aom/vpx_ports/arm_cpudetect.c

191 строка
4.4 KiB
C
Исходник Обычный вид История

Add runtime CPU detection support for ARM. The primary goal is to allow a binary to be built which supports NEON, but can fall back to non-NEON routines, since some Android devices do not have NEON, even if they are otherwise ARMv7 (e.g., Tegra). The configure-generated flags HAVE_ARMV7, etc., are used to decide which versions of each function to build, and when CONFIG_RUNTIME_CPU_DETECT is enabled, the correct version is chosen at run time. In order for this to work, the CFLAGS must be set to something appropriate (e.g., without -mfpu=neon for ARMv7, and with appropriate -march and -mcpu for even earlier configurations), or the native C code will not be able to run. The ASFLAGS must remain set for the most advanced instruction set required at build time, since the ARM assembler will refuse to emit them otherwise. I have not attempted to make any changes to configure to do this automatically. Doing so will probably require the addition of new configure options. Many of the hooks for RTCD on ARM were already there, but a lot of the code had bit-rotted, and a good deal of the ARM-specific code is not integrated into the RTCD structs at all. I did not try to resolve the latter, merely to add the minimal amount of protection around them to allow RTCD to work. Those functions that were called based on an ifdef at the calling site were expanded to check the RTCD flags at that site, but they should be added to an RTCD struct somewhere in the future. The functions invoked with global function pointers still are, but these should be moved into an RTCD struct for thread safety (I believe every platform currently supported has atomic pointer stores, but this is not guaranteed). The encoder's boolhuff functions did not even have _c and armv7 suffixes, and the correct version was resolved at link time. The token packing functions did have appropriate suffixes, but the version was selected with a define, with no associated RTCD struct. However, for both of these, the only armv7 instruction they actually used was rbit, and this was completely superfluous, so I reworked them to avoid it. The only non-ARMv4 instruction remaining in them is clz, which is ARMv5 (not even ARMv5TE is required). Considering that there are no ARM-specific configs which are not at least ARMv5TE, I did not try to detect these at runtime, and simply enable them for ARMv5 and above. Finally, the NEON register saving code was completely non-reentrant, since it saved the registers to a global, static variable. I moved the storage for this onto the stack. A single binary built with this code was tested on an ARM11 (ARMv6) and a Cortex A8 (ARMv7 w/NEON), for both the encoder and decoder, and produced identical output, while using the correct accelerated functions on each. I did not test on any earlier processors. Change-Id: I45cbd63a614f4554c3b325c45d46c0806f009eaa
2010-10-21 02:39:11 +04:00
/*
* Copyright (c) 2010 The WebM project authors. All Rights Reserved.
*
* Use of this source code is governed by a BSD-style license
* that can be found in the LICENSE file in the root of the source
* tree. An additional intellectual property rights grant can be found
* in the file PATENTS. All contributing project authors may
* be found in the AUTHORS file in the root of the source tree.
*/
#include <stdlib.h>
#include <string.h>
#include "arm.h"
static int arm_cpu_env_flags(int *flags)
{
char *env;
env = getenv("VPX_SIMD_CAPS");
if (env && *env)
{
*flags = (int)strtol(env, NULL, 0);
return 0;
}
*flags = 0;
return -1;
}
static int arm_cpu_env_mask(void)
{
char *env;
env = getenv("VPX_SIMD_CAPS_MASK");
return env && *env ? (int)strtol(env, NULL, 0) : ~0;
}
#if defined(_MSC_VER)
/*For GetExceptionCode() and EXCEPTION_ILLEGAL_INSTRUCTION.*/
#define WIN32_LEAN_AND_MEAN
#define WIN32_EXTRA_LEAN
#include <windows.h>
int arm_cpu_caps(void)
{
int flags;
int mask;
if (!arm_cpu_env_flags(&flags))
{
return flags;
}
mask = arm_cpu_env_mask();
/* MSVC has no inline __asm support for ARM, but it does let you __emit
* instructions via their assembled hex code.
* All of these instructions should be essentially nops.
*/
#if defined(HAVE_ARMV5TE)
if (mask & HAS_EDSP)
{
__try
{
/*PLD [r13]*/
__emit(0xF5DDF000);
flags |= HAS_EDSP;
}
__except(GetExceptionCode() == EXCEPTION_ILLEGAL_INSTRUCTION)
{
/*Ignore exception.*/
}
}
#if defined(HAVE_ARMV6)
if (mask & HAS_MEDIA)
__try
{
/*SHADD8 r3,r3,r3*/
__emit(0xE6333F93);
flags |= HAS_MEDIA;
}
__except(GetExceptionCode() == EXCEPTION_ILLEGAL_INSTRUCTION)
{
/*Ignore exception.*/
}
}
#if defined(HAVE_ARMV7)
if (mask & HAS_NEON)
{
__try
{
/*VORR q0,q0,q0*/
__emit(0xF2200150);
flags |= HAS_NEON;
}
__except(GetExceptionCode() == EXCEPTION_ILLEGAL_INSTRUCTION)
{
/*Ignore exception.*/
}
}
#endif
#endif
#endif
return flags & mask;
}
#elif defined(__linux__)
#include <stdio.h>
int arm_cpu_caps(void)
{
FILE *fin;
int flags;
int mask;
if (!arm_cpu_env_flags(&flags))
{
return flags;
}
mask = arm_cpu_env_mask();
/* Reading /proc/self/auxv would be easier, but that doesn't work reliably
* on Android.
* This also means that detection will fail in Scratchbox.
*/
fin = fopen("/proc/cpuinfo","r");
if(fin != NULL)
{
/* 512 should be enough for anybody (it's even enough for all the flags
* that x86 has accumulated... so far).
*/
char buf[512];
while (fgets(buf, 511, fin) != NULL)
{
#if defined(HAVE_ARMV5TE) || defined(HAVE_ARMV7)
if (memcmp(buf, "Features", 8) == 0)
{
char *p;
#if defined(HAVE_ARMV5TE)
p=strstr(buf, " edsp");
if (p != NULL && (p[5] == ' ' || p[5] == '\n'))
{
flags |= HAS_EDSP;
}
#if defined(HAVE_ARMV7)
p = strstr(buf, " neon");
if (p != NULL && (p[5] == ' ' || p[5] == '\n'))
{
flags |= HAS_NEON;
}
#endif
#endif
}
#endif
#if defined(HAVE_ARMV6)
if (memcmp(buf, "CPU architecture:",17) == 0){
int version;
version = atoi(buf+17);
if (version >= 6)
{
flags |= HAS_MEDIA;
}
}
#endif
}
fclose(fin);
}
return flags & mask;
}
#elif !CONFIG_RUNTIME_CPU_DETECT
int arm_cpu_caps(void)
{
int flags;
int mask;
if (!arm_cpu_env_flags(&flags))
{
return flags;
}
mask = arm_cpu_env_mask();
#if defined(HAVE_ARMV5TE)
flags |= HAS_EDSP;
#endif
#if defined(HAVE_ARMV6)
flags |= HAS_MEDIA;
#endif
#if defined(HAVE_ARMV7)
flags |= HAS_NEON;
#endif
return flags & mask;
}
#else
#error "--enable-runtime-cpu-detect selected, but no CPU detection method " \
"available for your platform. Reconfigure without --enable-runtime-cpu-detect."
#endif