aom/test/fdct4x4_test.cc

343 строки
13 KiB
C++
Исходник Обычный вид История

/*
* Copyright (c) 2012 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 <math.h>
#include <stdlib.h>
#include <string.h>
#include "third_party/googletest/src/include/gtest/gtest.h"
#include "./vp10_rtcd.h"
#include "./vpx_dsp_rtcd.h"
#include "test/acm_random.h"
#include "test/clear_system_state.h"
#include "test/register_state_check.h"
#include "test/transform_test_base.h"
#include "test/util.h"
#include "vp10/common/entropy.h"
#include "vpx/vpx_codec.h"
#include "vpx/vpx_integer.h"
#include "vpx_ports/mem.h"
using libvpx_test::ACMRandom;
namespace {
typedef void (*FdctFunc)(const int16_t *in, tran_low_t *out, int stride);
typedef void (*IdctFunc)(const tran_low_t *in, uint8_t *out, int stride);
typedef void (*IhtFunc)(const tran_low_t *in, uint8_t *out, int stride,
int tx_type);
using libvpx_test::FhtFunc;
typedef std::tr1::tuple<FdctFunc, IdctFunc, int, vpx_bit_depth_t, int>
Dct4x4Param;
typedef std::tr1::tuple<FhtFunc, IhtFunc, int, vpx_bit_depth_t, int> Ht4x4Param;
void fdct4x4_ref(const int16_t *in, tran_low_t *out, int stride,
int /*tx_type*/) {
vpx_fdct4x4_c(in, out, stride);
}
void fht4x4_ref(const int16_t *in, tran_low_t *out, int stride, int tx_type) {
vp10_fht4x4_c(in, out, stride, tx_type);
}
void fwht4x4_ref(const int16_t *in, tran_low_t *out, int stride,
int /*tx_type*/) {
vp10_fwht4x4_c(in, out, stride);
}
#if CONFIG_VP9_HIGHBITDEPTH
void idct4x4_10(const tran_low_t *in, uint8_t *out, int stride) {
vpx_highbd_idct4x4_16_add_c(in, out, stride, 10);
}
void idct4x4_12(const tran_low_t *in, uint8_t *out, int stride) {
vpx_highbd_idct4x4_16_add_c(in, out, stride, 12);
}
void iht4x4_10(const tran_low_t *in, uint8_t *out, int stride, int tx_type) {
vp10_highbd_iht4x4_16_add_c(in, out, stride, tx_type, 10);
}
void iht4x4_12(const tran_low_t *in, uint8_t *out, int stride, int tx_type) {
vp10_highbd_iht4x4_16_add_c(in, out, stride, tx_type, 12);
}
void iwht4x4_10(const tran_low_t *in, uint8_t *out, int stride) {
vpx_highbd_iwht4x4_16_add_c(in, out, stride, 10);
}
void iwht4x4_12(const tran_low_t *in, uint8_t *out, int stride) {
vpx_highbd_iwht4x4_16_add_c(in, out, stride, 12);
}
#if HAVE_SSE2
void idct4x4_10_sse2(const tran_low_t *in, uint8_t *out, int stride) {
vpx_highbd_idct4x4_16_add_sse2(in, out, stride, 10);
}
void idct4x4_12_sse2(const tran_low_t *in, uint8_t *out, int stride) {
vpx_highbd_idct4x4_16_add_sse2(in, out, stride, 12);
}
#endif // HAVE_SSE2
#endif // CONFIG_VP9_HIGHBITDEPTH
class Trans4x4DCT : public libvpx_test::TransformTestBase,
public ::testing::TestWithParam<Dct4x4Param> {
public:
virtual ~Trans4x4DCT() {}
virtual void SetUp() {
fwd_txfm_ = GET_PARAM(0);
inv_txfm_ = GET_PARAM(1);
tx_type_ = GET_PARAM(2);
pitch_ = 4;
fwd_txfm_ref = fdct4x4_ref;
bit_depth_ = GET_PARAM(3);
mask_ = (1 << bit_depth_) - 1;
num_coeffs_ = GET_PARAM(4);
