3e3fcb1ad4c5e8aaa5..a3aa4066c63a50d0bedc22ed853bf9b087e2ac2b 100644
--- a/media/libjpeg/simd/arm64/jsimd_neon.S
+++ b/media/libjpeg/simd/arm64/jsimd_neon.S
@@ -31,6 +31,251 @@
.section .note.GNU-stack, "", %progbits /* mark stack as non-executable */
#endif
+#if defined(__APPLE__)
+.section __DATA, __const
+#else
+.section .rodata, "a", %progbits
+#endif
+
+/* Constants for jsimd_idct_islow_neon() */
+
+#define F_0_298 2446 /* FIX(0.298631336) */
+#define F_0_390 3196 /* FIX(0.390180644) */
+#define F_0_541 4433 /* FIX(0.541196100) */
+#define F_0_765 6270 /* FIX(0.765366865) */
+#define F_0_899 7373 /* FIX(0.899976223) */
+#define F_1_175 9633 /* FIX(1.175875602) */
+#define F_1_501 12299 /* FIX(1.501321110) */
+#define F_1_847 15137 /* FIX(1.847759065) */
+#define F_1_961 16069 /* FIX(1.961570560) */
+#define F_2_053 16819 /* FIX(2.053119869) */
+#define F_2_562 20995 /* FIX(2.562915447) */
+#define F_3_072 25172 /* FIX(3.072711026) */
+
+.balign 16
+Ljsimd_idct_islow_neon_consts:
+ .short F_0_298
+ .short -F_0_390
+ .short F_0_541
+ .short F_0_765
+ .short - F_0_899
+ .short F_1_175
+ .short F_1_501
+ .short - F_1_847
+ .short - F_1_961
+ .short F_2_053
+ .short - F_2_562
+ .short F_3_072
+ .short 0 /* padding */
+ .short 0
+ .short 0
+ .short 0
+
+#undef F_0_298
+#undef F_0_390
+#undef F_0_541
+#undef F_0_765
+#undef F_0_899
+#undef F_1_175
+#undef F_1_501
+#undef F_1_847
+#undef F_1_961
+#undef F_2_053
+#undef F_2_562
+#undef F_3_072
+
+/* Constants for jsimd_idct_ifast_neon() */
+
+.balign 16
+Ljsimd_idct_ifast_neon_consts:
+ .short (277 * 128 - 256 * 128) /* XFIX_1_082392200 */
+ .short (362 * 128 - 256 * 128) /* XFIX_1_414213562 */
+ .short (473 * 128 - 256 * 128) /* XFIX_1_847759065 */
+ .short (669 * 128 - 512 * 128) /* XFIX_2_613125930 */
+
+/* Constants for jsimd_idct_4x4_neon() and jsimd_idct_2x2_neon() */
+
+#define CONST_BITS 13
+
+#define FIX_0_211164243 (1730) /* FIX(0.211164243) */
+#define FIX_0_509795579 (4176) /* FIX(0.509795579) */
+#define FIX_0_601344887 (4926) /* FIX(0.601344887) */
+#define FIX_0_720959822 (5906) /* FIX(0.720959822) */
+#define FIX_0_765366865 (6270) /* FIX(0.765366865) */
+#define FIX_0_850430095 (6967) /* FIX(0.850430095) */
+#define FIX_0_899976223 (7373) /* FIX(0.899976223) */
+#define FIX_1_061594337 (8697) /* FIX(1.061594337) */
+#define FIX_1_272758580 (10426) /* FIX(1.272758580) */
+#define FIX_1_451774981 (11893) /* FIX(1.451774981) */
+#define FIX_1_847759065 (15137) /* FIX(1.847759065) */
+#define FIX_2_172734803 (17799) /* FIX(2.172734803) */
+#define FIX_2_562915447 (20995) /* FIX(2.562915447) */
+#define FIX_3_624509785 (29692) /* FIX(3.624509785) */
+
+.balign 16
+Ljsimd_idct_4x4_neon_consts:
+ .short FIX_1_847759065 /* v0.h[0] */
+ .short -FIX_0_765366865 /* v0.h[1] */
+ .short -FIX_0_211164243 /* v0.h[2] */
+ .short FIX_1_451774981 /* v0.h[3] */
+ .short -FIX_2_172734803 /* d1[0] */
+ .short FIX_1_061594337 /* d1[1] */
+ .short -FIX_0_509795579 /* d1[2] */
+ .short -FIX_0_601344887 /* d1[3] */
+ .short FIX_0_899976223 /* v2.h[0] */
+ .short FIX_2_562915447 /* v2.h[1] */
+ .short 1 << (CONST_BITS + 1) /* v2.h[2] */
+ .short 0 /* v2.h[3] */
+
+.balign 8
+Ljsimd_idct_2x2_neon_consts:
+ .short -FIX_0_720959822 /* v14[0] */
+ .short FIX_0_850430095 /* v14[1] */
+ .short -FIX_1_272758580 /* v14[2] */
+ .short FIX_3_624509785 /* v14[3] */
+
+/* Constants for jsimd_ycc_*_neon() */
+
+.balign 16
+Ljsimd_ycc_rgb_neon_consts:
+ .short 0, 0, 0, 0
+ .short 22971, -11277, -23401, 29033
+ .short -128, -128, -128, -128
+ .short -128, -128, -128, -128
+
+/* Constants for jsimd_*_ycc_neon() */
+
+.balign 16
+Ljsimd_rgb_ycc_neon_consts:
+ .short 19595, 38470, 7471, 11059
+ .short 21709, 32768, 27439, 5329
+ .short 32767, 128, 32767, 128
+ .short 32767, 128, 32767, 128
+
+/* Constants for jsimd_fdct_islow_neon() */
+
+#define F_0_298 2446 /* FIX(0.298631336) */
+#define F_0_390 3196 /* FIX(0.390180644) */
+#define F_0_541 4433 /* FIX(0.541196100) */
+#define F_0_765 6270 /* FIX(0.765366865) */
+#define F_0_899 7373 /* FIX(0.899976223) */
+#define F_1_175 9633 /* FIX(1.175875602) */
+#define F_1_501 12299 /* FIX(1.501321110) */
+#define F_1_847 15137 /* FIX(1.847759065) */
+#define F_1_961 16069 /* FIX(1.961570560) */
+#define F_2_053 16819 /* FIX(2.053119869) */
+#define F_2_562 20995 /* FIX(2.562915447) */
+#define F_3_072 25172 /* FIX(3.072711026) */
+
+.balign 16
+Ljsimd_fdct_islow_neon_consts:
+ .short F_0_298
+ .short -F_0_390
+ .short F_0_541
+ .short F_0_765
+ .short - F_0_899
+ .short F_1_175
+ .short F_1_501
+ .short - F_1_847
+ .short - F_1_961
+ .short F_2_053
+ .short - F_2_562
+ .short F_3_072
+ .short 0 /* padding */
+ .short 0
+ .short 0
+ .short 0
+
+#undef F_0_298
+#undef F_0_390
+#undef F_0_541
+#undef F_0_765
+#undef F_0_899
+#undef F_1_175
+#undef F_1_501
+#undef F_1_847
+#undef F_1_961
+#undef F_2_053
+#undef F_2_562
+#undef F_3_072
+
+/* Constants for jsimd_fdct_ifast_neon() */
+
+.balign 16
+Ljsimd_fdct_ifast_neon_consts:
+ .short (98 * 128) /* XFIX_0_382683433 */
+ .short (139 * 128) /* XFIX_0_541196100 */
+ .short (181 * 128) /* XFIX_0_707106781 */
+ .short (334 * 128 - 256 * 128) /* XFIX_1_306562965 */
+
+/* Constants for jsimd_h2*_downsample_neon() */
+
+.balign 16
+Ljsimd_h2_downsample_neon_consts:
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F /* diff 0 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0E /* diff 1 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0D, 0x0D /* diff 2 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0C, 0x0C, 0x0C /* diff 3 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0B, 0x0B, 0x0B, 0x0B, 0x0B /* diff 4 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A /* diff 5 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09 /* diff 6 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08 /* diff 7 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07 /* diff 8 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x06, \
+ 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06 /* diff 9 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x05, 0x05, \
+ 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05 /* diff 10 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x04, 0x04, 0x04, \
+ 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04 /* diff 11 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x03, 0x03, 0x03, 0x03, \
+ 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03 /* diff 12 */
+ .byte 0x00, 0x01, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, \
+ 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02 /* diff 13 */
+ .byte 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, \
+ 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01 /* diff 14 */
+ .byte 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 /* diff 15 */
+
+/* Constants for jsimd_huff_encode_one_block_neon() */
+
+.balign 16
+Ljsimd_huff_encode_one_block_neon_consts:
+ .byte 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, \
+ 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80
+ .byte 0, 1, 2, 3, 16, 17, 32, 33, \
+ 18, 19, 4, 5, 6, 7, 20, 21 /* L0 => L3 : 4 lines OK */
+ .byte 34, 35, 48, 49, 255, 255, 50, 51, \
+ 36, 37, 22, 23, 8, 9, 10, 11 /* L0 => L3 : 4 lines OK */
+ .byte 8, 9, 22, 23, 36, 37, 50, 51, \
+ 255, 255, 255, 255, 255, 255, 52, 53 /* L1 => L4 : 4 lines OK */
+ .byte 54, 55, 40, 41, 26, 27, 12, 13, \
+ 14, 15, 28, 29, 42, 43, 56, 57 /* L0 => L3 : 4 lines OK */
+ .byte 6, 7, 20, 21, 34, 35, 48, 49, \
+ 50, 51, 36, 37, 22, 23, 8, 9 /* L4 => L7 : 4 lines OK */
+ .byte 42, 43, 28, 29, 14, 15, 30, 31, \
+ 44, 45, 58, 59, 255, 255, 255, 255 /* L1 => L4 : 4 lines OK */
+ .byte 255, 255, 255, 255, 56, 57, 42, 43, \
+ 28, 29, 14, 15, 30, 31, 44, 45 /* L3 => L6 : 4 lines OK */
+ .byte 26, 27, 40, 41, 42, 43, 28, 29, \
+ 14, 15, 30, 31, 44, 45, 46, 47 /* L5 => L7 : 3 lines OK */
+ .byte 255, 255, 255, 255, 0, 1, 255, 255, \
+ 255, 255, 255, 255, 255, 255, 255, 255 /* L4 : 1 lines OK */
+ .byte 255, 255, 255, 255, 255, 255, 255, 255, \
+ 0, 1, 16, 17, 2, 3, 255, 255 /* L5 => L6 : 2 lines OK */
+ .byte 255, 255, 255, 255, 255, 255, 255, 255, \
+ 255, 255, 255, 255, 8, 9, 22, 23 /* L5 => L6 : 2 lines OK */
+ .byte 4, 5, 6, 7, 255, 255, 255, 255, \
+ 255, 255, 255, 255, 255, 255, 255, 255 /* L7 : 1 line OK */
+
.text
@@ -55,6 +300,17 @@ _\fname:
#endif
.endm
+/* Get symbol location */
+.macro get_symbol_loc reg, symbol
+#ifdef __APPLE__
+ adrp \reg, \symbol@PAGE
+ add \reg, \reg, \symbol@PAGEOFF
+#else
+ adrp \reg, \symbol
+ add \reg, \reg, :lo12:\symbol
+#endif
+.endm
+
/* Transpose elements of single 128 bit registers */
.macro transpose_single x0, x1, xi, xilen, literal
ins \xi\xilen[0], \x0\xilen[0]
@@ -139,51 +395,6 @@ _\fname:
#define CONST_BITS 13
#define PASS1_BITS 2
-#define F_0_298 2446 /* FIX(0.298631336) */
-#define F_0_390 3196 /* FIX(0.390180644) */
-#define F_0_541 4433 /* FIX(0.541196100) */
-#define F_0_765 6270 /* FIX(0.765366865) */
-#define F_0_899 7373 /* FIX(0.899976223) */
-#define F_1_175 9633 /* FIX(1.175875602) */
-#define F_1_501 12299 /* FIX(1.501321110) */
-#define F_1_847 15137 /* FIX(1.847759065) */
-#define F_1_961 16069 /* FIX(1.961570560) */
-#define F_2_053 16819 /* FIX(2.053119869) */
-#define F_2_562 20995 /* FIX(2.562915447) */
-#define F_3_072 25172 /* FIX(3.072711026) */
-
-.balign 16
-Ljsimd_idct_islow_neon_consts:
- .short F_0_298
- .short -F_0_390
- .short F_0_541
- .short F_0_765
- .short - F_0_899
- .short F_1_175
- .short F_1_501
- .short - F_1_847
- .short - F_1_961
- .short F_2_053
- .short - F_2_562
- .short F_3_072
- .short 0 /* padding */
- .short 0
- .short 0
- .short 0
-
-#undef F_0_298
-#undef F_0_390
-#undef F_0_541
-#undef F_0_765
-#undef F_0_899
-#undef F_1_175
-#undef F_1_501
-#undef F_1_847
-#undef F_1_961
-#undef F_2_053
-#undef F_2_562
-#undef F_3_072
-
#define XFIX_P_0_298 v0.h[0]
#define XFIX_N_0_390 v0.h[1]
#define XFIX_P_0_541 v0.h[2]
@@ -217,7 +428,7 @@ asm_function jsimd_idct_islow_neon
uxtw x3, w3
sub sp, sp, #64
- adr x15, Ljsimd_idct_islow_neon_consts
+ get_symbol_loc x15, Ljsimd_idct_islow_neon_consts
mov x10, sp
st1 {v8.8b, v9.8b, v10.8b, v11.8b}, [x10], #32
st1 {v12.8b, v13.8b, v14.8b, v15.8b}, [x10], #32
@@ -791,13 +1002,6 @@ asm_function jsimd_idct_islow_neon
#define XFIX_1_847759065 v0.h[2]
#define XFIX_2_613125930 v0.h[3]
-.balign 16
-Ljsimd_idct_ifast_neon_consts:
- .short (277 * 128 - 256 * 128) /* XFIX_1_082392200 */
- .short (362 * 128 - 256 * 128) /* XFIX_1_414213562 */
- .short (473 * 128 - 256 * 128) /* XFIX_1_847759065 */
- .short (669 * 128 - 512 * 128) /* XFIX_2_613125930 */
-
asm_function jsimd_idct_ifast_neon
DCT_TABLE .req x0
@@ -832,7 +1036,7 @@ asm_function jsimd_idct_ifast_neon
* 7 | d30 | d31 ( v23.8h )
*/
/* Save NEON registers used in fast IDCT */
- adr TMP5, Ljsimd_idct_ifast_neon_consts
+ get_symbol_loc TMP5, Ljsimd_idct_ifast_neon_consts
ld1 {v16.8h, v17.8h}, [COEF_BLOCK], 32
ld1 {v0.8h, v1.8h}, [DCT_TABLE], 32
ld1 {v18.8h, v19.8h}, [COEF_BLOCK], 32
@@ -1023,38 +1227,6 @@ asm_function jsimd_idct_ifast_neon
* but readability will suffer somewhat.
