19c791cdac
With rare exceptions ...
- Always separate line continuation characters by one space from
preceding code.
- Always use two-space indentation. Never use tabs.
- Always use K&R-style conditional blocks.
- Always surround operators with spaces, except in raw assembly code.
- Always put a space after, but not before, a comma.
- Never put a space between type casts and variables/function calls.
- Never put a space between the function name and the argument list in
function declarations and prototypes.
- Always surround braces ('{' and '}') with spaces.
- Always surround statements (if, for, else, catch, while, do, switch)
with spaces.
- Always attach pointer symbols ('*' and '**') to the variable or
function name.
- Always precede pointer symbols ('*' and '**') by a space in type
casts.
- Use the MIN() macro from jpegint.h within the libjpeg and TurboJPEG
API libraries (using min() from tjutil.h is still necessary for
TJBench.)
- Where it makes sense (particularly in the TurboJPEG code), put a blank
line after variable declaration blocks.
- Always separate statements in one-liners by two spaces.
The purpose of this was to ease maintenance on my part and also to make
it easier for contributors to figure out how to format patch
submissions. This was admittedly confusing (even to me sometimes) when
we had 3 or 4 different style conventions in the same source tree. The
new convention is more consistent with the formatting of other OSS code
bases.
This commit corrects deviations from the chosen formatting style in the
libjpeg API code and reformats the TurboJPEG API code such that it
conforms to the same standard.
NOTES:
- Although it is no longer necessary for the function name in function
declarations to begin in Column 1 (this was historically necessary
because of the ansi2knr utility, which allowed libjpeg to be built
with non-ANSI compilers), we retain that formatting for the libjpeg
code because it improves readability when using libjpeg's function
attribute macros (GLOBAL(), etc.)
- This reformatting project was accomplished with the help of AStyle and
Uncrustify, although neither was completely up to the task, and thus
a great deal of manual tweaking was required. Note to developers of
code formatting utilities: the libjpeg-turbo code base is an
excellent test bed, because AFAICT, it breaks every single one of the
utilities that are currently available.
- The legacy (MMX, SSE, 3DNow!) assembly code for i386 has been
formatted to match the SSE2 code (refer to
ff5685d5344273df321eb63a005eaae19d2496e3.) I hadn't intended to
bother with this, but the Loongson MMI implementation demonstrated
that there is still academic value to the MMX implementation, as an
algorithmic model for other 64-bit vector implementations. Thus, it
is desirable to improve its readability in the same manner as that of
the SSE2 implementation.
132 lines
3.6 KiB
NASM
132 lines
3.6 KiB
NASM
;
|
|
; jsimdcpu.asm - SIMD instruction support check
|
|
;
|
|
; Copyright 2009 Pierre Ossman <ossman@cendio.se> for Cendio AB
|
|
; Copyright (C) 2016, D. R. Commander.
|
|
;
|
|
; 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
|
|
;
|
|
; This file should be assembled with NASM (Netwide Assembler),
|
|
; can *not* be assembled with Microsoft's MASM or any compatible
|
|
; 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"
|
|
|
|
; --------------------------------------------------------------------------
|
|
SECTION SEG_TEXT
|
|
BITS 32
|
|
;
|
|
; Check if the CPU supports SIMD instructions
|
|
;
|
|
; GLOBAL(unsigned int)
|
|
; jpeg_simd_cpu_support(void)
|
|
;
|
|
|
|
align 32
|
|
GLOBAL_FUNCTION(jpeg_simd_cpu_support)
|
|
|
|
EXTN(jpeg_simd_cpu_support):
|
|
push ebx
|
|
; push ecx ; need not be preserved
|
|
; push edx ; need not be preserved
|
|
; push esi ; unused
|
|
push edi
|
|
|
|
xor edi, edi ; simd support flag
|
|
|
|
pushfd
|
|
pop eax
|
|
mov edx, eax
|
|
xor eax, 1<<21 ; flip ID bit in EFLAGS
|
|
push eax
|
|
popfd
|
|
pushfd
|
|
pop eax
|
|
xor eax, edx
|
|
jz near .return ; CPUID is not supported
|
|
|
|
; Check for MMX instruction support
|
|
xor eax, eax
|
|
cpuid
|
|
test eax, eax
|
|
jz near .return
|
|
|
|
xor eax, eax
|
|
inc eax
|
|
cpuid
|
|
mov eax, edx ; eax = Standard feature flags
|
|
|
|
test eax, 1<<23 ; bit23:MMX
|
|
jz short .no_mmx
|
|
or edi, byte JSIMD_MMX
|
|
.no_mmx:
|
|
test eax, 1<<25 ; bit25:SSE
|
|
jz short .no_sse
|
|
or edi, byte JSIMD_SSE
|
|
.no_sse:
|
|
test eax, 1<<26 ; bit26:SSE2
|
|
jz short .no_sse2
|
|
or edi, byte JSIMD_SSE2
|
|
.no_sse2:
|
|
|
|
; Check for AVX2 instruction support
|
|
mov eax, 7
|
|
xor ecx, ecx
|
|
cpuid
|
|
mov eax, ebx
|
|
test eax, 1<<5 ; bit5:AVX2
|
|
jz short .no_avx2
|
|
|
|
; Check for AVX2 O/S support
|
|
mov eax, 1
|
|
xor ecx, ecx
|
|
cpuid
|
|
test ecx, 1<<27
|
|
jz short .no_avx2 ; O/S does not support XSAVE
|
|
test ecx, 1<<28
|
|
jz short .no_avx2 ; CPU does not support AVX2
|
|
|
|
xor ecx, ecx
|
|
xgetbv
|
|
test eax, 6 ; O/S does not manage XMM/YMM state
|
|
; using XSAVE
|
|
jz short .no_avx2
|
|
|
|
or edi, JSIMD_AVX2
|
|
.no_avx2:
|
|
|
|
; Check for 3DNow! instruction support
|
|
mov eax, 0x80000000
|
|
cpuid
|
|
cmp eax, 0x80000000
|
|
jbe short .return
|
|
|
|
mov eax, 0x80000001
|
|
cpuid
|
|
mov eax, edx ; eax = Extended feature flags
|
|
|
|
test eax, 1<<31 ; bit31:3DNow!(vendor independent)
|
|
jz short .no_3dnow
|
|
or edi, byte JSIMD_3DNOW
|
|
.no_3dnow:
|
|
|
|
.return:
|
|
mov eax, edi
|
|
|
|
pop edi
|
|
; pop esi ; unused
|
|
; pop edx ; need not be preserved
|
|
; pop ecx ; need not be preserved
|
|
pop ebx
|
|
ret
|
|
|
|
; For some reason, the OS X linker does not honor the request to align the
|
|
; segment unless we do this.
|
|
align 32
|