}
virtual void TearDown() { libvpx_test::ClearSystemState(); }
protected:
void RunFwdTxfm(const int16_t *in, tran_low_t *out, int stride) {
fwd_txfm_(in, out, stride);
}
void RunInvTxfm(const tran_low_t *out, uint8_t *dst, int stride) {
inv_txfm_(out, dst, stride);
}
FdctFunc fwd_txfm_;
IdctFunc inv_txfm_;
};
TEST_P(Trans4x4DCT, AccuracyCheck) { RunAccuracyCheck(1); }
TEST_P(Trans4x4DCT, CoeffCheck) { RunCoeffCheck(); }
TEST_P(Trans4x4DCT, MemCheck) { RunMemCheck(); }
TEST_P(Trans4x4DCT, InvAccuracyCheck) { RunInvAccuracyCheck(1); }
class Trans4x4HT : public libvpx_test::TransformTestBase,
public ::testing::TestWithParam<Ht4x4Param> {
public:
virtual ~Trans4x4HT() {}
virtual void SetUp() {
fwd_txfm_ = GET_PARAM(0);
inv_txfm_ = GET_PARAM(1);
tx_type_ = GET_PARAM(2);
pitch_ = 4;
fwd_txfm_ref = fht4x4_ref;
bit_depth_ = GET_PARAM(3);
mask_ = (1 << bit_depth_) - 1;
num_coeffs_ = GET_PARAM(4);
}
virtual void TearDown() { libvpx_test::ClearSystemState(); }
protected:
void RunFwdTxfm(const int16_t *in, tran_low_t *out, int stride) {
fwd_txfm_(in, out, stride, tx_type_);
}
void RunInvTxfm(const tran_low_t *out, uint8_t *dst, int stride) {
inv_txfm_(out, dst, stride, tx_type_);
}
FhtFunc fwd_txfm_;
IhtFunc inv_txfm_;
};
TEST_P(Trans4x4HT, AccuracyCheck) { RunAccuracyCheck(1); }
TEST_P(Trans4x4HT, CoeffCheck) { RunCoeffCheck(); }
TEST_P(Trans4x4HT, MemCheck) { RunMemCheck(); }
TEST_P(Trans4x4HT, InvAccuracyCheck) { RunInvAccuracyCheck(1); }
class Trans4x4WHT : public libvpx_test::TransformTestBase,
public ::testing::TestWithParam<Dct4x4Param> {
public:
virtual ~Trans4x4WHT() {}
virtual void SetUp() {
fwd_txfm_ = GET_PARAM(0);
inv_txfm_ = GET_PARAM(1);
tx_type_ = GET_PARAM(2);
pitch_ = 4;
fwd_txfm_ref = fwht4x4_ref;
bit_depth_ = GET_PARAM(3);
mask_ = (1 << bit_depth_) - 1;
num_coeffs_ = GET_PARAM(4);
}
virtual void TearDown() { libvpx_test::ClearSystemState(); }
protected:
void RunFwdTxfm(const int16_t *in, tran_low_t *out, int stride) {
fwd_txfm_(in, out, stride);
}
void RunInvTxfm(const tran_low_t *out, uint8_t *dst, int stride) {
inv_txfm_(out, dst, stride);
}
FdctFunc fwd_txfm_;
IdctFunc inv_txfm_;
};
TEST_P(Trans4x4WHT, AccuracyCheck) { RunAccuracyCheck(0); }
TEST_P(Trans4x4WHT, CoeffCheck) { RunCoeffCheck(); }
TEST_P(Trans4x4WHT, MemCheck) { RunMemCheck(); }
TEST_P(Trans4x4WHT, InvAccuracyCheck) { RunInvAccuracyCheck(0); }
using std::tr1::make_tuple;
#if CONFIG_VP9_HIGHBITDEPTH
INSTANTIATE_TEST_CASE_P(
C, Trans4x4DCT,
::testing::Values(
make_tuple(&vpx_highbd_fdct4x4_c, &idct4x4_10, 0, VPX_BITS_10, 16),
make_tuple(&vpx_highbd_fdct4x4_c, &idct4x4_12, 0, VPX_BITS_12, 16),
make_tuple(&vpx_fdct4x4_c, &vpx_idct4x4_16_add_c, 0, VPX_BITS_8, 16)));
#else
INSTANTIATE_TEST_CASE_P(C, Trans4x4DCT,
::testing::Values(make_tuple(&vpx_fdct4x4_c,
&vpx_idct4x4_16_add_c, 0,
VPX_BITS_8, 16)));
#endif // CONFIG_VP9_HIGHBITDEPTH
#if CONFIG_VP9_HIGHBITDEPTH