*/
-#define CONST_BITS 13
-
-#define FIX_0_211164243 (1730) /* FIX(0.211164243) */
-#define FIX_0_509795579 (4176) /* FIX(0.509795579) */
-#define FIX_0_601344887 (4926) /* FIX(0.601344887) */
-#define FIX_0_720959822 (5906) /* FIX(0.720959822) */
-#define FIX_0_765366865 (6270) /* FIX(0.765366865) */
-#define FIX_0_850430095 (6967) /* FIX(0.850430095) */
-#define FIX_0_899976223 (7373) /* FIX(0.899976223) */
-#define FIX_1_061594337 (8697) /* FIX(1.061594337) */
-#define FIX_1_272758580 (10426) /* FIX(1.272758580) */
-#define FIX_1_451774981 (11893) /* FIX(1.451774981) */
-#define FIX_1_847759065 (15137) /* FIX(1.847759065) */
-#define FIX_2_172734803 (17799) /* FIX(2.172734803) */
-#define FIX_2_562915447 (20995) /* FIX(2.562915447) */
-#define FIX_3_624509785 (29692) /* FIX(3.624509785) */
-
-.balign 16
-Ljsimd_idct_4x4_neon_consts:
- .short FIX_1_847759065 /* v0.h[0] */
- .short -FIX_0_765366865 /* v0.h[1] */
- .short -FIX_0_211164243 /* v0.h[2] */
- .short FIX_1_451774981 /* v0.h[3] */
- .short -FIX_2_172734803 /* d1[0] */
- .short FIX_1_061594337 /* d1[1] */
- .short -FIX_0_509795579 /* d1[2] */
- .short -FIX_0_601344887 /* d1[3] */
- .short FIX_0_899976223 /* v2.h[0] */
- .short FIX_2_562915447 /* v2.h[1] */
- .short 1 << (CONST_BITS + 1) /* v2.h[2] */
- .short 0 /* v2.h[3] */
-
.macro idct_helper x4, x6, x8, x10, x12, x14, x16, shift, y26, y27, y28, y29
smull v28.4s, \x4, v2.h[2]
smlal v28.4s, \x8, v0.h[0]
@@ -1121,7 +1293,7 @@ asm_function jsimd_idct_4x4_neon
sub sp, sp, 64
mov x9, sp
/* Load constants (v3.4h is just used for padding) */
- adr TMP4, Ljsimd_idct_4x4_neon_consts
+ get_symbol_loc TMP4, Ljsimd_idct_4x4_neon_consts
st1 {v8.8b, v9.8b, v10.8b, v11.8b}, [x9], 32
st1 {v12.8b, v13.8b, v14.8b, v15.8b}, [x9], 32
ld1 {v0.4h, v1.4h, v2.4h, v3.4h}, [TMP4]
@@ -1264,13 +1436,6 @@ asm_function jsimd_idct_4x4_neon
* bit exact compatibility with jpeg-6b.
*/
-.balign 8
-Ljsimd_idct_2x2_neon_consts:
- .short -FIX_0_720959822 /* v14[0] */
- .short FIX_0_850430095 /* v14[1] */
- .short -FIX_1_272758580 /* v14[2] */
- .short FIX_3_624509785 /* v14[3] */
-
.macro idct_helper x4, x6, x10, x12, x16, shift, y26, y27
sshll v15.4s, \x4, #15
smull v26.4s, \x6, v14.h[3]
@@ -1311,7 +1476,7 @@ asm_function jsimd_idct_2x2_neon
mov x9, sp
/* Load constants */
- adr TMP2, Ljsimd_idct_2x2_neon_consts
+ get_symbol_loc TMP2, Ljsimd_idct_2x2_neon_consts
st1 {v8.8b, v9.8b, v10.8b, v11.8b}, [x9], 32
st1 {v12.8b, v13.8b, v14.8b, v15.8b}, [x9], 32
ld1 {v14.4h}, [TMP2]
@@ -1663,21 +1828,6 @@ asm_function jsimd_idct_2x2_neon
do_yuv_to_rgb_stage2
.endm
-/* Apple gas crashes on adrl, work around that by using adr.
- * But this requires a copy of these constants for each function.
- */
-
-.balign 16
-.if \fast_st3 == 1
-Ljsimd_ycc_\colorid\()_neon_consts:
-.else
-Ljsimd_ycc_\colorid\()_neon_slowst3_consts:
-.endif
- .short 0, 0, 0, 0
- .short 22971, -11277, -23401, 29033
- .short -128, -128, -128, -128
- .short -128, -128, -128, -128
-
.if \fast_st3 == 1
asm_function jsimd_ycc_\colorid\()_convert_neon
.else
@@ -1703,11 +1853,7 @@ asm_function jsimd_ycc_\colorid\()_convert_neon_slowst3
mov x9, sp
/* Load constants to d1, d2, d3 (v0.4h is just used for padding) */
- .if \fast_st3 == 1
- adr x15, Ljsimd_ycc_\colorid\()_neon_consts
- .else
- adr x15, Ljsimd_ycc_\colorid\()_neon_slowst3_consts
- .endif
+ get_symbol_loc x15, Ljsimd_ycc_rgb_neon_consts
/* Save NEON registers */
st1 {v8.8b, v9.8b, v10.8b, v11.8b}, [x9], 32
@@ -2004,17 +2150,6 @@ generate_jsimd_ycc_rgb_convert_neon extbgr, 24, 2, .4h, 1, .4h, 0, .4h, .8b,
do_rgb_to_yuv_stage1
.endm
-.balign 16
-.if \fast_ld3 == 1
-Ljsimd_\colorid\()_ycc_neon_consts:
-.else
-Ljsimd_\colorid\()_ycc_neon_slowld3_consts:
-.endif
- .short 19595, 38470, 7471, 11059
- .short 21709, 32768, 27439, 5329
- .short 32767, 128, 32767, 128
- .short 32767, 128, 32767, 128
-
.if \fast_ld3 == 1
asm_function jsimd_\colorid\()_ycc_convert_neon
.else
@@ -2037,11 +2172,7 @@ asm_function jsimd_\colorid\()_ycc_convert_neon_slowld3
N .req w12
/* Load constants to d0, d1, d2, d3 */
- .if \fast_ld3 == 1
- adr x13, Ljsimd_\colorid\()_ycc_neon_consts
- .else
- adr x13, Ljsimd_\colorid\()_ycc_neon_slowld3_consts
- .endif
+ get_symbol_loc x13, Ljsimd_rgb_ycc_neon_consts
ld1 {v0.8h, v1.8h}, [x13]
ldr OUTPUT_BUF0, [OUTPUT_BUF]
@@ -2241,50 +2372,6 @@ asm_function jsimd_convsamp_neon
#define DESCALE_P1 (CONST_BITS - PASS1_BITS)
#define DESCALE_P2 (CONST_BITS + PASS1_BITS)
-#define F_0_298 2446 /* FIX(0.298631336) */
-#define F_0_390 3196 /* FIX(0.390180644) */
-#define F_0_541 4433 /* FIX(0.541196100) */
-#define F_0_765 6270 /* FIX(0.765366865) */
-#define F_0_899 7373 /* FIX(0.899976223) */
-#define F_1_175 9633 /* FIX(1.175875602) */
-#define F_1_501 12299 /* FIX(1.501321110) */
-#define F_1_847 15137 /* FIX(1.847759065) */
-#define F_1_961 16069 /* FIX(1.961570560) */
-#define F_2_053 16819 /* FIX(2.053119869) */
-#define F_2_562 20995 /* FIX(2.562915447) */
-#define F_3_072 25172 /* FIX(3.072711026) */
-
-.balign 16
-Ljsimd_fdct_islow_neon_consts:
- .short F_0_298
- .short -F_0_390
- .short F_0_541
- .short F_0_765
- .short - F_0_899
- .short F_1_175
- .short F_1_501
- .short - F_1_847
- .short - F_1_961
- .short F_2_053
- .short - F_2_562
- .short F_3_072
- .short 0 /* padding */
- .short 0
- .short 0
- .short 0
-
-#undef F_0_298
-#undef F_0_390
-#undef F_0_541
-#undef F_0_765
-#undef F_0_899
-#undef F_1_175
-#undef F_1_501
-#undef F_1_847
-#undef F_1_961
-#undef F_2_053
-#undef F_2_562
-#undef F_3_072
#define XFIX_P_0_298 v0.h[0]
#define XFIX_N_0_390 v0.h[1]
#define XFIX_P_0_541 v0.h[2]
@@ -2304,7 +2391,7 @@ asm_function jsimd_fdct_islow_neon
TMP .req x9
/* Load constants */
- adr TMP, Ljsimd_fdct_islow_neon_consts
+ get_symbol_loc TMP, Ljsimd_fdct_islow_neon_consts
ld1 {v0.8h, v1.8h}, [TMP]
/* Save NEON registers */
@@ -2583,20 +2670,13 @@ asm_function jsimd_fdct_islow_neon
#define XFIX_0_707106781 v0.h[2]
#define XFIX_1_306562965 v0.h[3]
-.balign 16
-Ljsimd_fdct_ifast_neon_consts:
- .short (98 * 128) /* XFIX_0_382683433 */
- .short (139 * 128) /* XFIX_0_541196100 */
- .short (181 * 128) /* XFIX_0_707106781 */
- .short (334 * 128 - 256 * 128) /* XFIX_1_306562965 */
-
asm_function jsimd_fdct_ifast_neon
DATA .req x0
TMP .req x9
/* Load constants */
- adr TMP, Ljsimd_fdct_ifast_neon_consts
+ get_symbol_loc TMP, Ljsimd_fdct_ifast_neon_consts
ld1 {v0.4h}, [TMP]
/* Load all DATA into NEON registers with the following allocation:
@@ -2775,41 +2855,6 @@ asm_function jsimd_quantize_neon
* JSAMPARRAY input_data, JSAMPARRAY output_data);
*/
-.balign 16
-Ljsimd_h2_downsample_neon_consts:
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F /* diff 0 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0E /* diff 1 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0D, 0x0D /* diff 2 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0C, 0x0C, 0x0C /* diff 3 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0B, 0x0B, 0x0B, 0x0B, 0x0B /* diff 4 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A /* diff 5 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09 /* diff 6 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08 /* diff 7 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07 /* diff 8 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x06, \
- 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06 /* diff 9 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x05, 0x05, \
- 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05 /* diff 10 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x04, 0x04, 0x04, \
- 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04 /* diff 11 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x03, 0x03, 0x03, 0x03, \
- 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03 /* diff 12 */
- .byte 0x00, 0x01, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, \
- 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02 /* diff 13 */
- .byte 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, \
- 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01 /* diff 14 */
- .byte 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \
- 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 /* diff 15 */
-
asm_function jsimd_h2v1_downsample_neon
IMAGE_WIDTH .req x0
MAX_V_SAMP .req x1
@@ -2827,7 +2872,7 @@ asm_function jsimd_h2v1_downsample_neon
mov TMPDUP, #0x10000
lsl TMP2, BLOCK_WIDTH, #4
sub TMP2, TMP2, IMAGE_WIDTH
- adr TMP3, Ljsimd_h2_downsample_neon_consts
+ get_symbol_loc TMP3, Ljsimd_h2_downsample_neon_consts
add TMP3, TMP3, TMP2, lsl #4
dup v16.4s, TMPDUP
ld1 {v18.16b}, [TMP3]
@@ -2906,7 +2951,7 @@ asm_function jsimd_h2v2_downsample_neon
lsl TMP2, BLOCK_WIDTH, #4
lsl TMPDUP, TMPDUP, #17
