On Mon, Feb 7, 2011 at 3:32 AM, Stefan Dösinger <stefandoesin...@gmx.at> wrote: > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA1 > > > Am 07.02.2011 um 03:37 schrieb Misha Koshelev: >> + FLOAT full[10] = { 1.0f, -2.0f, 6.55e4, 6.10352e-5, 5.96046e-8, 0.0f, >> -0.0f, INFINITY, -INFINITY, NAN }, >> + full_exp[10] = { 1.0f, -2.0f, 6.55e4, 6.10352e-5, 5.96046e-8, 0.0f, >> -0.0f, 65536.0f, -131008.0f, 131008.0f }, >> + full_res[10]; > I'd rather call them "single" instead of full because 32 bit floats are > usually referred to as single precision(doubles are double precision, and 16 > bit floats half precision) Done.
> >> math.c:2238: Test failed: Got 7fff, expected 7c00 for index 7. > Looks like Windows doesn't do INF, and returns NaN instead. Your -INF value > test already expects NaN as return value, but with the sign bit set. INF or > -INF should have all mantissa bits set to 0. NaN looks like +/- INF, just > with mantissa != 0(so there are many possible encodings of NaN). > > However, it is also possible that Windows doesn't support those special > values at all. This is suggested by the fact that +/- NaN is happily > converted into a proper single precision value. Stefan: I believe this is actually a _difference_ between Windows versions. As you will note on the full results from winetestbot as well as my own testing on XP (what I _thought_ was SP3) is that only 3/9 platforms have this error. The rest pass fine. Thus, it seems a variance in the tests. Please see http://testbot.winehq.org/JobDetails.pl?Key=8981. I have attached a patch that passes all tests: https://testbot.winehq.org/JobDetails.pl?Key=8985 What do you think? If I am missing something please do let me know. Thank you Misha p.s. I heard down the grapevine that Henri might be on vacation for a week. If so, please wish him the best for me and I hope he enjoys his time. If I am mistaken, would be great to know. Thank you. > > -----BEGIN PGP SIGNATURE----- > Version: GnuPG/MacGPG2 v2.0.17 (Darwin) > > iQIcBAEBAgAGBQJNT64vAAoJEN0/YqbEcdMwHskP/2UvtNtsTuC6wL9skKbAhMxf > 9AyjSx+k8BOb2fQpkLrrR8gPC3feERax+MCrprPDgjSWftWKxWezfRDSAL9eR/+E > BQNRq0v+NfEITVCHVbMee3CNV+acWv2rXViz2HT03JCbuTe3htBytf8XPGPcrfUj > ls1KjNPVoYxH5cQJ4sVwAxbMR7CVI9F++B9LiLV8UzJkeYhztilKC3Qu+PLj1QFh > jXhfbwHMgCo4cunLIPTxZFndFcLvKwHVUSpZcFmY/OQBxWDAKqlo4fQKVw8Gonlb > Q0AbwKMbWQeOPq8Wlyb0XFV35qdUdDkAkJ0139SiyMCakgzmnebAmpx2Ur5/LNQl > t82jG+30Ajvnq43oXyczrmoueLtCdOqrXUiEl8wSpcQqFdC13N67NzzGNRvhBfNK > wJw25P9VZZCvpw5Wx3iqVXpk1Honrjmrn/hgLLHCKOA1Iv4mByp1svu263n4mfIq > Ga3gUdKzcv++1qr9eOfFfG7waGxrNZ8+X2q5Pp6f0SmeoX2nlhYjzOlCOdFDbFA1 > yEjHXFYkeZw9PD83c7fOkpLkrEcyDCEol9reDzzQXqmFKYoYP2JLLvRjjnPWoxk0 > LviYxmFQ1kZMBhR6WojGx1WjEPVEa+uQxmrK4n6H8fymsXVGu5TfbFgJvmrmg2hG > hRDKzYpNRuUYojjHKP6N > =EhgD > -----END PGP SIGNATURE----- >
From 4495cd387784a57b8671245d1960f884b36f9fd9 Mon Sep 17 00:00:00 2001 From: Misha Koshelev <misha...@gmail.com> Date: Mon, 7 Feb 2011 13:25:07 -0500 Subject: d3dx9: Implement D3DXFloat16to32Array and D3DXFloat32to16Array. To: wine-patches <wine-patc...