INSTANTIATE_TEST_CASE_P(
C, Trans4x4HT,
::testing::Values(
make_tuple(&vp10_highbd_fht4x4_c, &iht4x4_10, 0, VPX_BITS_10, 16),
make_tuple(&vp10_highbd_fht4x4_c, &iht4x4_10, 1, VPX_BITS_10, 16),
make_tuple(&vp10_highbd_fht4x4_c, &iht4x4_10, 2, VPX_BITS_10, 16),
make_tuple(&vp10_highbd_fht4x4_c, &iht4x4_10, 3, VPX_BITS_10, 16),
make_tuple(&vp10_highbd_fht4x4_c, &iht4x4_12, 0, VPX_BITS_12, 16),
make_tuple(&vp10_highbd_fht4x4_c, &iht4x4_12, 1, VPX_BITS_12, 16),
make_tuple(&vp10_highbd_fht4x4_c, &iht4x4_12, 2, VPX_BITS_12, 16),
make_tuple(&vp10_highbd_fht4x4_c, &iht4x4_12, 3, VPX_BITS_12, 16),
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_c, 0, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_c, 1, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_c, 2, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_c, 3, VPX_BITS_8, 16)));
#else
INSTANTIATE_TEST_CASE_P(
C, Trans4x4HT,
::testing::Values(
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_c, 0, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_c, 1, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_c, 2, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_c, 3, VPX_BITS_8, 16)));
#endif // CONFIG_VP9_HIGHBITDEPTH
#if CONFIG_VP9_HIGHBITDEPTH
INSTANTIATE_TEST_CASE_P(
C, Trans4x4WHT,
::testing::Values(
make_tuple(&vp10_highbd_fwht4x4_c, &iwht4x4_10, 0, VPX_BITS_10, 16),
make_tuple(&vp10_highbd_fwht4x4_c, &iwht4x4_12, 0, VPX_BITS_12, 16),
make_tuple(&vp10_fwht4x4_c, &vpx_iwht4x4_16_add_c, 0, VPX_BITS_8, 16)));
#else
INSTANTIATE_TEST_CASE_P(C, Trans4x4WHT,
::testing::Values(make_tuple(&vp10_fwht4x4_c,
&vpx_iwht4x4_16_add_c, 0,
VPX_BITS_8, 16)));
#endif // CONFIG_VP9_HIGHBITDEPTH
#if HAVE_NEON_ASM && !CONFIG_VP9_HIGHBITDEPTH && !CONFIG_EMULATE_HARDWARE
INSTANTIATE_TEST_CASE_P(NEON, Trans4x4DCT,
::testing::Values(make_tuple(&vpx_fdct4x4_c,
&vpx_idct4x4_16_add_neon,
0, VPX_BITS_8, 16)));
#endif // HAVE_NEON_ASM && !CONFIG_VP9_HIGHBITDEPTH && !CONFIG_EMULATE_HARDWARE
#if HAVE_NEON && !CONFIG_VP9_HIGHBITDEPTH && !CONFIG_EMULATE_HARDWARE
INSTANTIATE_TEST_CASE_P(
NEON, Trans4x4HT,
::testing::Values(
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_neon, 0, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_neon, 1, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_neon, 2, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_c, &vp10_iht4x4_16_add_neon, 3, VPX_BITS_8,
16)));
#endif // HAVE_NEON && !CONFIG_VP9_HIGHBITDEPTH && !CONFIG_EMULATE_HARDWARE