sub TMP2, TMP2, IMAGE_WIDTH
- adr TMP3, Ljsimd_h2_downsample_neon_consts
+ get_symbol_loc TMP3, Ljsimd_h2_downsample_neon_consts
orr TMPDUP, TMPDUP, #1
add TMP3, TMP3, TMP2, lsl #4
dup v16.4s, TMPDUP
@@ -3012,41 +3057,6 @@ asm_function jsimd_h2v2_downsample_neon
.macro generate_jsimd_huff_encode_one_block fast_tbl
-.balign 16
-.if \fast_tbl == 1
-Ljsimd_huff_encode_one_block_neon_consts:
-.else
-Ljsimd_huff_encode_one_block_neon_slowtbl_consts:
-.endif
- .byte 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, \
- 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80
-.if \fast_tbl == 1
- .byte 0, 1, 2, 3, 16, 17, 32, 33, \
- 18, 19, 4, 5, 6, 7, 20, 21 /* L0 => L3 : 4 lines OK */
- .byte 34, 35, 48, 49, 255, 255, 50, 51, \
- 36, 37, 22, 23, 8, 9, 10, 11 /* L0 => L3 : 4 lines OK */
- .byte 8, 9, 22, 23, 36, 37, 50, 51, \
- 255, 255, 255, 255, 255, 255, 52, 53 /* L1 => L4 : 4 lines OK */
- .byte 54, 55, 40, 41, 26, 27, 12, 13, \
- 14, 15, 28, 29, 42, 43, 56, 57 /* L0 => L3 : 4 lines OK */
- .byte 6, 7, 20, 21, 34, 35, 48, 49, \
- 50, 51, 36, 37, 22, 23, 8, 9 /* L4 => L7 : 4 lines OK */
- .byte 42, 43, 28, 29, 14, 15, 30, 31, \
- 44, 45, 58, 59, 255, 255, 255, 255 /* L1 => L4 : 4 lines OK */
- .byte 255, 255, 255, 255, 56, 57, 42, 43, \
- 28, 29, 14, 15, 30, 31, 44, 45 /* L3 => L6 : 4 lines OK */
- .byte 26, 27, 40, 41, 42, 43, 28, 29, \
- 14, 15, 30, 31, 44, 45, 46, 47 /* L5 => L7 : 3 lines OK */
- .byte 255, 255, 255, 255, 0, 1, 255, 255, \
- 255, 255, 255, 255, 255, 255, 255, 255 /* L4 : 1 lines OK */
- .byte 255, 255, 255, 255, 255, 255, 255, 255, \
- 0, 1, 16, 17, 2, 3, 255, 255 /* L5 => L6 : 2 lines OK */
- .byte 255, 255, 255, 255, 255, 255, 255, 255, \
- 255, 255, 255, 255, 8, 9, 22, 23 /* L5 => L6 : 2 lines OK */
- .byte 4, 5, 6, 7, 255, 255, 255, 255, \
- 255, 255, 255, 255, 255, 255, 255, 255 /* L7 : 1 line OK */
-.endif
-
.if \fast_tbl == 1
asm_function jsimd_huff_encode_one_block_neon
.else
@@ -3056,11 +3066,7 @@ asm_function jsimd_huff_encode_one_block_neon_slowtbl
sub BUFFER, BUFFER, #0x1 /* BUFFER=buffer-- */
/* Save ARM registers */
stp x19, x20, [sp]
-.if \fast_tbl == 1
- adr x15, Ljsimd_huff_encode_one_block_neon_consts
-.else
- adr x15, Ljsimd_huff_encode_one_block_neon_slowtbl_consts
-.endif
+ get_symbol_loc x15, Ljsimd_huff_encode_one_block_neon_consts
ldr PUT_BUFFER, [x0, #0x10]
ldr PUT_BITSw, [x0, #0x18]
ldrsh w12, [x2] /* load DC coeff in w12 */
diff --git a/media/libjpeg/simd/i386/jccolext-avx2.asm b/media/libjpeg/simd/i386/jccolext-avx2.asm
index 7a8d784a5e505c3fa5ffa8471ed9f36f21463dbe..c46d684436dd774d3a03d771b679ed1deab912c1 100644
--- a/media/libjpeg/simd/i386/jccolext-avx2.asm
+++ b/media/libjpeg/simd/i386/jccolext-avx2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -110,12 +108,12 @@ EXTN(jsimd_rgb_ycc_convert_avx2):
test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
diff --git a/media/libjpeg/simd/i386/jccolext-mmx.asm b/media/libjpeg/simd/i386/jccolext-mmx.asm
index 9a2c30e236f397045e98e85cce97c3abfb8a18cf..6357a42b2cf4887503da4067b35f09efcdb2e492 100644
--- a/media/libjpeg/simd/i386/jccolext-mmx.asm
+++ b/media/libjpeg/simd/i386/jccolext-mmx.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -111,13 +109,13 @@ EXTN(jsimd_rgb_ycc_convert_mmx):
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
xor eax, eax
- mov al, BYTE [esi+ecx]
+ mov al, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
xor edx, edx
- mov dx, WORD [esi+ecx]
+ mov dx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
@@ -127,7 +125,7 @@ EXTN(jsimd_rgb_ycc_convert_mmx):
test cl, SIZEOF_DWORD
jz short .column_ld8
sub ecx, byte SIZEOF_DWORD
- movd mmG, DWORD [esi+ecx]
+ movd mmG, dword [esi+ecx]
psllq mmA, DWORD_BIT
por mmA, mmG
.column_ld8:
@@ -197,7 +195,7 @@ EXTN(jsimd_rgb_ycc_convert_mmx):
test cl, SIZEOF_MMWORD/8
jz short .column_ld2
sub ecx, byte SIZEOF_MMWORD/8
- movd mmA, DWORD [esi+ecx*RGB_PIXELSIZE]
+ movd mmA, dword [esi+ecx*RGB_PIXELSIZE]
.column_ld2:
test cl, SIZEOF_MMWORD/4
jz short .column_ld4
diff --git a/media/libjpeg/simd/i386/jccolext-sse2.asm b/media/libjpeg/simd/i386/jccolext-sse2.asm
index e830562cee89f73eb32927ea9cc236f1b9742177..c6c80852ac5b0356afb912414b065d61e97027b4 100644
--- a/media/libjpeg/simd/i386/jccolext-sse2.asm
+++ b/media/libjpeg/simd/i386/jccolext-sse2.asm
@@ -12,8 +12,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -109,12 +107,12 @@ EXTN(jsimd_rgb_ycc_convert_sse2):
test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
diff --git a/media/libjpeg/simd/i386/jccolor-avx2.asm b/media/libjpeg/simd/i386/jccolor-avx2.asm
index 958517f38031b24c1dd7b99f49923e662874ecc2..14944e952f19903862fc64af5acb2d0185e2407a 100644
--- a/media/libjpeg/simd/i386/jccolor-avx2.asm
+++ b/media/libjpeg/simd/i386/jccolor-avx2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jccolor-mmx.asm b/media/libjpeg/simd/i386/jccolor-mmx.asm
index 47be9e1e23709bafd4dbaab0fd032028c42d4bd8..8cb399bdc43f9e97e84fd9a15df6d611383dc9d1 100644
--- a/media/libjpeg/simd/i386/jccolor-mmx.asm
+++ b/media/libjpeg/simd/i386/jccolor-mmx.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jccolor-sse2.asm b/media/libjpeg/simd/i386/jccolor-sse2.asm
index c0d5d45e85370cb85cbba942af37beb0c81054ab..686d222ff700037f7deb3c3ac1e1185111c16039 100644
--- a/media/libjpeg/simd/i386/jccolor-sse2.asm
+++ b/media/libjpeg/simd/i386/jccolor-sse2.asm
@@ -12,8 +12,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jcgray-avx2.asm b/media/libjpeg/simd/i386/jcgray-avx2.asm
index 4d66242cf33f8ce0dd7a73fee07b52be1e7fe3c5..560ee0c71e2b1a4fedf27c3b70764ff475324ec2 100644
--- a/media/libjpeg/simd/i386/jcgray-avx2.asm
+++ b/media/libjpeg/simd/i386/jcgray-avx2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jcgray-mmx.asm b/media/libjpeg/simd/i386/jcgray-mmx.asm
index 07c7ea6c789652da5bd551ad4dfe1c24f025fde1..79fdf082a84846873ee50ca9ad0e4eb69c7e5fee 100644
--- a/media/libjpeg/simd/i386/jcgray-mmx.asm
+++ b/media/libjpeg/simd/i386/jcgray-mmx.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jcgray-sse2.asm b/media/libjpeg/simd/i386/jcgray-sse2.asm
index 4b8c79716ce139d86ac607c3d7db9864ab6c6028..cb4b28e8f495b9a3b30fd2a18f4ab8e58eaabbfd 100644
--- a/media/libjpeg/simd/i386/jcgray-sse2.asm
+++ b/media/libjpeg/simd/i386/jcgray-sse2.asm
@@ -12,8 +12,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jcgryext-avx2.asm b/media/libjpeg/simd/i386/jcgryext-avx2.asm
index 52e99a84cf65572c6f86e067ff4e7c1b0892e2e3..3fa7973d72b4445e8997d035cbbce1d67f419c01 100644
--- a/media/libjpeg/simd/i386/jcgryext-avx2.asm
+++ b/media/libjpeg/simd/i386/jcgryext-avx2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -102,12 +100,12 @@ EXTN(jsimd_rgb_gray_convert_avx2):
test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
diff --git a/media/libjpeg/simd/i386/jcgryext-mmx.asm b/media/libjpeg/simd/i386/jcgryext-mmx.asm
index 4a9ab0da2eb86af08857763d5c5f34d834ab7684..8af42e5a33225cb45287d00321bab467d3c57ce4 100644
--- a/media/libjpeg/simd/i386/jcgryext-mmx.asm
+++ b/media/libjpeg/simd/i386/jcgryext-mmx.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -103,13 +101,13 @@ EXTN(jsimd_rgb_gray_convert_mmx):
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
xor eax, eax
- mov al, BYTE [esi+ecx]
+ mov al, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
xor edx, edx
- mov dx, WORD [esi+ecx]
+ mov dx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
@@ -119,7 +117,7 @@ EXTN(jsimd_rgb_gray_convert_mmx):
test cl, SIZEOF_DWORD
jz short .column_ld8
sub ecx, byte SIZEOF_DWORD
- movd mmG, DWORD [esi+ecx]
+ movd mmG, dword [esi+ecx]
psllq mmA, DWORD_BIT
por mmA, mmG
.column_ld8:
@@ -189,7 +187,7 @@ EXTN(jsimd_rgb_gray_convert_mmx):
test cl, SIZEOF_MMWORD/8
jz short .column_ld2
sub ecx, byte SIZEOF_MMWORD/8
- movd mmA, DWORD [esi+ecx*RGB_PIXELSIZE]
+ movd mmA, dword [esi+ecx*RGB_PIXELSIZE]
.column_ld2:
test cl, SIZEOF_MMWORD/4
jz short .column_ld4
diff --git a/media/libjpeg/simd/i386/jcgryext-sse2.asm b/media/libjpeg/simd/i386/jcgryext-sse2.asm
index 04d891cdc59276f3543ddfebb6b4c5bbef434173..c9d6ff1e351c394628e164cdb3691c4f1d9ef7b4 100644
--- a/media/libjpeg/simd/i386/jcgryext-sse2.asm
+++ b/media/libjpeg/simd/i386/jcgryext-sse2.asm
@@ -12,8 +12,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -101,12 +99,12 @@ EXTN(jsimd_rgb_gray_convert_sse2):
test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
diff --git a/media/libjpeg/simd/i386/jchuff-sse2.asm b/media/libjpeg/simd/i386/jchuff-sse2.asm
index fea4de3506e50eb09be73745c498fa9f70397b0a..d0112e61070a60f9373390ed729942bef2399745 100644
--- a/media/libjpeg/simd/i386/jchuff-sse2.asm
+++ b/media/libjpeg/simd/i386/jchuff-sse2.asm
@@ -17,8 +17,6 @@
; This file contains an SSE2 implementation for Huffman coding of one block.
