mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2025-06-28 07:23:30 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

core: remove raw SSE2/NEON implementation from convert.cpp (#9831)

Browse Source 
* remove raw SSE2/NEON implementation from convert.cpp
  * remove raw implementation from Cvt_SIMD
  * remove raw implementation from cvtScale_SIMD
  * remove raw implementation from cvtScaleAbs_SIMD
  * remove duplicated implementation cvt_<float, short>
  * remove duplicated implementation cvtScale_<short, short, float>
  * add "from double" version of Cvt_SIMD
  * modify the condition of test ConvertScaleAbs

* Update convert.cpp

fixed crash in cvtScaleAbs(8s=>8u)

* fixed compile error on Win32

* fixed several test failures because of accuracy loss in cvtScale(int=>int)

* fixed NEON implementation of v_cvt_f64(int=>double) intrinsic

* another attempt to fix test failures

* keep trying to fix the test failures and just introduced compile warnings

* fixed one remaining test (subtractScalar)
This commit is contained in:
Tomoaki Teshima 2017-12-15 06:00:35 +09:00 committed by Vadim Pisarevsky
parent 6cedc82799
commit ca1a0a1108
3 changed files with 1374 additions and 2422 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
modules/core/perf/perf_arithm.cpp
View File

@ -80,16 +80,18 @@ PERF_TEST_P(Size_MatType, absdiff, TYPICAL_MATS_CORE_ARITHM)
declare.in(a, b, WARMUP_RNG).out(c);
double eps = 1e-8;
if (CV_MAT_DEPTH(type) == CV_32S)
{
//see ticket 1529: absdiff can be without saturation on 32S
a /= 2;
b /= 2;
eps = 1;
}
TEST_CYCLE() absdiff(a, b, c);
SANITY_CHECK(c, 1e-8);
SANITY_CHECK(c, eps);
}
PERF_TEST_P(Size_MatType, absdiffScalar, TYPICAL_MATS_CORE_ARITHM)
@ -102,16 +104,18 @@ PERF_TEST_P(Size_MatType, absdiffScalar, TYPICAL_MATS_CORE_ARITHM)
declare.in(a, b, WARMUP_RNG).out(c);
double eps = 1e-8;
if (CV_MAT_DEPTH(type) == CV_32S)
{
//see ticket 1529: absdiff can be without saturation on 32S
a /= 2;
b /= 2;
eps = 1;
}
TEST_CYCLE() absdiff(a, b, c);
SANITY_CHECK(c, 1e-8);
SANITY_CHECK(c, eps);
}
PERF_TEST_P(Size_MatType, add, TYPICAL_MATS_CORE_ARITHM)
@ -125,16 +129,18 @@ PERF_TEST_P(Size_MatType, add, TYPICAL_MATS_CORE_ARITHM)
declare.in(a, b, WARMUP_RNG).out(c);
declare.time(50);
double eps = 1e-8;
if (CV_MAT_DEPTH(type) == CV_32S)
{
//see ticket 1529: add can be without saturation on 32S
a /= 2;
b /= 2;
eps = 1;
}
TEST_CYCLE() add(a, b, c);
SANITY_CHECK(c, 1e-8);
SANITY_CHECK(c, eps);
}
PERF_TEST_P(Size_MatType, addScalar, TYPICAL_MATS_CORE_ARITHM)
@ -147,16 +153,18 @@ PERF_TEST_P(Size_MatType, addScalar, TYPICAL_MATS_CORE_ARITHM)
declare.in(a, b, WARMUP_RNG).out(c);
double eps = 1e-8;
if (CV_MAT_DEPTH(type) == CV_32S)
{
//see ticket 1529: add can be without saturation on 32S
a /= 2;
b /= 2;
eps = 1;
}
TEST_CYCLE() add(a, b, c);
SANITY_CHECK(c, 1e-8);
SANITY_CHECK(c, eps);
}
PERF_TEST_P(Size_MatType, subtract, TYPICAL_MATS_CORE_ARITHM)
@ -169,16 +177,18 @@ PERF_TEST_P(Size_MatType, subtract, TYPICAL_MATS_CORE_ARITHM)
declare.in(a, b, WARMUP_RNG).out(c);
double eps = 1e-8;
if (CV_MAT_DEPTH(type) == CV_32S)
{
//see ticket 1529: subtract can be without saturation on 32S
a /= 2;
b /= 2;
eps = 1;
}
TEST_CYCLE() subtract(a, b, c);
SANITY_CHECK(c, 1e-8);
SANITY_CHECK(c, eps);
}
PERF_TEST_P(Size_MatType, subtractScalar, TYPICAL_MATS_CORE_ARITHM)
@ -191,16 +201,18 @@ PERF_TEST_P(Size_MatType, subtractScalar, TYPICAL_MATS_CORE_ARITHM)
declare.in(a, b, WARMUP_RNG).out(c);
double eps = 1e-8;
if (CV_MAT_DEPTH(type) == CV_32S)
{
//see ticket 1529: subtract can be without saturation on 32S
a /= 2;
b /= 2;
eps = 1;
}
TEST_CYCLE() subtract(a, b, c);
SANITY_CHECK(c, 1e-8);
SANITY_CHECK(c, eps);
}
PERF_TEST_P(Size_MatType, multiply, TYPICAL_MATS_CORE_ARITHM)

3767
modules/core/src/convert.cpp
View File

File diff suppressed because it is too large Load Diff

5
modules/core/test/test_arithm.cpp
View File

@ -806,6 +806,11 @@ struct ConvertScaleAbsOp : public BaseElemWiseOp
{
cvtest::add(src[0], alpha, Mat(), 0, Scalar::all(gamma[0]), dst, CV_8UC(src[0].channels()), true);
}
int getRandomType(RNG& rng)
{
return cvtest::randomType(rng, _OutputArray::DEPTH_MASK_ALL, 1,
ninputs > 1 ? ARITHM_MAX_CHANNELS : 4);
}
double getMaxErr(int)
{
return 1;