65e376a721
Otherwise a smaller type may be promoted to int, which can hit undefined
behaviour:
../src/gallium/auxiliary/util/u_half.h:126:29: runtime error: left shift of 32768 by 16 places cannot be represented in type 'int'
#0 0x5646ff63d488 in util_half_to_float ../src/gallium/auxiliary/util/u_half.h:126
#1 0x5646ff63d749 in _mesa_half_to_float ../src/util/half_float.c:145
#2 0x5646ff54d557 in nir_const_value_negative_equal ../src/compiler/nir/nir_instr_set.c:372
#3 0x5646ff44d29a in const_value_negative_equal_test_nir_type_float16_trivially_true_Test::TestBody() ../src/compiler/nir/tests/negative_equal_tests.cpp:121
#4 0x5646ff505c05 in void testing::internal::HandleSehExceptionsInMethodIfSupported<testing::Test, void>(testing::Test*, void (testing::Test::*)(), char const*) ../src/gtest/src/gtest.cc:2402
#5 0x5646ff4f1513 in void testing::internal::HandleExceptionsInMethodIfSupported<testing::Test, void>(testing::Test*, void (testing::Test::*)(), char const*) ../src/gtest/src/gtest.cc:2438
#6 0x5646ff4979b5 in testing::Test::Run() ../src/gtest/src/gtest.cc:2474
#7 0x5646ff49a08e in testing::TestInfo::Run() ../src/gtest/src/gtest.cc:2656
#8 0x5646ff49c81c in testing::TestCase::Run() ../src/gtest/src/gtest.cc:2774
#9 0x5646ff4b81f6 in testing::internal::UnitTestImpl::RunAllTests() ../src/gtest/src/gtest.cc:4649
#10 0x5646ff50981e in bool testing::internal::HandleSehExceptionsInMethodIfSupported<testing::internal::UnitTestImpl, bool>(testing::internal::UnitTestImpl*, bool (testing::internal::UnitTestImpl::*)(), char const*) ../src/gtest/src/gtest.cc:2402
#11 0x5646ff4f4eeb in bool testing::internal::HandleExceptionsInMethodIfSupported<testing::internal::UnitTestImpl, bool>(testing::internal::UnitTestImpl*, bool (testing::internal::UnitTestImpl::*)(), char const*) ../src/gtest/src/gtest.cc:2438
#12 0x5646ff4af818 in testing::UnitTest::Run() ../src/gtest/src/gtest.cc:4257
#13 0x5646ff52e639 in RUN_ALL_TESTS() ../src/gtest/include/gtest/gtest.h:2233
#14 0x5646ff52e4f9 in main ../src/gtest/src/gtest_main.cc:37
#15 0x7f6bacb78bba in __libc_start_main ../csu/libc-start.c:308
#16 0x5646ff448019 in _start (/home/daenzer/src/mesa-git/mesa/build-amd64-sanitize/src/compiler/nir/negative_equal+0x17c019)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Adam Jackson <ajax@redhat.com>
137 lines
3.6 KiB
C
137 lines
3.6 KiB
C
/**************************************************************************
|
|
*
|
|
* Copyright 2010 Luca Barbieri
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person obtaining
|
|
* a copy of this software and associated documentation files (the
|
|
* "Software"), to deal in the Software without restriction, including
|
|
* without limitation the rights to use, copy, modify, merge, publish,
|
|
* distribute, sublicense, and/or sell copies of the Software, and to
|
|
* permit persons to whom the Software is furnished to do so, subject to
|
|
* the following conditions:
|
|
*
|
|
* The above copyright notice and this permission notice (including the
|
|
* next paragraph) shall be included in all copies or substantial
|
|
* portions of the Software.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
|
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
|
* IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE
|
|
* LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
|
* OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
|
* WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
|
*
|
|
**************************************************************************/
|
|
|
|
|
|
#ifndef U_HALF_H
|
|
#define U_HALF_H
|
|
|
|
#include "pipe/p_compiler.h"
|
|
#include "util/u_math.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
/*
|
|
* References for float <-> half conversions
|
|
*
|
|
* http://fgiesen.wordpress.com/2012/03/28/half-to-float-done-quic/
|
|
* https://gist.github.com/2156668
|
|
* https://gist.github.com/2144712
|
|
*/
|
|
|
|
static inline uint16_t
|
|
util_float_to_half(float f)
|
|
{
|
|
uint32_t sign_mask = 0x80000000;
|
|
uint32_t round_mask = ~0xfff;
|
|
uint32_t f32inf = 0xff << 23;
|
|
uint32_t f16inf = 0x1f << 23;
|
|
uint32_t sign;
|
|
union fi magic;
|
|
union fi f32;
|
|
uint16_t f16;
|
|
|
|
magic.ui = 0xf << 23;
|
|
|
|
f32.f = f;
|
|
|
|
/* Sign */
|
|
sign = f32.ui & sign_mask;
|
|
f32.ui ^= sign;
|
|
|
|
if (f32.ui == f32inf) {
|
|
/* Inf */
|
|
f16 = 0x7c00;
|
|
} else if (f32.ui > f32inf) {
|
|
/* NaN */
|
|
f16 = 0x7e00;
|
|
} else {
|
|
/* Number */
|
|
f32.ui &= round_mask;
|
|
f32.f *= magic.f;
|
|
f32.ui -= round_mask;
|
|
/*
|
|
* XXX: The magic mul relies on denorms being available, otherwise
|
|
* all f16 denorms get flushed to zero - hence when this is used
|
|
* for tgsi_exec in softpipe we won't get f16 denorms.
|
|
*/
|
|
/*
|
|
* Clamp to max finite value if overflowed.
|
|
* OpenGL has completely undefined rounding behavior for float to
|
|
* half-float conversions, and this matches what is mandated for float
|
|
* to fp11/fp10, which recommend round-to-nearest-finite too.
|
|
* (d3d10 is deeply unhappy about flushing such values to infinity, and
|
|
* while it also mandates round-to-zero it doesn't care nearly as much
|
|
* about that.)
|
|
*/
|
|
if (f32.ui > f16inf)
|
|
f32.ui = f16inf - 1;
|
|
|
|
f16 = f32.ui >> 13;
|
|
}
|
|
|
|
/* Sign */
|
|
f16 |= sign >> 16;
|
|
|
|
return f16;
|
|
}
|
|
|
|
static inline float
|
|
util_half_to_float(uint16_t f16)
|
|
{
|
|
union fi infnan;
|
|
union fi magic;
|
|
union fi f32;
|
|
|
|
infnan.ui = 0x8f << 23;
|
|
infnan.f = 65536.0f;
|
|
magic.ui = 0xef << 23;
|
|
|
|
/* Exponent / Mantissa */
|
|
f32.ui = (f16 & 0x7fff) << 13;
|
|
|
|
/* Adjust */
|
|
f32.f *= magic.f;
|
|
/* XXX: The magic mul relies on denorms being available */
|
|
|
|
/* Inf / NaN */
|
|
if (f32.f >= infnan.f)
|
|
f32.ui |= 0xff << 23;
|
|
|
|
/* Sign */
|
|
f32.ui |= (uint32_t)(f16 & 0x8000) << 16;
|
|
|
|
return f32.f;
|
|
}
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* U_HALF_H */
|
|
|