; The following code is based directly on jchuff.c; see jchuff.c for more
; details.
-;
-; [TAB8]
%include "jsimdext.inc"
@@ -196,8 +194,8 @@ EXTN(jsimd_huff_encode_one_block_sse2):
push ebp
mov esi, POINTER [eax+8] ; (working_state *state)
- mov put_buffer, DWORD [esi+8] ; put_buffer = state->cur.put_buffer;
- mov put_bits, DWORD [esi+12] ; put_bits = state->cur.put_bits;
+ mov put_buffer, dword [esi+8] ; put_buffer = state->cur.put_buffer;
+ mov put_bits, dword [esi+12] ; put_bits = state->cur.put_bits;
push esi ; esi is now scratch
get_GOT edx ; get GOT address
@@ -213,7 +211,7 @@ EXTN(jsimd_huff_encode_one_block_sse2):
; Encode the DC coefficient difference per section F.1.2.1
mov esi, POINTER [esp+block] ; block
movsx ecx, word [esi] ; temp = temp2 = block[0] - last_dc_val;
- sub ecx, DWORD [eax+20]
+ sub ecx, dword [eax+20]
mov esi, ecx
; This is a well-known technique for obtaining the absolute value
@@ -228,12 +226,12 @@ EXTN(jsimd_huff_encode_one_block_sse2):
; For a negative input, want temp2 = bitwise complement of abs(input)
; This code assumes we are on a two's complement machine
add esi, edx ; temp2 += temp3;
- mov DWORD [esp+temp], esi ; backup temp2 in temp
+ mov dword [esp+temp], esi ; backup temp2 in temp
; Find the number of bits needed for the magnitude of the coefficient
movpic ebp, POINTER [esp+gotptr] ; load GOT address (ebp)
movzx edx, byte [GOTOFF(ebp, EXTN(jpeg_nbits_table) + ecx)] ; nbits = JPEG_NBITS(temp);
- mov DWORD [esp+temp2], edx ; backup nbits in temp2
+ mov dword [esp+temp2], edx ; backup nbits in temp2
; Emit the Huffman-coded symbol for the number of bits
mov ebp, POINTER [eax+24] ; After this point, arguments are not accessible anymore
@@ -241,13 +239,13 @@ EXTN(jsimd_huff_encode_one_block_sse2):
movzx ecx, byte [ebp + edx + 1024] ; size = dctbl->ehufsi[nbits];
EMIT_BITS eax ; EMIT_BITS(code, size)
- mov ecx, DWORD [esp+temp2] ; restore nbits
+ mov ecx, dword [esp+temp2] ; restore nbits
; Mask off any extra bits in code
mov eax, 1
shl eax, cl
dec eax
- and eax, DWORD [esp+temp] ; temp2 &= (((JLONG)1)<<nbits) - 1;
+ and eax, dword [esp+temp] ; temp2 &= (((JLONG)1)<<nbits) - 1;
; Emit that number of bits of the value, if positive,
; or the complement of its magnitude, if negative.
@@ -290,22 +288,22 @@ EXTN(jsimd_huff_encode_one_block_sse2):
jz near .ELOOP
lea esi, [esi+ecx*2] ; k += r;
shr edx, cl ; index >>= r;
- mov DWORD [esp+temp3], edx
+ mov dword [esp+temp3], edx
.BRLOOP:
cmp ecx, 16 ; while (r > 15) {
jl near .ERLOOP
sub ecx, 16 ; r -= 16;
- mov DWORD [esp+temp], ecx
+ mov dword [esp+temp], ecx
mov eax, INT [ebp + 240 * 4] ; code_0xf0 = actbl->ehufco[0xf0];
movzx ecx, byte [ebp + 1024 + 240] ; size_0xf0 = actbl->ehufsi[0xf0];
EMIT_BITS eax ; EMIT_BITS(code_0xf0, size_0xf0)
- mov ecx, DWORD [esp+temp]
+ mov ecx, dword [esp+temp]
jmp .BRLOOP
.ERLOOP:
movsx eax, word [esi] ; temp = t1[k];
movpic edx, POINTER [esp+gotptr] ; load GOT address (edx)
movzx eax, byte [GOTOFF(edx, EXTN(jpeg_nbits_table) + eax)] ; nbits = JPEG_NBITS(temp);
- mov DWORD [esp+temp2], eax
+ mov dword [esp+temp2], eax
; Emit Huffman symbol for run length / number of bits
shl ecx, 4 ; temp3 = (r << 4) + nbits;
add ecx, eax
@@ -315,13 +313,13 @@ EXTN(jsimd_huff_encode_one_block_sse2):
movsx edx, word [esi+DCTSIZE2*2] ; temp2 = t2[k];
; Mask off any extra bits in code
- mov ecx, DWORD [esp+temp2]
+ mov ecx, dword [esp+temp2]
mov eax, 1
shl eax, cl
dec eax
and eax, edx ; temp2 &= (((JLONG)1)<<nbits) - 1;
EMIT_BITS eax ; PUT_BITS(temp2, nbits)
- mov edx, DWORD [esp+temp3]
+ mov edx, dword [esp+temp3]
add esi, 2 ; ++k;
shr edx, 1 ; index >>= 1;
@@ -351,29 +349,29 @@ EXTN(jsimd_huff_encode_one_block_sse2):
shr edx, cl ; index >>= r;
add ecx, eax
lea esi, [esi+ecx*2] ; k += r;
- mov DWORD [esp+temp3], edx
+ mov dword [esp+temp3], edx
jmp .BRLOOP2
.BLOOP2:
bsf ecx, edx ; r = __builtin_ctzl(index);
jz near .ELOOP2
lea esi, [esi+ecx*2] ; k += r;
shr edx, cl ; index >>= r;
- mov DWORD [esp+temp3], edx
+ mov dword [esp+temp3], edx
.BRLOOP2:
cmp ecx, 16 ; while (r > 15) {
jl near .ERLOOP2
sub ecx, 16 ; r -= 16;
- mov DWORD [esp+temp], ecx
+ mov dword [esp+temp], ecx
mov eax, INT [ebp + 240 * 4] ; code_0xf0 = actbl->ehufco[0xf0];
movzx ecx, byte [ebp + 1024 + 240] ; size_0xf0 = actbl->ehufsi[0xf0];
EMIT_BITS eax ; EMIT_BITS(code_0xf0, size_0xf0)
- mov ecx, DWORD [esp+temp]
+ mov ecx, dword [esp+temp]
jmp .BRLOOP2
.ERLOOP2:
movsx eax, word [esi] ; temp = t1[k];
bsr eax, eax ; nbits = 32 - __builtin_clz(temp);
inc eax
- mov DWORD [esp+temp2], eax
+ mov dword [esp+temp2], eax
; Emit Huffman symbol for run length / number of bits
shl ecx, 4 ; temp3 = (r << 4) + nbits;
add ecx, eax
@@ -383,13 +381,13 @@ EXTN(jsimd_huff_encode_one_block_sse2):
movsx edx, word [esi+DCTSIZE2*2] ; temp2 = t2[k];
; Mask off any extra bits in code
- mov ecx, DWORD [esp+temp2]
+ mov ecx, dword [esp+temp2]
mov eax, 1
shl eax, cl
dec eax
and eax, edx ; temp2 &= (((JLONG)1)<<nbits) - 1;
EMIT_BITS eax ; PUT_BITS(temp2, nbits)
- mov edx, DWORD [esp+temp3]
+ mov edx, dword [esp+temp3]
add esi, 2 ; ++k;
shr edx, 1 ; index >>= 1;
@@ -406,8 +404,8 @@ EXTN(jsimd_huff_encode_one_block_sse2):
mov eax, [esp+buffer]
pop esi
; Save put_buffer & put_bits
- mov DWORD [esi+8], put_buffer ; state->cur.put_buffer = put_buffer;
- mov DWORD [esi+12], put_bits ; state->cur.put_bits = put_bits;
+ mov dword [esi+8], put_buffer ; state->cur.put_buffer = put_buffer;
+ mov dword [esi+12], put_bits ; state->cur.put_bits = put_bits;
pop ebp
pop edi
diff --git a/media/libjpeg/simd/i386/jcphuff-sse2.asm b/media/libjpeg/simd/i386/jcphuff-sse2.asm
index e35a7d8bbfb66358325045036c81566e33098690..8b731783760ff002c5a99c99fd55c20e8e8b7148 100644
--- a/media/libjpeg/simd/i386/jcphuff-sse2.asm
+++ b/media/libjpeg/simd/i386/jcphuff-sse2.asm
@@ -15,8 +15,6 @@
;
; This file contains an SSE2 implementation of data preparation for progressive
; Huffman encoding. See jcphuff.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jcsample-avx2.asm b/media/libjpeg/simd/i386/jcsample-avx2.asm
index 5bcdefd502ed19295fd2230fb1050d1c6b57fcae..0a20802dd89086b33dcf5abd7378362a0ac28360 100644
--- a/media/libjpeg/simd/i386/jcsample-avx2.asm
+++ b/media/libjpeg/simd/i386/jcsample-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jcsample-mmx.asm b/media/libjpeg/simd/i386/jcsample-mmx.asm
index faf4234589887fc129eb157a6594d67f52b1ff80..2c223eebe8160ec247f58dbe5a8d1d92751bffe9 100644
--- a/media/libjpeg/simd/i386/jcsample-mmx.asm
+++ b/media/libjpeg/simd/i386/jcsample-mmx.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jcsample-sse2.asm b/media/libjpeg/simd/i386/jcsample-sse2.asm
index b10fa836a55f4b0b2e4966f5cf63203b0bf7af05..4fea60d2e2106b9beaab57f289843f72f189adc8 100644
--- a/media/libjpeg/simd/i386/jcsample-sse2.asm
+++ b/media/libjpeg/simd/i386/jcsample-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jdcolext-avx2.asm b/media/libjpeg/simd/i386/jdcolext-avx2.asm
index 46de9b9df2b60083f617534eb97c66ce49d98858..015be0416c5cb3c47ac2bc6231d8e2e2c2613090 100644
--- a/media/libjpeg/simd/i386/jdcolext-avx2.asm
+++ b/media/libjpeg/simd/i386/jdcolext-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -348,7 +346,7 @@ EXTN(jsimd_ycc_rgb_convert_avx2):
vmovd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
@@ -357,7 +355,7 @@ EXTN(jsimd_ycc_rgb_convert_avx2):
; space.