@winehq.org> Reply-To: wine-devel <wine-devel@winehq.org> --- dlls/d3dx9_36/d3dx9_36.spec | 4 +- dlls/d3dx9_36/math.c | 90 +++++++++++++++++++++++++++++++++++++++++++ dlls/d3dx9_36/tests/math.c | 39 ++++++++++++++++++ include/d3dx9math.h | 18 +++++++++ include/d3dx9math.inl | 31 +++++++++++++++ 5 files changed, 180 insertions(+), 2 deletions(-) diff --git a/dlls/d3dx9_36/d3dx9_36.spec b/dlls/d3dx9_36/d3dx9_36.spec index cbb6d20..55fe0cb 100644 --- a/dlls/d3dx9_36/d3dx9_36.spec +++ b/dlls/d3dx9_36/d3dx9_36.spec @@ -130,8 +130,8 @@ @ stub D3DXFillVolumeTextureTX @ stdcall D3DXFilterTexture(ptr ptr long long) @ stdcall D3DXFindShaderComment(ptr long ptr ptr) -@ stub D3DXFloat16To32Array -@ stub D3DXFloat32To16Array +@ stdcall D3DXFloat16To32Array(ptr ptr long) +@ stdcall D3DXFloat32To16Array(ptr ptr long) @ stub D3DXFrameAppendChild @ stub D3DXFrameCalculateBoundingSphere @ stub D3DXFrameDestroy diff --git a/dlls/d3dx9_36/math.c b/dlls/d3dx9_36/math.c index fdb5f92..6d9b9b2 100644 --- a/dlls/d3dx9_36/math.c +++ b/dlls/d3dx9_36/math.c @@ -1769,3 +1769,93 @@ D3DXVECTOR4* WINAPI D3DXVec4TransformArray(D3DXVECTOR4* out, UINT outstride, CON } return out; } + +static inline unsigned short float_32_to_16(const float *in) +{ + int exp = 0; + float tmp = fabs(*in); + unsigned int mantissa; + unsigned short ret; + + /* Deal with special numbers */ + if (*((unsigned int *) in) == 0x00000000) return 0x0000; + if (*((unsigned int *) in) == 0x80000000) return 0x8000; + if (isnan(*in)) return 0x7FFF; + if (isinf(*in)) return (*in < 0.0f ? 0xFFFF : 0x7c00); + + if (tmp < powf(2, 10)) { + do + { + tmp = tmp * 2.0f; + exp--; + } while (tmp < powf(2, 10)); + } else if (tmp >= powf(2, 11)) { + do + { + tmp /= 2.0f; + exp++; + } while (tmp >= powf(2, 11)); + } + + mantissa = (unsigned int) tmp; + if (tmp - mantissa >= 0.5f) mantissa++; /* round to nearest, away from zero */ + + exp += 10; /* Normalize the mantissa */ + exp += 15; /* Exponent is encoded with excess 15 */ + + if (exp > 30) { /* too big */ + ret = 0x7c00; /* INF */ + } else if (exp <= 0) { + /* exp == 0: Non-normalized mantissa. Returns 0x0000 (=0.0) for too small numbers */ + while (exp <= 0) { + mantissa = mantissa >> 1; + exp++; + } + ret = mantissa & 0x3ff; + } else { + ret = (exp << 10) | (mantissa & 0x3ff); + } + + ret |= ((*in < 0.0f ? 1 : 0) << 15); /* Add the sign */ + return ret; +} + +D3DXFLOAT16 *WINAPI D3DXFloat32To16Array(D3DXFLOAT16 *pout, CONST FLOAT *pin, UINT n) +{ + unsigned int i; + + for (i = 0; i < n; ++i) { + pout[i].value = float_32_to_16(&pin[i]); + } + + return pout; +} + +static inline float float_16_to_32(const unsigned short *in) { + const unsigned short s = ((*in) & 0x8000); + const unsigned short e = ((*in) & 0x7C00) >> 10; + const unsigned short m = (*in) & 0x3FF; + const float sgn = (s ? -1.0f : 1.0f); + + if (e == 0) { + if (m == 0) return sgn * 0.0f; /* +0.0 or -0.0 */ + else return sgn * powf(2, -14.0f) * ((float)m / 1024.0f); + } else if (e < 31) { + return sgn * powf(2, (float)e - 15.0f) * (1.0f + ((float)m / 1024.0f)); + } else { + if (m == 0) return 65536.0f; + else if (s) return -131008.0f; + else return 131008.0f; + } +} + +FLOAT *WINAPI D3DXFloat16To32Array(FLOAT *pout, CONST D3DXFLOAT16 *pin, UINT n) +{ + unsigned int i; + + for (i = 0; i < n; ++i) { + pout[i] = float_16_to_32(&pin[i].value); + } + + return pout; +} diff --git a/dlls/d3dx9_36/tests/math.c b/dlls/d3dx9_36/tests/math.c index e455a96..4d86c2d 100644 --- a/dlls/d3dx9_36/tests/math.c +++ b/dlls/d3dx9_36/tests/math.c @@ -2216,6 +2216,44 @@ static void test_D3DXVec_Array(void) compare_planes(exp_plane, out_plane); } +#include <math.h> +static void test_D3DXFloat_Array(void) +{ + unsigned int i; + void *out = NULL; + D3DXFLOAT16 half_res[10]; + FLOAT single[10] = { 1.0f, -2.0f, 6.55e4, 6.10352e-5, 5.96046e-8, 0.0f, -0.0f, INFINITY, -INFINITY, NAN }, + single_exp[10] = { 1.0f, -2.0f, 6.55e4, 6.10352e-5, 5.96046e-8, 0.0f, -0.0f, 65536.0f, -131008.0f, 131008.0f }, + single_res[10]; + WORD half_ver1[10] = { 0x3c00, 0xc000, 0x7bff, 0x0400, 0x0001, 0x0000, 0x8000, 0x7c00, 0xffff, 0x7fff }; + WORD half_ver2[10] = { 0x3c00, 0xc000, 0x7bff, 0x0400, 0x0001, 0x0000, 0x8000, 0x7fff, 0xffff, 0x7fff }; + + /* exception on NULL out or in parameter */ + out = D3DXFloat32To16Array(half_res, single, 0); + ok(out == half_res, "Got %p, expected %p.