b71962fdc9
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
66 lines
1.9 KiB
C
66 lines
1.9 KiB
C
/*
|
|
* 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.
|
|
*/
|
|
|
|
|
|
#ifndef IDCT_ARM_H
|
|
#define IDCT_ARM_H
|
|
|
|
#if HAVE_ARMV6
|
|
extern prototype_idct(vp8_short_idct4x4llm_1_v6);
|
|
extern prototype_idct(vp8_short_idct4x4llm_v6_dual);
|
|
extern prototype_idct_scalar_add(vp8_dc_only_idct_add_v6);
|
|
extern prototype_second_order(vp8_short_inv_walsh4x4_1_v6);
|
|
extern prototype_second_order(vp8_short_inv_walsh4x4_v6);
|
|
|
|
#if !CONFIG_RUNTIME_CPU_DETECT
|
|
#undef vp8_idct_idct1
|
|
#define vp8_idct_idct1 vp8_short_idct4x4llm_1_v6
|
|
|
|
#undef vp8_idct_idct16
|
|
#define vp8_idct_idct16 vp8_short_idct4x4llm_v6_dual
|
|
|
|
#undef vp8_idct_idct1_scalar_add
|
|
#define vp8_idct_idct1_scalar_add vp8_dc_only_idct_add_v6
|
|
|
|
#undef vp8_idct_iwalsh1
|
|
#define vp8_idct_iwalsh1 vp8_short_inv_walsh4x4_1_v6
|
|
|
|
#undef vp8_idct_iwalsh16
|
|
#define vp8_idct_iwalsh16 vp8_short_inv_walsh4x4_v6
|
|
#endif
|
|
#endif
|
|
|
|
#if HAVE_ARMV7
|
|
extern prototype_idct(vp8_short_idct4x4llm_1_neon);
|
|
extern prototype_idct(vp8_short_idct4x4llm_neon);
|
|
extern prototype_idct_scalar_add(vp8_dc_only_idct_add_neon);
|
|
extern prototype_second_order(vp8_short_inv_walsh4x4_1_neon);
|
|
extern prototype_second_order(vp8_short_inv_walsh4x4_neon);
|
|
|
|
#if !CONFIG_RUNTIME_CPU_DETECT
|
|
#undef vp8_idct_idct1
|
|
#define vp8_idct_idct1 vp8_short_idct4x4llm_1_neon
|
|
|
|
#undef vp8_idct_idct16
|
|
#define vp8_idct_idct16 vp8_short_idct4x4llm_neon
|
|
|
|
#undef vp8_idct_idct1_scalar_add
|
|
#define vp8_idct_idct1_scalar_add vp8_dc_only_idct_add_neon
|
|
|
|
#undef vp8_idct_iwalsh1
|
|
#define vp8_idct_iwalsh1 vp8_short_inv_walsh4x4_1_neon
|
|
|
|
#undef vp8_idct_iwalsh16
|
|
#define vp8_idct_iwalsh16 vp8_short_inv_walsh4x4_neon
|
|
#endif
|
|
#endif
|
|
|
|
#endif
|