test ecx, ecx
jz short .nextrow
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/media/libjpeg/simd/i386/jdcolext-mmx.asm b/media/libjpeg/simd/i386/jdcolext-mmx.asm
index cd2cb3f95d44d272353eed23d00aa03668a3bc76..5813cfcb66f57a578e4e8f4f712c26e6a35a8d33 100644
--- a/media/libjpeg/simd/i386/jdcolext-mmx.asm
+++ b/media/libjpeg/simd/i386/jdcolext-mmx.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -280,7 +278,7 @@ EXTN(jsimd_ycc_rgb_convert_mmx):
movd eax, mmA
cmp ecx, byte SIZEOF_DWORD
jb short .column_st2
- mov DWORD [edi+0*SIZEOF_DWORD], eax
+ mov dword [edi+0*SIZEOF_DWORD], eax
psrlq mmA, DWORD_BIT
movd eax, mmA
sub ecx, byte SIZEOF_DWORD
@@ -288,14 +286,14 @@ EXTN(jsimd_ycc_rgb_convert_mmx):
.column_st2:
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi+0*SIZEOF_WORD], ax
+ mov word [edi+0*SIZEOF_WORD], ax
shr eax, WORD_BIT
sub ecx, byte SIZEOF_WORD
add edi, byte SIZEOF_WORD
.column_st1:
cmp ecx, byte SIZEOF_BYTE
jb short .nextrow
- mov BYTE [edi+0*SIZEOF_BYTE], al
+ mov byte [edi+0*SIZEOF_BYTE], al
%else ; RGB_PIXELSIZE == 4 ; -----------
@@ -367,7 +365,7 @@ EXTN(jsimd_ycc_rgb_convert_mmx):
.column_st4:
cmp ecx, byte SIZEOF_MMWORD/8
jb short .nextrow
- movd DWORD [edi+0*SIZEOF_DWORD], mmA
+ movd dword [edi+0*SIZEOF_DWORD], mmA
%endif ; RGB_PIXELSIZE ; ---------------
diff --git a/media/libjpeg/simd/i386/jdcolext-sse2.asm b/media/libjpeg/simd/i386/jdcolext-sse2.asm
index 0fcb0067f5e2bb60ba8767cd40fb5cb6f1614117..d5572b32946ceb75908ac1865dcfa5538c36833a 100644
--- a/media/libjpeg/simd/i386/jdcolext-sse2.asm
+++ b/media/libjpeg/simd/i386/jdcolext-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -320,7 +318,7 @@ EXTN(jsimd_ycc_rgb_convert_sse2):
movd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
@@ -329,7 +327,7 @@ EXTN(jsimd_ycc_rgb_convert_sse2):
; space.
test ecx, ecx
jz short .nextrow
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/media/libjpeg/simd/i386/jdcolor-avx2.asm b/media/libjpeg/simd/i386/jdcolor-avx2.asm
index d2f86e65017905040ed514cc96bad350307c4e7a..e05b60d001799c6c23444e9a3f32903b5a13fa4a 100644
--- a/media/libjpeg/simd/i386/jdcolor-avx2.asm
+++ b/media/libjpeg/simd/i386/jdcolor-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jdcolor-mmx.asm b/media/libjpeg/simd/i386/jdcolor-mmx.asm
index 8f5a3b3f28ada297175a218f9624245a1efced0d..fb7e7bcce4b030bff905d4f27546a9e989672d4c 100644
--- a/media/libjpeg/simd/i386/jdcolor-mmx.asm
+++ b/media/libjpeg/simd/i386/jdcolor-mmx.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jdcolor-sse2.asm b/media/libjpeg/simd/i386/jdcolor-sse2.asm
index ae553dba3e683afbc308f19ab3bf7641e69d93c6..b736255317e38f0143e0f6b5cda6f61cc7bd52f0 100644
--- a/media/libjpeg/simd/i386/jdcolor-sse2.asm
+++ b/media/libjpeg/simd/i386/jdcolor-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jdmerge-avx2.asm b/media/libjpeg/simd/i386/jdmerge-avx2.asm
index 173184406f945acca86bde1a0a60d68db06ab567..711e6792d0f52fc8a728bb510f5fdb1375dae3e4 100644
--- a/media/libjpeg/simd/i386/jdmerge-avx2.asm
+++ b/media/libjpeg/simd/i386/jdmerge-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jdmerge-mmx.asm b/media/libjpeg/simd/i386/jdmerge-mmx.asm
index 607bf39f3143579680603769417db98afb3bbbd4..6e8311d4081666b06929f05b60fc165e19b37880 100644
--- a/media/libjpeg/simd/i386/jdmerge-mmx.asm
+++ b/media/libjpeg/simd/i386/jdmerge-mmx.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jdmerge-sse2.asm b/media/libjpeg/simd/i386/jdmerge-sse2.asm
index ddb1d5e7127efaa94337269a312083d5da7311a9..e32f90aa177836da443f17f12388ea011a7b6aca 100644
--- a/media/libjpeg/simd/i386/jdmerge-sse2.asm
+++ b/media/libjpeg/simd/i386/jdmerge-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jdmrgext-avx2.asm b/media/libjpeg/simd/i386/jdmrgext-avx2.asm
index cde48653acf01394d138b3a0b1180755a48932e6..e35f7282bc41d071d6104fae2b6c1467f15045ac 100644
--- a/media/libjpeg/simd/i386/jdmrgext-avx2.asm
+++ b/media/libjpeg/simd/i386/jdmrgext-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -354,7 +352,7 @@ EXTN(jsimd_h2v1_merged_upsample_avx2):
vmovd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
@@ -363,7 +361,7 @@ EXTN(jsimd_h2v1_merged_upsample_avx2):
; space.
test ecx, ecx
jz short .endcolumn
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/media/libjpeg/simd/i386/jdmrgext-mmx.asm b/media/libjpeg/simd/i386/jdmrgext-mmx.asm
index 4b9e35d894674697cd86961ceb117c9599e032c3..eb3e36b4759bfbff33f9f764975eeaadf881acfb 100644
--- a/media/libjpeg/simd/i386/jdmrgext-mmx.asm
+++ b/media/libjpeg/simd/i386/jdmrgext-mmx.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -283,7 +281,7 @@ EXTN(jsimd_h2v1_merged_upsample_mmx):
movd eax, mmA
cmp ecx, byte SIZEOF_DWORD
jb short .column_st2
- mov DWORD [edi+0*SIZEOF_DWORD], eax
+ mov dword [edi+0*SIZEOF_DWORD], eax
psrlq mmA, DWORD_BIT
movd eax, mmA
sub ecx, byte SIZEOF_DWORD
@@ -291,14 +289,14 @@ EXTN(jsimd_h2v1_merged_upsample_mmx):
.column_st2:
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi+0*SIZEOF_WORD], ax
+ mov word [edi+0*SIZEOF_WORD], ax
shr eax, WORD_BIT
sub ecx, byte SIZEOF_WORD
add edi, byte SIZEOF_WORD
.column_st1:
cmp ecx, byte SIZEOF_BYTE
jb short .endcolumn
- mov BYTE [edi+0*SIZEOF_BYTE], al
+ mov byte [edi+0*SIZEOF_BYTE], al
%else ; RGB_PIXELSIZE == 4 ; -----------
@@ -373,7 +371,7 @@ EXTN(jsimd_h2v1_merged_upsample_mmx):
.column_st4:
cmp ecx, byte SIZEOF_MMWORD/8
jb short .endcolumn
- movd DWORD [edi+0*SIZEOF_DWORD], mmA
+ movd dword [edi+0*SIZEOF_DWORD], mmA
%endif ; RGB_PIXELSIZE ; ---------------
diff --git a/media/libjpeg/simd/i386/jdmrgext-sse2.asm b/media/libjpeg/simd/i386/jdmrgext-sse2.asm
index ac4697ef610bc0b8d12fd3b7fd8a95bb95f04207..c113dc4d27ed3b0ea2d155f3007c15a514a5c48b 100644
--- a/media/libjpeg/simd/i386/jdmrgext-sse2.asm
+++ b/media/libjpeg/simd/i386/jdmrgext-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -325,7 +323,7 @@ EXTN(jsimd_h2v1_merged_upsample_sse2):
movd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
@@ -334,7 +332,7 @@ EXTN(jsimd_h2v1_merged_upsample_sse2):
; space.
test ecx, ecx
jz short .endcolumn
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/media/libjpeg/simd/i386/jdsample-avx2.asm b/media/libjpeg/simd/i386/jdsample-avx2.asm
index 61ce511c76f8b53798fdb8514655461f146bf284..a800c35e08351f602dc33dde388e2491ec82e847 100644
--- a/media/libjpeg/simd/i386/jdsample-avx2.asm
+++ b/media/libjpeg/simd/i386/jdsample-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jdsample-mmx.asm b/media/libjpeg/simd/i386/jdsample-mmx.asm
index 1f810fabe1b47f054a26941189bd9db038dfc949..12c49f0eab5741ed740c77e7b6fca38d54334fa0 100644
--- a/media/libjpeg/simd/i386/jdsample-mmx.asm
+++ b/media/libjpeg/simd/i386/jdsample-mmx.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jdsample-sse2.asm b/media/libjpeg/simd/i386/jdsample-sse2.asm
index f0da626924a2694f9e3a01d709d06d0eccec1f39..4e28d2f4b80293c4780d4f5daeecafdbf002755d 100644
--- a/media/libjpeg/simd/i386/jdsample-sse2.asm
+++ b/media/libjpeg/simd/i386/jdsample-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/i386/jfdctflt-3dn.asm b/media/libjpeg/simd/i386/jfdctflt-3dn.asm
index 1d45865b473a5a39145150e4388396921ebd4617..322ab1632526fa8e65828cab1342b2414cc58d08 100644
--- a/media/libjpeg/simd/i386/jfdctflt-3dn.asm
+++ b/media/libjpeg/simd/i386/jfdctflt-3dn.asm
@@ -17,8 +17,6 @@
; This file contains a floating-point implementation of the forward DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jfdctflt.c; see the jfdctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jfdctflt-sse.asm b/media/libjpeg/simd/i386/jfdctflt-sse.asm
index 1faf83523a69af2a12ecdf785afd09def007c0a6..86952c6499cf5cfe13c265a13d7e5a5d0cffdbf4 100644
--- a/media/libjpeg/simd/i386/jfdctflt-sse.asm
+++ b/media/libjpeg/simd/i386/jfdctflt-sse.asm
@@ -17,8 +17,6 @@
; This file contains a floating-point implementation of the forward DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jfdctflt.c; see the jfdctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jfdctfst-mmx.asm b/media/libjpeg/simd/i386/jfdctfst-mmx.asm
index 0271901c9c4bc6925fa069b0515527004ac1a859..80645a50d7e7c815c51638a5226a4a5f4a71f6c8 100644
--- a/media/libjpeg/simd/i386/jfdctfst-mmx.asm
+++ b/media/libjpeg/simd/i386/jfdctfst-mmx.asm
@@ -18,8 +18,6 @@
; the forward DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jfdctfst.c; see the jfdctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jfdctfst-sse2.asm b/media/libjpeg/simd/i386/jfdctfst-sse2.asm
index f09dadd9444f3c4fbbb352ea131019a42e63036c..446fa7a68f78e119f854c22910da9406239778b9 100644
--- a/media/libjpeg/simd/i386/jfdctfst-sse2.asm
+++ b/media/libjpeg/simd/i386/jfdctfst-sse2.asm
@@ -18,8 +18,6 @@
; the forward DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jfdctfst.c; see the jfdctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jfdctint-avx2.asm b/media/libjpeg/simd/i386/jfdctint-avx2.asm
index ae258eee4e75b6c7b09e12f231195940f7d21b89..97de2302b54d438e7eff12041934e0c21ccfb6cd 100644
--- a/media/libjpeg/simd/i386/jfdctint-avx2.asm
+++ b/media/libjpeg/simd/i386/jfdctint-avx2.asm
@@ -18,8 +18,6 @@
; forward DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jfdctint.c; see the jfdctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jfdctint-mmx.asm b/media/libjpeg/simd/i386/jfdctint-mmx.asm
index c6bd9597cd517a36376e011f30886ebd8e249aae..3ade9d4921d92371fea5d51e27a5095cfa184849 100644
--- a/media/libjpeg/simd/i386/jfdctint-mmx.asm
+++ b/media/libjpeg/simd/i386/jfdctint-mmx.asm
@@ -18,8 +18,6 @@
; forward DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jfdctint.c; see the jfdctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jfdctint-sse2.asm b/media/libjpeg/simd/i386/jfdctint-sse2.asm
index d67dcc1b8d51168bde65c915997952b508028ca7..71b684c4fb44a3f4d0ebc38148ac3113e3349325 100644
--- a/media/libjpeg/simd/i386/jfdctint-sse2.asm
+++ b/media/libjpeg/simd/i386/jfdctint-sse2.asm
@@ -18,8 +18,6 @@
; forward DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jfdctint.c; see the jfdctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jidctflt-3dn.asm b/media/libjpeg/simd/i386/jidctflt-3dn.asm
index 73aa18d0e647a2f90434e9c86e239727a457384d..87951910d8e555d6a0f33d3b28b1373b6c56595a 100644
--- a/media/libjpeg/simd/i386/jidctflt-3dn.asm
+++ b/media/libjpeg/simd/i386/jidctflt-3dn.asm
@@ -17,8 +17,6 @@
; This file contains a floating-point implementation of the inverse DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jidctflt.c; see the jidctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -92,23 +90,23 @@ EXTN(jsimd_idct_float_3dnow):
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_3DNOW
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
pushpic ebx ; save GOT address
- mov ebx, DWORD [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
- mov eax, DWORD [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
- or ebx, DWORD [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
- or ebx, DWORD [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
+ mov ebx, dword [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
+ or ebx, dword [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
+ or ebx, dword [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