\n", out, half_res); + + out = D3DXFloat32To16Array(half_res, single, 10); + ok(out == half_res, "Got %p, expected %p.\n", out, half_res); + + for (i = 0; i < 10; i++) { + ok(half_res[i].value == half_ver1[i] || + half_res[i].value == half_ver2[i], "Got %x, expected %x or %x for index %d.\n", + half_res[i].value, half_ver1[i], half_ver2[i], i); + } + + /* exception on NULL out or in parameter */ + out = D3DXFloat16To32Array(single_res, (D3DXFLOAT16 *)half_ver1, 0); + ok(out == single_res, "Got %p, expected %p.\n", out, single_res); + + out = D3DXFloat16To32Array(single_res, (D3DXFLOAT16 *)half_ver1, 10); + ok(out == single_res, "Got %p, expected %p.\n", out, single_res); + + for (i = 0; i < 10; i++) { + ok(relative_error(single_res[i], single_exp[i]) < admitted_error, "Got %f, expected %f for index %d.\n", + single_res[i], single_exp[i], i); + } +} + START_TEST(math) { D3DXColorTest(); @@ -2231,4 +2269,5 @@ START_TEST(math) test_Matrix_Decompose(); test_Matrix_Transformation2D(); test_D3DXVec_Array(); + test_D3DXFloat_Array(); } diff --git a/include/d3dx9math.h b/include/d3dx9math.h index f842e3e..cdb1deb 100644 --- a/include/d3dx9math.h +++ b/include/d3dx9math.h @@ -261,6 +261,21 @@ typedef struct D3DXCOLOR FLOAT r, g, b, a; } D3DXCOLOR, *LPD3DXCOLOR; +typedef struct D3DXFLOAT16 +{ +#ifdef __cplusplus + D3DXFLOAT16(); + D3DXFLOAT16(FLOAT f); + D3DXFLOAT16(CONST D3DXFLOAT16 &f); + + operator FLOAT (); + + BOOL operator == (CONST D3DXFLOAT16 &) const; + BOOL operator != (CONST D3DXFLOAT16 &) const; +#endif /* __cplusplus */ + WORD value; +} D3DXFLOAT16, *LPD3DXFLOAT16; + #ifdef __cplusplus extern "C" { #endif @@ -358,6 +373,9 @@ D3DXVECTOR4* WINAPI D3DXVec4Normalize(D3DXVECTOR4 *pout, CONST D3DXVECTOR4 *pv); D3DXVECTOR4* WINAPI D3DXVec4Transform(D3DXVECTOR4 *pout, CONST D3DXVECTOR4 *pv, CONST D3DXMATRIX *pm); D3DXVECTOR4* WINAPI D3DXVec4TransformArray(D3DXVECTOR4 *pout, UINT outstride, CONST D3DXVECTOR4 *pv, UINT vstride, CONST D3DXMATRIX *pm, UINT n); +D3DXFLOAT16 *WINAPI D3DXFloat32To16Array(D3DXFLOAT16 *pout, CONST FLOAT *pin, UINT n); +FLOAT *WINAPI D3DXFloat16To32Array(FLOAT *pout, CONST D3DXFLOAT16 *pin, UINT n); + #ifdef __cplusplus } #endif diff --git a/include/d3dx9math.inl b/include/d3dx9math.inl index 3cd078a..3f55aef 100644 --- a/include/d3dx9math.inl +++ b/include/d3dx9math.inl @@ -851,6 +851,37 @@ inline BOOL D3DXCOLOR::operator != (CONST D3DXCOLOR& col) const return r != col.r || g != col.g || b != col.b || a != col.a; } +inline D3DXFLOAT16::D3DXFLOAT16() +{ +} + +inline D3DXFLOAT16::D3DXFLOAT16(FLOAT f) +{ + D3DXFloat32To16Array(this, &f, 1); +} + +inline D3DXFLOAT16::D3DXFLOAT16(CONST D3DXFLOAT16 &f) +{ + value = f.value; +} + +inline D3DXFLOAT16::operator FLOAT () +{ + FLOAT f; + D3DXFloat16To32Array(&f, this, 1); + return f; +} + +inline BOOL D3DXFLOAT16::operator == (CONST D3DXFLOAT16 &f) const +{ + return value == f.value; +} + +inline BOOL D3DXFLOAT16::operator != (CONST D3DXFLOAT16 &f) const +{ + return value != f.value; +} + #endif /* __cplusplus */ /*_______________D3DXCOLOR_____________________*/ -- 1.7.4