Merge changes from libvpx/master by cherry-pick This commit bring all up-to-date changes from master that are applicable to nextgenv2. Due to the remove VP10 code in master, we had to cherry pick the following commits to get those changes: Add default flags for arm64/armv8 builds Allows building simple targets with sane default flags. For example, using the Android arm64 toolchain from the NDK: https://developer.android.com/ndk/guides/standalone_toolchain.html ./build/tools/make-standalone-toolchain.sh --arch=arm64 \ --platform=android-24 --install-dir=/tmp/arm64 CROSS=/tmp/arm64/bin/aarch64-linux-android- \ ~/libvpx/configure --target=arm64-linux-gcc --disable-multithread BUG=webm:1143 vpx_lpf_horizontal_4_sse2: Remove dead load. Change-Id: I51026c52baa1f0881fcd5b68e1fdf08a2dc0916e Fail early when android target does not include --sdk-path Change-Id: I07e7e63476a2e32e3aae123abdee8b7bbbdc6a8c configure: clean up var style and set_all usage Use quotes whenever possible and {} always for variables. Replace multiple set_all calls with *able_feature(). Conflicts: build/make/configure.sh vp9-svc: Remove some unneeded code/comment. datarate_test,DatarateTestLarge: normalize bits type quiets a msvc warning: conversion from 'const int64_t' to 'size_t', possible loss of data mips added p6600 cpu support Removed -funroll-loops psnr.c: use int64_t for sum of differences Since the values can be negative. *.asm: normalize label format add a trailing ':', though it's optional with the tools we support, it's more common to use it to mark a label. this also quiets the orphan-labels warning with nasm/yasm. BUG=b/29583530 Prevent negative variance Due to rounding, hbd variance may become negative. This commit put in check and clamp of negative values to 0. configure: remove old visual studio support (<2010) BUG=b/29583530 Conflicts: configure configure: restore vs_version variable inadvertently lost in the final patchset of: 078dff7 configure: remove old visual studio support (<2010) this prevents an empty CONFIG_VS_VERSION and avoids make failure Require x86inc.asm Force enable x86inc.asm when building for x86. Previously there were compatibility issues so a flag was added to simplify disabling this code. The known issues have been resolved and x86inc.asm is the preferred abstraction layer (over x86_abi_support.asm). BUG=b:29583530 convolve_test: fix byte offsets in hbd build CONVERT_TO_BYTEPTR(x) was corrected in: 003a9d2 Port metric computation changes from nextgenv2 to use the more common (x) within the expansion. offsets should occur after converting the pointer to the desired type. + factorized some common expressions Conflicts: test/convolve_test.cc vpx_dsp: remove x86inc.asm distinction BUG=b:29583530 Conflicts: vpx_dsp/vpx_dsp.mk vpx_dsp/vpx_dsp_rtcd_defs.pl vpx_dsp/x86/highbd_variance_sse2.c vpx_dsp/x86/variance_sse2.c test: remove x86inc.asm distinction BUG=b:29583530 Conflicts: test/vp9_subtract_test.cc configure: remove x86inc.asm distinction BUG=b:29583530 Change-Id: I59a1192142e89a6a36b906f65a491a734e603617 Update vpx subpixel 1d filter ssse3 asm Speed test shows the new vertical filters have degradation on Celeron Chromebook. Added "X86_SUBPIX_VFILTER_PREFER_SLOW_CELERON" to control the vertical filters activated code. Now just simply active the code