or eax, ebx
poppic ebx ; restore GOT address
jnz short .columnDCT
; -- AC terms all zero
- movd mm0, DWORD [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
+ movd mm0, dword [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
punpcklwd mm0, mm0
psrad mm0, (DWORD_BIT-WORD_BIT)
@@ -135,10 +133,10 @@ EXTN(jsimd_idct_float_3dnow):
; -- Even part
- movd mm0, DWORD [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
- movd mm1, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
- movd mm2, DWORD [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
- movd mm3, DWORD [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
+ movd mm0, dword [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
+ movd mm1, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ movd mm2, dword [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
+ movd mm3, dword [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
punpcklwd mm0, mm0
punpcklwd mm1, mm1
@@ -182,10 +180,10 @@ EXTN(jsimd_idct_float_3dnow):
; -- Odd part
- movd mm2, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- movd mm3, DWORD [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
- movd mm5, DWORD [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
- movd mm1, DWORD [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
+ movd mm2, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ movd mm3, dword [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
+ movd mm5, dword [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
+ movd mm1, dword [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
punpcklwd mm2, mm2
punpcklwd mm3, mm3
diff --git a/media/libjpeg/simd/i386/jidctflt-sse.asm b/media/libjpeg/simd/i386/jidctflt-sse.asm
index 386650f0ccf0aca8affa7c6261fa0418577782ab..b27ecfdf46a0a496c9dde7c72132f0a49b9fcadd 100644
--- a/media/libjpeg/simd/i386/jidctflt-sse.asm
+++ b/media/libjpeg/simd/i386/jidctflt-sse.asm
@@ -17,8 +17,6 @@
; This file contains a floating-point implementation of the inverse DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jidctflt.c; see the jidctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -102,8 +100,8 @@ EXTN(jsimd_idct_float_sse):
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_SSE
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
diff --git a/media/libjpeg/simd/i386/jidctflt-sse2.asm b/media/libjpeg/simd/i386/jidctflt-sse2.asm
index 9de71392805e0ab2ed0b6d4c240a98d40eff3988..c646eaef76ef31bff57a31c9e7ad7ca746e9eff1 100644
--- a/media/libjpeg/simd/i386/jidctflt-sse2.asm
+++ b/media/libjpeg/simd/i386/jidctflt-sse2.asm
@@ -17,8 +17,6 @@
; This file contains a floating-point implementation of the inverse DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jidctflt.c; see the jidctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -102,8 +100,8 @@ EXTN(jsimd_idct_float_sse2):
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_SSE
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movq xmm1, XMM_MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
diff --git a/media/libjpeg/simd/i386/jidctfst-mmx.asm b/media/libjpeg/simd/i386/jidctfst-mmx.asm
index d3e8a5d631d93ddc953b2f8288d0e654ddb755a8..24622d43693f1dab81a2b5f17240457cfe6fc85b 100644
--- a/media/libjpeg/simd/i386/jidctfst-mmx.asm
+++ b/media/libjpeg/simd/i386/jidctfst-mmx.asm
@@ -18,8 +18,6 @@
; the inverse DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jidctfst.c; see the jidctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -123,8 +121,8 @@ EXTN(jsimd_idct_ifast_mmx):
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_IFAST_MMX
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
diff --git a/media/libjpeg/simd/i386/jidctfst-sse2.asm b/media/libjpeg/simd/i386/jidctfst-sse2.asm
index 83bc414a531262c16b649a58852a2e19e2e2005c..19704ffa48f369ff7de834b1ae9b91aeb1dcdcf0 100644
--- a/media/libjpeg/simd/i386/jidctfst-sse2.asm
+++ b/media/libjpeg/simd/i386/jidctfst-sse2.asm
@@ -18,8 +18,6 @@
; the inverse DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jidctfst.c; see the jidctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -118,8 +116,8 @@ EXTN(jsimd_idct_ifast_sse2):
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_IFAST_SSE2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
diff --git a/media/libjpeg/simd/i386/jidctint-avx2.asm b/media/libjpeg/simd/i386/jidctint-avx2.asm
index b3b7b14f586c563a77e435158c03f6f1e62e39ee..c371985c76a54e6866642463e615c5ba35935267 100644
--- a/media/libjpeg/simd/i386/jidctint-avx2.asm
+++ b/media/libjpeg/simd/i386/jidctint-avx2.asm
@@ -18,8 +18,6 @@
; inverse DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jidctint.c; see the jidctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -320,8 +318,8 @@ EXTN(jsimd_idct_islow_avx2):
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_AVX2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
diff --git a/media/libjpeg/simd/i386/jidctint-mmx.asm b/media/libjpeg/simd/i386/jidctint-mmx.asm
index 6ca6d060eae268ada79bd108795e8c695c82c74b..4f07f567f55f5427b9e1603b409639fd45843dd1 100644
--- a/media/libjpeg/simd/i386/jidctint-mmx.asm
+++ b/media/libjpeg/simd/i386/jidctint-mmx.asm
@@ -18,8 +18,6 @@
; inverse DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jidctint.c; see the jidctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -136,8 +134,8 @@ EXTN(jsimd_idct_islow_mmx):
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_MMX
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
diff --git a/media/libjpeg/simd/i386/jidctint-sse2.asm b/media/libjpeg/simd/i386/jidctint-sse2.asm
index a6bd00a9d33ed03a6eba3bfe960b083e9e0279c4..e442fdd2ddbf6e8898efd6f1488cdb83003f6951 100644
--- a/media/libjpeg/simd/i386/jidctint-sse2.asm
+++ b/media/libjpeg/simd/i386/jidctint-sse2.asm
@@ -18,8 +18,6 @@
; inverse DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jidctint.c; see the jidctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -131,8 +129,8 @@ EXTN(jsimd_idct_islow_sse2):
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_SSE2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
diff --git a/media/libjpeg/simd/i386/jidctred-mmx.asm b/media/libjpeg/simd/i386/jidctred-mmx.asm
index 336ee3b909ffb6b799a433ff46054a6887a03b22..e2307e1cb6c6a16b33c220317c585d7a104f247a 100644
--- a/media/libjpeg/simd/i386/jidctred-mmx.asm
+++ b/media/libjpeg/simd/i386/jidctred-mmx.asm
@@ -18,8 +18,6 @@
; output: either 4x4 or 2x2 pixels from an 8x8 DCT block.
; The following code is based directly on the IJG's original jidctred.c;
; see the jidctred.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -144,8 +142,8 @@ EXTN(jsimd_idct_4x4_mmx):
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_4X4_MMX
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
@@ -464,16 +462,16 @@ EXTN(jsimd_idct_4x4_mmx):
mov edx, JSAMPROW [edi+0*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+2*SIZEOF_JSAMPROW]
- movd DWORD [edx+eax*SIZEOF_JSAMPLE], mm1
- movd DWORD [esi+eax*SIZEOF_JSAMPLE], mm0
+ movd dword [edx+eax*SIZEOF_JSAMPLE], mm1
+ movd dword [esi+eax*SIZEOF_JSAMPLE], mm0
psrlq mm1, 4*BYTE_BIT
psrlq mm0, 4*BYTE_BIT
mov edx, JSAMPROW [edi+1*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+3*SIZEOF_JSAMPROW]
- movd DWORD [edx+eax*SIZEOF_JSAMPLE], mm1
- movd DWORD [esi+eax*SIZEOF_JSAMPLE], mm0
+ movd dword [edx+eax*SIZEOF_JSAMPLE], mm1
+ movd dword [esi+eax*SIZEOF_JSAMPLE], mm0
emms ; empty MMX state
@@ -688,8 +686,8 @@ EXTN(jsimd_idct_2x2_mmx):
mov edx, JSAMPROW [edi+0*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+1*SIZEOF_JSAMPROW]
- mov WORD [edx+eax*SIZEOF_JSAMPLE], bx
- mov WORD [esi+eax*SIZEOF_JSAMPLE], cx
+ mov word [edx+eax*SIZEOF_JSAMPLE], bx
+ mov word [esi+eax*SIZEOF_JSAMPLE], cx
emms ; empty MMX state
diff --git a/media/libjpeg/simd/i386/jidctred-sse2.asm b/media/libjpeg/simd/i386/jidctred-sse2.asm
index 97838baffb8749482deb5744764731875862e1bb..6e56494e9751cadfa2f1089b489c7d7b9cd5e193 100644
--- a/media/libjpeg/simd/i386/jidctred-sse2.asm
+++ b/media/libjpeg/simd/i386/jidctred-sse2.asm
@@ -18,8 +18,6 @@
; output: either 4x4 or 2x2 pixels from an 8x8 DCT block.
; The following code is based directly on the IJG's original jidctred.c;
; see the jidctred.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -139,8 +137,8 @@ EXTN(jsimd_idct_4x4_sse2):
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_4X4_SSE2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
@@ -578,8 +576,8 @@ EXTN(jsimd_idct_2x2_sse2):
mov edx, JSAMPROW [edi+0*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+1*SIZEOF_JSAMPROW]
- mov WORD [edx+eax*SIZEOF_JSAMPLE], bx
- mov WORD [esi+eax*SIZEOF_JSAMPLE], cx
+ mov word [edx+eax*SIZEOF_JSAMPLE], bx
+ mov word [esi+eax*SIZEOF_JSAMPLE], cx
pop edi
pop esi
diff --git a/media/libjpeg/simd/i386/jquant-3dn.asm b/media/libjpeg/simd/i386/jquant-3dn.asm
index 1767f444a32822f944bbc5f24f4c1f905ab8e467..5cb60caa947a0694b0a9a52a664f0e241716256e 100644
--- a/media/libjpeg/simd/i386/jquant-3dn.asm
+++ b/media/libjpeg/simd/i386/jquant-3dn.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jquant-mmx.asm b/media/libjpeg/simd/i386/jquant-mmx.asm
index 98932db61b335dbace2b0ecc67eb8b4f721894f6..61305c625de8559b7f57de4a73917afce335ba45 100644
--- a/media/libjpeg/simd/i386/jquant-mmx.asm
+++ b/media/libjpeg/simd/i386/jquant-mmx.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jquant-sse.asm b/media/libjpeg/simd/i386/jquant-sse.asm
index cc244c4baac665827f74ae983956d5312817423f..218adc976f3c47d8f9e2648d144670148d5507e5 100644
--- a/media/libjpeg/simd/i386/jquant-sse.asm
+++ b/media/libjpeg/simd/i386/jquant-sse.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jquantf-sse2.asm b/media/libjpeg/simd/i386/jquantf-sse2.asm
index 8d1201c0b2a36af2a53267d98778833a5925d076..a881ab50f924177799cb469ec86692478ccc6303 100644
--- a/media/libjpeg/simd/i386/jquantf-sse2.asm
+++ b/media/libjpeg/simd/i386/jquantf-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jquanti-avx2.asm b/media/libjpeg/simd/i386/jquanti-avx2.asm
index ea8e1a1e21ad816f971309e26a7d85e1f9f4984a..5ed6bec246ca15b83d96ed9d1fc689a250991cc5 100644
--- a/media/libjpeg/simd/i386/jquanti-avx2.asm
+++ b/media/libjpeg/simd/i386/jquanti-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jquanti-sse2.asm b/media/libjpeg/simd/i386/jquanti-sse2.asm
index 2a69494be31348348d4a27a8108d3f5f1b0f83ef..0a509408aa1314f5434a60aff46fd61d0a1efa08 100644
--- a/media/libjpeg/simd/i386/jquanti-sse2.asm
+++ b/media/libjpeg/simd/i386/jquanti-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/i386/jsimdcpu.asm b/media/libjpeg/simd/i386/jsimdcpu.asm
index 0af4eecf8f45f2bb583a5eddad77ec2f9fc2970e..ddcafa9e2139ca20977f8aa6837e0d6bdb73ea48 100644
--- a/media/libjpeg/simd/i386/jsimdcpu.asm
+++ b/media/libjpeg/simd/i386/jsimdcpu.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/nasm/jcolsamp.inc b/media/libjpeg/simd/nasm/jcolsamp.inc
index a2d5b494a73e7e17854245444e018ea901564230..6f6d7f29d1d95976683e1ecb94449bd8ae179d82 100644
--- a/media/libjpeg/simd/nasm/jcolsamp.inc
+++ b/media/libjpeg/simd/nasm/jcolsamp.inc
@@ -7,8 +7,6 @@
; Based on the x86 SIMD extension for IJG JPEG library
; Copyright (C) 1999-2006, MIYASAKA Masaru.