without degradation on Celeron. Later there should be 2 set of vertical filters ssse3 functions, and let jump table to choose based on CPU type. improve vpx_filter_block1d* based on replace paddsw+psrlw to pmulhrsw Make set_reference control API work in VP9 Moved the API patch from NextGenv2. An example was included. To try it, for example, run the following command: $ examples/vpx_cx_set_ref vp9 352 288 in.yuv out.ivf 4 30 Conflicts: examples.mk examples/vpx_cx_set_ref.c test/cx_set_ref.sh vp9/decoder/vp9_decoder.c deblock filter : moved from vp8 code branch The deblocking filters used in vp8 have been moved to vpx_dsp for use by both vp8 and vp9. vpx_thread.[hc]: update webp source reference + drop the blob hash, the updated reference will be updated in the commit message BUG=b/29583578 vpx_thread: use native windows cond var if available BUG=b/29583578 original webp change: commit 110ad5835ecd66995d0e7f66dca1b90dea595f5a Author: James Zern <jzern@google.com> Date: Mon Nov 23 19:49:58 2015 -0800 thread: use native windows cond var if available Vista / Server 2008 and up. no speed difference observed. 100644 blob 4fc372b7bc6980a9ed3618c8cce5b67ed7b0f412 src/utils/thread.c 100644 blob 840831185502d42a3246e4b7ff870121c8064791 src/utils/thread.h vpx_thread: use InitializeCriticalSectionEx if available BUG=b/29583578 original webp change: commit 63fadc9ffacc77d4617526a50c696d21d558a70b Author: James Zern <jzern@google.com> Date: Mon Nov 23 20:38:46 2015 -0800 thread: use InitializeCriticalSectionEx if available Windows Vista / Server 2008 and up 100644 blob f84207d89b3a6bb98bfe8f3fa55cad72dfd061ff src/utils/thread.c 100644 blob 840831185502d42a3246e4b7ff870121c8064791 src/utils/thread.h vpx_thread: use WaitForSingleObjectEx if available BUG=b/29583578 original webp change: commit 0fd0e12bfe83f16ce4f1c038b251ccbc13c62ac2 Author: James Zern <jzern@google.com> Date: Mon Nov 23 20:40:26 2015 -0800 thread: use WaitForSingleObjectEx if available Windows XP and up 100644 blob d58f74e5523dbc985fc531cf5f0833f1e9157cf0 src/utils/thread.c 100644 blob 840831185502d42a3246e4b7ff870121c8064791 src/utils/thread.h vpx_thread: use CreateThread for windows phone BUG=b/29583578 original webp change: commit d2afe974f9d751de144ef09d31255aea13b442c0 Author: James Zern <jzern@google.com> Date: Mon Nov 23 20:41:26 2015 -0800 thread: use CreateThread for windows phone _beginthreadex is unavailable for winrt/uwp Change-Id: Ie7412a568278ac67f0047f1764e2521193d74d4d 100644 blob 93f7622797f05f6acc1126e8296c481d276e4047 src/utils/thread.c 100644 blob 840831185502d42a3246e4b7ff870121c8064791 src/utils/thread.h vp9_postproc.c missing extern. BUG=webm:1256 deblock: missing const on extern const. postproc - move filling of noise buffer to vpx_dsp. Fix encoder crashes for odd size input clean-up vp9_intrapred_test remove tuple and overkill VP9IntraPredBase class. postproc: noise style fixes. gtest-all.cc: quiet an unused variable warning under windows / mingw builds vp9_intrapred_test: follow-up cleanup address few comments from ce050afaf3e288895c3bee4160336e2d2133b6ea Change-Id: I3eece7efa9335f4210303993ef6c1857ad5c29c8
2016-06-23 02:08:10 +03:00
#if HAVE_SSE2 && !CONFIG_EMULATE_HARDWARE
INSTANTIATE_TEST_CASE_P(
SSE2, Trans4x4WHT,
::testing::Values(make_tuple(&vp10_fwht4x4_c, &vpx_iwht4x4_16_add_c, 0,
VPX_BITS_8, 16),
make_tuple(&vp10_fwht4x4_c, &vpx_iwht4x4_16_add_sse2, 0,
VPX_BITS_8, 16)));
#endif
#if HAVE_SSE2 && !CONFIG_VP9_HIGHBITDEPTH && !CONFIG_EMULATE_HARDWARE
INSTANTIATE_TEST_CASE_P(SSE2, Trans4x4DCT,
::testing::Values(make_tuple(&vpx_fdct4x4_sse2,
&vpx_idct4x4_16_add_sse2,
0, VPX_BITS_8, 16)));
INSTANTIATE_TEST_CASE_P(
SSE2, Trans4x4HT,
::testing::Values(make_tuple(&vp10_fht4x4_sse2, &vp10_iht4x4_16_add_sse2, 0,
VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_sse2, &vp10_iht4x4_16_add_sse2, 1,
VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_sse2, &vp10_iht4x4_16_add_sse2, 2,
VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_sse2, &vp10_iht4x4_16_add_sse2, 3,
VPX_BITS_8, 16)));
#endif // HAVE_SSE2 && !CONFIG_VP9_HIGHBITDEPTH && !CONFIG_EMULATE_HARDWARE
#if HAVE_SSE2 && CONFIG_VP9_HIGHBITDEPTH && !CONFIG_EMULATE_HARDWARE
INSTANTIATE_TEST_CASE_P(
SSE2, Trans4x4DCT,
::testing::Values(
make_tuple(&vpx_highbd_fdct4x4_c, &idct4x4_10_sse2, 0, VPX_BITS_10, 16),
make_tuple(&vpx_highbd_fdct4x4_sse2, &idct4x4_10_sse2, 0, VPX_BITS_10,
16),
make_tuple(&vpx_highbd_fdct4x4_c, &idct4x4_12_sse2, 0, VPX_BITS_12, 16),
make_tuple(&vpx_highbd_fdct4x4_sse2, &idct4x4_12_sse2, 0, VPX_BITS_12,
16),
make_tuple(&vpx_fdct4x4_sse2, &vpx_idct4x4_16_add_c, 0, VPX_BITS_8,
16)));
INSTANTIATE_TEST_CASE_P(
SSE2, Trans4x4HT,
::testing::Values(
make_tuple(&vp10_fht4x4_sse2, &vp10_iht4x4_16_add_c, 0, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_sse2, &vp10_iht4x4_16_add_c, 1, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_sse2, &vp10_iht4x4_16_add_c, 2, VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_sse2, &vp10_iht4x4_16_add_c, 3, VPX_BITS_8,
16)));
#endif // HAVE_SSE2 && CONFIG_VP9_HIGHBITDEPTH && !CONFIG_EMULATE_HARDWARE
#if HAVE_MSA && !CONFIG_VP9_HIGHBITDEPTH && !CONFIG_EMULATE_HARDWARE
INSTANTIATE_TEST_CASE_P(MSA, Trans4x4DCT,
::testing::Values(make_tuple(&vpx_fdct4x4_msa,
&vpx_idct4x4_16_add_msa, 0,
VPX_BITS_8, 16)));
INSTANTIATE_TEST_CASE_P(
MSA, Trans4x4HT,
::testing::Values(make_tuple(&vp10_fht4x4_msa, &vp10_iht4x4_16_add_msa, 0,
VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_msa, &vp10_iht4x4_16_add_msa, 1,
VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_msa, &vp10_iht4x4_16_add_msa, 2,
VPX_BITS_8, 16),
make_tuple(&vp10_fht4x4_msa, &vp10_iht4x4_16_add_msa, 3,
VPX_BITS_8, 16)));
#endif // HAVE_MSA && !CONFIG_VP9_HIGHBITDEPTH && !CONFIG_EMULATE_HARDWARE
} // namespace