; For conditions of distribution and use, see copyright notice in jsimdext.inc
-;
-; [TAB8]
; --------------------------------------------------------------------------
diff --git a/media/libjpeg/simd/nasm/jdct.inc b/media/libjpeg/simd/nasm/jdct.inc
index 79d514603995caee82fc6cd95c4ca2b44c3b8bb6..9192f66f0cefa099b6843259eed5fd84e15106bc 100644
--- a/media/libjpeg/simd/nasm/jdct.inc
+++ b/media/libjpeg/simd/nasm/jdct.inc
@@ -7,8 +7,6 @@
; Based on the x86 SIMD extension for IJG JPEG library
; Copyright (C) 1999-2006, MIYASAKA Masaru.
; For conditions of distribution and use, see copyright notice in jsimdext.inc
-;
-; [TAB8]
; Each IDCT routine is responsible for range-limiting its results and
; converting them to unsigned form (0..MAXJSAMPLE). The raw outputs could
diff --git a/media/libjpeg/simd/nasm/jsimdext.inc b/media/libjpeg/simd/nasm/jsimdext.inc
index b40901f03331e3fa62f29865c555df307fa1a4d1..9930d80c2ab32a599cb1b1e65cab68761aedac91 100644
--- a/media/libjpeg/simd/nasm/jsimdext.inc
+++ b/media/libjpeg/simd/nasm/jsimdext.inc
@@ -2,7 +2,7 @@
; jsimdext.inc - common declarations
;
; Copyright 2009 Pierre Ossman <ossman@cendio.se> for Cendio AB
-; Copyright (C) 2010, 2016, D. R. Commander.
+; Copyright (C) 2010, 2016, 2019, D. R. Commander.
; Copyright (C) 2018, Matthieu Darbois.
;
; Based on the x86 SIMD extension for IJG JPEG library - version 1.02
@@ -24,8 +24,6 @@
; 2. Altered source versions must be plainly marked as such, and must not be
; misrepresented as being the original software.
; 3. This notice may not be removed or altered from any source distribution.
-;
-; [TAB8]
; ==========================================================================
; System-dependent configurations
@@ -167,19 +165,19 @@ section .note.GNU-stack noalloc noexec nowrite progbits
%define XMM_DWORD
%define XMM_MMWORD
-%define SIZEOF_BYTE 1 ; sizeof(BYTE)
-%define SIZEOF_WORD 2 ; sizeof(WORD)
-%define SIZEOF_DWORD 4 ; sizeof(DWORD)
-%define SIZEOF_QWORD 8 ; sizeof(QWORD)
-%define SIZEOF_OWORD 16 ; sizeof(OWORD)
-%define SIZEOF_YWORD 32 ; sizeof(YWORD)
+%define SIZEOF_BYTE 1 ; sizeof(byte)
+%define SIZEOF_WORD 2 ; sizeof(word)
+%define SIZEOF_DWORD 4 ; sizeof(dword)
+%define SIZEOF_QWORD 8 ; sizeof(qword)
+%define SIZEOF_OWORD 16 ; sizeof(oword)
+%define SIZEOF_YWORD 32 ; sizeof(yword)
%define BYTE_BIT 8 ; CHAR_BIT in C
-%define WORD_BIT 16 ; sizeof(WORD)*BYTE_BIT
-%define DWORD_BIT 32 ; sizeof(DWORD)*BYTE_BIT
-%define QWORD_BIT 64 ; sizeof(QWORD)*BYTE_BIT
-%define OWORD_BIT 128 ; sizeof(OWORD)*BYTE_BIT
-%define YWORD_BIT 256 ; sizeof(YWORD)*BYTE_BIT
+%define WORD_BIT 16 ; sizeof(word)*BYTE_BIT
+%define DWORD_BIT 32 ; sizeof(dword)*BYTE_BIT
+%define QWORD_BIT 64 ; sizeof(qword)*BYTE_BIT
+%define OWORD_BIT 128 ; sizeof(oword)*BYTE_BIT
+%define YWORD_BIT 256 ; sizeof(yword)*BYTE_BIT
; --------------------------------------------------------------------------
; External Symbol Name
@@ -198,6 +196,11 @@ section .note.GNU-stack noalloc noexec nowrite progbits
%ifdef __YASM_VER__
%define GLOBAL_FUNCTION(name) global EXTN(name):private_extern
%define GLOBAL_DATA(name) global EXTN(name):private_extern
+%else
+%if __NASM_VERSION_ID__ >= 0x020E0000
+%define GLOBAL_FUNCTION(name) global EXTN(name):private_extern
+%define GLOBAL_DATA(name) global EXTN(name):private_extern
+%endif
%endif
%endif
diff --git a/media/libjpeg/simd/x86_64/jccolext-avx2.asm b/media/libjpeg/simd/x86_64/jccolext-avx2.asm
index 5fa3848c19003030a4007fcb1d10c34cd27f5d12..10d28348a96fa22476f0bc12a8fdf714bf0e42f8 100644
--- a/media/libjpeg/simd/x86_64/jccolext-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jccolext-avx2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -96,12 +94,12 @@ EXTN(jsimd_rgb_ycc_convert_avx2):
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
diff --git a/media/libjpeg/simd/x86_64/jccolext-sse2.asm b/media/libjpeg/simd/x86_64/jccolext-sse2.asm
index b1486c0bbc4015bf3f518541f1961f45128902c5..2c914d318382fb5a915c6b10ffb50dadc61902de 100644
--- a/media/libjpeg/simd/x86_64/jccolext-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jccolext-sse2.asm
@@ -12,8 +12,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -95,12 +93,12 @@ EXTN(jsimd_rgb_ycc_convert_sse2):
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
diff --git a/media/libjpeg/simd/x86_64/jccolor-avx2.asm b/media/libjpeg/simd/x86_64/jccolor-avx2.asm
index f9f4be06b72eed3584787e95b9746b181c841ca6..16b78298dc4ff5791f80dce33bcb122855d2939f 100644
--- a/media/libjpeg/simd/x86_64/jccolor-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jccolor-avx2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jccolor-sse2.asm b/media/libjpeg/simd/x86_64/jccolor-sse2.asm
index 3e46601d9596f0f875602d0a76bd33578967278a..e2955c213404085be7d84455150ff74f41b61963 100644
--- a/media/libjpeg/simd/x86_64/jccolor-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jccolor-sse2.asm
@@ -12,8 +12,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jcgray-avx2.asm b/media/libjpeg/simd/x86_64/jcgray-avx2.asm
index 0ec24104f539e8754db165f3ead01c1770f5fda1..591255bb1122e391565d528294cdb47ae9894b4c 100644
--- a/media/libjpeg/simd/x86_64/jcgray-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jcgray-avx2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jcgray-sse2.asm b/media/libjpeg/simd/x86_64/jcgray-sse2.asm
index edf9222e73a2d831c3f0875b6be50f007b5a72e5..e389904f2f85bc53d8432c4f07b66ea76e9bb9fd 100644
--- a/media/libjpeg/simd/x86_64/jcgray-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jcgray-sse2.asm
@@ -12,8 +12,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jcgryext-avx2.asm b/media/libjpeg/simd/x86_64/jcgryext-avx2.asm
index 79e2aa01c3918c4a0f3b2b9f4e0f886164c20faf..175b60de613e69ff37d1b3e3a0fd99ac6f397ae9 100644
--- a/media/libjpeg/simd/x86_64/jcgryext-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jcgryext-avx2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -88,12 +86,12 @@ EXTN(jsimd_rgb_gray_convert_avx2):
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
diff --git a/media/libjpeg/simd/x86_64/jcgryext-sse2.asm b/media/libjpeg/simd/x86_64/jcgryext-sse2.asm
index 9c3ae5ef47ef0e6ed714f6d6a4178cf42d29f4f0..873be80564a6a6b33ed0f337ce689eb56ac277b5 100644
--- a/media/libjpeg/simd/x86_64/jcgryext-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jcgryext-sse2.asm
@@ -12,8 +12,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -87,12 +85,12 @@ EXTN(jsimd_rgb_gray_convert_sse2):
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
diff --git a/media/libjpeg/simd/x86_64/jchuff-sse2.asm b/media/libjpeg/simd/x86_64/jchuff-sse2.asm
index 5ec8b1ae6208b32d290bd79d5524535bf30b3efb..7deab582b972b172dfb67da23083700ffada70dc 100644
--- a/media/libjpeg/simd/x86_64/jchuff-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jchuff-sse2.asm
@@ -17,8 +17,6 @@
; This file contains an SSE2 implementation for Huffman coding of one block.
; The following code is based directly on jchuff.c; see jchuff.c for more
; details.
-;
-; [TAB8]
%include "jsimdext.inc"
@@ -199,7 +197,7 @@ EXTN(jsimd_huff_encode_one_block_sse2):
mov buffer, r11 ; r11 is now sratch
mov put_buffer, MMWORD [r10+16] ; put_buffer = state->cur.put_buffer;
- mov put_bits, DWORD [r10+24] ; put_bits = state->cur.put_bits;
+ mov put_bits, dword [r10+24] ; put_bits = state->cur.put_bits;
push r10 ; r10 is now scratch
; Encode the DC coefficient difference per section F.1.2.1
@@ -332,7 +330,7 @@ EXTN(jsimd_huff_encode_one_block_sse2):
pop r10
; Save put_buffer & put_bits
mov MMWORD [r10+16], put_buffer ; state->cur.put_buffer = put_buffer;
- mov DWORD [r10+24], put_bits ; state->cur.put_bits = put_bits;
+ mov dword [r10+24], put_bits ; state->cur.put_bits = put_bits;
pop rbx
uncollect_args 6
diff --git a/media/libjpeg/simd/x86_64/jcphuff-sse2.asm b/media/libjpeg/simd/x86_64/jcphuff-sse2.asm
index a9446b7a96bcf57e9b214e298154f2b14554e09f..8ed44728fed6ddaa1609223d9043a8d0eaf8834d 100644
--- a/media/libjpeg/simd/x86_64/jcphuff-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jcphuff-sse2.asm
@@ -16,8 +16,6 @@
;
; This file contains an SSE2 implementation of data preparation for progressive
; Huffman encoding. See jcphuff.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jcsample-avx2.asm b/media/libjpeg/simd/x86_64/jcsample-avx2.asm
index 9d5a8618bf1186a5ef0c26e331b9d1ca698d3480..d9922bb4cbf9987be22500c90488a56f1901a524 100644
--- a/media/libjpeg/simd/x86_64/jcsample-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jcsample-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jcsample-sse2.asm b/media/libjpeg/simd/x86_64/jcsample-sse2.asm
index 1b315364d835dc670bf5cf54e01702fbd89395dc..0f107e9a07ffa614cf3dd72cef0210f1e7782aff 100644
--- a/media/libjpeg/simd/x86_64/jcsample-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jcsample-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jdcolext-avx2.asm b/media/libjpeg/simd/x86_64/jdcolext-avx2.asm
index e2b96c732d042f0c94111410047f6801701deb08..677b8ed84e4579571e47a13f4be167d4ea4984a0 100644
--- a/media/libjpeg/simd/x86_64/jdcolext-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jdcolext-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -334,7 +332,7 @@ EXTN(jsimd_ycc_rgb_convert_avx2):
vmovd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
@@ -343,7 +341,7 @@ EXTN(jsimd_ycc_rgb_convert_avx2):
; space.
test rcx, rcx
jz short .nextrow
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/media/libjpeg/simd/x86_64/jdcolext-sse2.asm b/media/libjpeg/simd/x86_64/jdcolext-sse2.asm
index a94954bb8d04933313ddf391b30a2724eaf1b3df..071aa629133dee556430cb37eefe2a3f6a0dfa55 100644
--- a/media/libjpeg/simd/x86_64/jdcolext-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jdcolext-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -306,7 +304,7 @@ EXTN(jsimd_ycc_rgb_convert_sse2):
movd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
@@ -315,7 +313,7 @@ EXTN(jsimd_ycc_rgb_convert_sse2):
; space.
test rcx, rcx
jz short .nextrow
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/media/libjpeg/simd/x86_64/jdcolor-avx2.asm b/media/libjpeg/simd/x86_64/jdcolor-avx2.asm
index abad17662b511f1c551886a9188143da8894457e..43de9db04dc6c737a08af8f3194a0b4c5aca0622 100644
--- a/media/libjpeg/simd/x86_64/jdcolor-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jdcolor-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jdcolor-sse2.asm b/media/libjpeg/simd/x86_64/jdcolor-sse2.asm
index e7079f60b626117d713b565d6ad2531604df6322..b3f1fec07eb59a6dc8b5524ecc1208d78925572d 100644
--- a/media/libjpeg/simd/x86_64/jdcolor-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jdcolor-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jdmerge-avx2.asm b/media/libjpeg/simd/x86_64/jdmerge-avx2.asm
index ca3f063c785ab5fb20072f70f8a298f5c24231d4..9515a17013d35dce9a3a611fde81328cecd5db05 100644
--- a/media/libjpeg/simd/x86_64/jdmerge-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jdmerge-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jdmerge-sse2.asm b/media/libjpeg/simd/x86_64/jdmerge-sse2.asm
index f3e09fa8c358c857afa8bec3c20df32171769122..aedccc20f6c0aee70a9dbd454df154198b79bcf5 100644
--- a/media/libjpeg/simd/x86_64/jdmerge-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jdmerge-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jdmrgext-avx2.asm b/media/libjpeg/simd/x86_64/jdmrgext-avx2.asm
index 04e8a945c6f4e56710b95beeda3b482b1febf64c..bb733c587a493ad7cbedd948bcda4ddb6b523ca6 100644
--- a/media/libjpeg/simd/x86_64/jdmrgext-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jdmrgext-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -339,7 +337,7 @@ EXTN(jsimd_h2v1_merged_upsample_avx2):
vmovd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
@@ -348,7 +346,7 @@ EXTN(jsimd_h2v1_merged_upsample_avx2):
; space.
test rcx, rcx
jz short .endcolumn
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/media/libjpeg/simd/x86_64/jdmrgext-sse2.asm b/media/libjpeg/simd/x86_64/jdmrgext-sse2.asm
index 1cc334557d62bb26a016971c2e4b7037537706e4..b176a4cd4f910e3a68d609ce2a2104a406dc4800 100644
--- a/media/libjpeg/simd/x86_64/jdmrgext-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jdmrgext-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
@@ -310,7 +308,7 @@ EXTN(jsimd_h2v1_merged_upsample_sse2):
movd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
@@ -319,7 +317,7 @@ EXTN(jsimd_h2v1_merged_upsample_sse2):
; space.
test rcx, rcx
jz short .endcolumn
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/media/libjpeg/simd/x86_64/jdsample-avx2.asm b/media/libjpeg/simd/x86_64/jdsample-avx2.asm
index 10fa5c45b50a9dcfbfde00fde48f7f11ae8dd418..fc274a95ea3041ec943f3a7507421dd7019674da 100644
--- a/media/libjpeg/simd/x86_64/jdsample-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jdsample-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jdsample-sse2.asm b/media/libjpeg/simd/x86_64/jdsample-sse2.asm
index d8ccda9b2b49a52f26045333d3d7c59e1409e460..20e07670e91917c6e47146afd3b79485a57438c8 100644
--- a/media/libjpeg/simd/x86_64/jdsample-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jdsample-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
diff --git a/media/libjpeg/simd/x86_64/jfdctflt-sse.asm b/media/libjpeg/simd/x86_64/jfdctflt-sse.asm
index 26f9fb6a51c30360e1f89905f8d9cffd54a6f5d9..ef2796649bc6ade7854d93fbedd4ec7fbb7ee17c 100644
--- a/media/libjpeg/simd/x86_64/jfdctflt-sse.asm
+++ b/media/libjpeg/simd/x86_64/jfdctflt-sse.asm
@@ -17,8 +17,6 @@
; This file contains a floating-point implementation of the forward DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jfdctflt.c; see the jfdctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/x86_64/jfdctfst-sse2.asm b/media/libjpeg/simd/x86_64/jfdctfst-sse2.asm
index aaf8b9e3feaf0c00d5282d2888e2ec8f1903f9c3..2e1bfe6e8c2fc0489ed48be40306a1a2cb2bf6b7 100644
--- a/media/libjpeg/simd/x86_64/jfdctfst-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jfdctfst-sse2.asm
@@ -18,8 +18,6 @@
; the forward DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jfdctfst.c; see the jfdctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/x86_64/jfdctint-avx2.asm b/media/libjpeg/simd/x86_64/jfdctint-avx2.asm
index 448f47d42f748b1da62aa6749dbc041b0da271cd..6ad4cf0bbf7a469ed628724f8cce701ba222bf1d 100644
--- a/media/libjpeg/simd/x86_64/jfdctint-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jfdctint-avx2.asm
@@ -18,8 +18,6 @@
; forward DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jfdctint.c; see the jfdctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/x86_64/jfdctint-sse2.asm b/media/libjpeg/simd/x86_64/jfdctint-sse2.asm
index ef16a52a706cc63c1e2dd7768970dfb5ff30bbed..5d0de3cf41b02dfcafbc176c14be575f0a6f42a1 100644
--- a/media/libjpeg/simd/x86_64/jfdctint-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jfdctint-sse2.asm
@@ -18,8 +18,6 @@
; forward DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jfdctint.c; see the jfdctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/x86_64/jidctflt-sse2.asm b/media/libjpeg/simd/x86_64/jidctflt-sse2.asm
index b676ef390755a485a48ee1c40de8a03352e678fa..ab95e1a6d665aee0014862e5948e6beee3f892d3 100644
--- a/media/libjpeg/simd/x86_64/jidctflt-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jidctflt-sse2.asm
@@ -17,8 +17,6 @@
; This file contains a floating-point implementation of the inverse DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jidctflt.c; see the jidctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -95,8 +93,8 @@ EXTN(jsimd_idct_float_sse2):
mov rcx, DCTSIZE/4 ; ctr
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_SSE
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz near .columnDCT
movq xmm1, XMM_MMWORD [MMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
diff --git a/media/libjpeg/simd/x86_64/jidctfst-sse2.asm b/media/libjpeg/simd/x86_64/jidctfst-sse2.asm
index c6c42f9bdd709657907b0ba91e0297bf024ee655..a66a6811e9dd4061839de885f53e3b1baa740f70 100644
--- a/media/libjpeg/simd/x86_64/jidctfst-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jidctfst-sse2.asm
@@ -18,8 +18,6 @@
; the inverse DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jidctfst.c; see the jidctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -111,8 +109,8 @@ EXTN(jsimd_idct_ifast_sse2):
mov rsi, r11 ; inptr
%ifndef NO_ZERO_COLUMN_TEST_IFAST_SSE2
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
diff --git a/media/libjpeg/simd/x86_64/jidctint-avx2.asm b/media/libjpeg/simd/x86_64/jidctint-avx2.asm
index b60b44f2cef908df674f01e3a8bc95db6fb9e473..50270f47e226bd455015a1058b58b2fd26aae550 100644
--- a/media/libjpeg/simd/x86_64/jidctint-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jidctint-avx2.asm
@@ -18,8 +18,6 @@
; inverse DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jidctint.c; see the jidctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -292,8 +290,8 @@ EXTN(jsimd_idct_islow_avx2):
; ---- Pass 1: process columns.
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_AVX2
- mov eax, DWORD [DWBLOCK(1,0,r11,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,r11,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,r11,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,r11,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,r11,SIZEOF_JCOEF)]
diff --git a/media/libjpeg/simd/x86_64/jidctint-sse2.asm b/media/libjpeg/simd/x86_64/jidctint-sse2.asm
index 83fc344bf08a359d9bf9e75bdf195dc2bd09c2f4..034530c2b8e238dcb5fbc36e70a2ddcd1595670f 100644
--- a/media/libjpeg/simd/x86_64/jidctint-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jidctint-sse2.asm
@@ -18,8 +18,6 @@
; inverse DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jidctint.c; see the jidctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -124,8 +122,8 @@ EXTN(jsimd_idct_islow_sse2):
mov rsi, r11 ; inptr
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_SSE2
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
diff --git a/media/libjpeg/simd/x86_64/jidctred-sse2.asm b/media/libjpeg/simd/x86_64/jidctred-sse2.asm
index af64fdc2343995b31d2a6661e153bf31b741371f..7fbfcc519dda23bf8696de11f6f77b81185aa8c7 100644
--- a/media/libjpeg/simd/x86_64/jidctred-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jidctred-sse2.asm
@@ -18,8 +18,6 @@
; output: either 4x4 or 2x2 pixels from an 8x8 DCT block.
; The following code is based directly on the IJG's original jidctred.c;
; see the jidctred.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
@@ -132,8 +130,8 @@ EXTN(jsimd_idct_4x4_sse2):
mov rsi, r11 ; inptr
%ifndef NO_ZERO_COLUMN_TEST_4X4_SSE2
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz short .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
@@ -562,8 +560,8 @@ EXTN(jsimd_idct_2x2_sse2):
mov rdx, JSAMPROW [rdi+0*SIZEOF_JSAMPROW]
mov rsi, JSAMPROW [rdi+1*SIZEOF_JSAMPROW]
- mov WORD [rdx+rax*SIZEOF_JSAMPLE], bx
- mov WORD [rsi+rax*SIZEOF_JSAMPLE], cx
+ mov word [rdx+rax*SIZEOF_JSAMPLE], bx
+ mov word [rsi+rax*SIZEOF_JSAMPLE], cx
pop rbx
uncollect_args 4
diff --git a/media/libjpeg/simd/x86_64/jquantf-sse2.asm b/media/libjpeg/simd/x86_64/jquantf-sse2.asm
index 4600eeccdbdc87ff8d2e79154c23337cf8d57026..83596a915b0b4c26f50395684b3f251c874fc886 100644
--- a/media/libjpeg/simd/x86_64/jquantf-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jquantf-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/x86_64/jquanti-avx2.asm b/media/libjpeg/simd/x86_64/jquanti-avx2.asm
index b7243e432b4fb75d77cceadf391e7229624f43c4..5f04d223305de07a288b8408760e1bd43329f8d0 100644
--- a/media/libjpeg/simd/x86_64/jquanti-avx2.asm
+++ b/media/libjpeg/simd/x86_64/jquanti-avx2.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/x86_64/jquanti-sse2.asm b/media/libjpeg/simd/x86_64/jquanti-sse2.asm
index 7ff7275f71f82264eabc9347803a5cba3c00b2d9..bb6fa69ea3c16b409f196b636c0c40e12071480e 100644
--- a/media/libjpeg/simd/x86_64/jquanti-sse2.asm
+++ b/media/libjpeg/simd/x86_64/jquanti-sse2.asm
@@ -13,8 +13,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
diff --git a/media/libjpeg/simd/x86_64/jsimdcpu.asm b/media/libjpeg/simd/x86_64/jsimdcpu.asm
index a905282aa2a78d9eff6586232fdbe4b14cbcf809..705f813d7da609474a5c99ed27ff8e6f63cb6f2d 100644
--- a/media/libjpeg/simd/x86_64/jsimdcpu.asm
+++ b/media/libjpeg/simd/x86_64/jsimdcpu.asm
@@ -14,8 +14,6 @@
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"