caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
a78861fc55d18046989ff4d624a037e9181da170
clang-p2996/libclc/generic/lib/math
History
Romaric Jodin 7e6a73959a libclc: increase fp16 support (#98149) 
Increase fp16 support to allow clspv to continue to be OpenCL compliant
following the update of the OpenCL-CTS adding more testing on math
functions and conversions with half.

Math functions are implemented by upscaling to fp32 and using the fp32
implementation. It garantees the accuracy required for half-precision
float-point by the CTS.
2024-07-18 12:00:41 +01:00
..
acos.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
acosh.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
acospi.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
asin.cl
libclc/asin: Switch to amd builtins version of asin
2020-02-04 14:29:20 -05:00
asinh.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
asinpi.cl
Implement asinpi builtin
2015-04-02 17:01:56 +00:00
atan2.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
atan2pi.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
atan.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
atanh.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
atanpi.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
binary_impl.inc
Protect functions taking double by #ifdef cl_khr_fp64
2014-06-23 14:15:39 +00:00
cbrt.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
ceil.cl
Move unary_instrinsic.inc to private headers.
2019-03-13 07:06:19 +00:00
clc_exp10.cl
exp10: Port from amd builtins
2018-04-17 18:08:08 +00:00
clc_fma.cl
math/fma: Add fp32 software implementation
2018-06-07 20:27:43 +00:00
clc_fmod.cl
fmod: Port from amd_builtins
2018-04-06 17:43:08 +00:00
clc_hypot.cl
hypot: Port from amd builtins
2018-04-10 00:11:58 +00:00
clc_ldexp.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
clc_nextafter.cl
…
clc_pow.cl
…
clc_pown.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
clc_powr.cl
…
clc_remainder.cl
…
clc_remquo.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
clc_rootn.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
clc_sqrt_impl.inc
Add initial support for half precision builtins
2018-05-17 22:55:30 +00:00
clc_sqrt.cl
Move unary_instrinsic.inc to private headers.
2019-03-13 07:06:19 +00:00
clc_sw_binary.inc
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
clc_sw_unary.inc
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
clc_tan.cl
tan: Port from amd_builtins
2018-01-19 18:57:19 +00:00
clc_tanpi.cl
…
copysign.cl
Add initial support for half precision builtins
2018-05-17 22:55:30 +00:00
cos.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
cosh.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
cospi.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
ep_log.cl
Implement asinh builtin
2015-04-02 17:01:54 +00:00
ep_log.h
…
erf.cl
libclc: generic: add half implementation for erf/erfc (#66901)
2024-01-09 16:47:53 +00:00
erfc.cl
libclc: generic: add half implementation for erf/erfc (#66901)
2024-01-09 16:47:53 +00:00
exp2.cl
Implement exp2 using OpenCL C rather than using an intrinsic
2015-05-13 03:55:07 +00:00
exp10.cl
exp10: Port from amd builtins
2018-04-17 18:08:08 +00:00
exp_helper.cl
Implement exp2 using OpenCL C rather than using an intrinsic
2015-05-13 03:55:07 +00:00
exp_helper.h
Implement exp2 using OpenCL C rather than using an intrinsic
2015-05-13 03:55:07 +00:00
exp.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
expm1.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
fabs.cl
Move unary_instrinsic.inc to private headers.
2019-03-13 07:06:19 +00:00
fdim.cl
Move cl_khr_fp64 exntension enablement to gentype include lists
2018-03-06 17:48:35 +00:00
fdim.inc
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
floor.cl
Move unary_instrinsic.inc to private headers.
2019-03-13 07:06:19 +00:00
fma.cl
math/fma: Add fp32 software implementation
2018-06-07 20:27:43 +00:00
fma.inc
math/fma: Add fp32 software implementation
2018-06-07 20:27:43 +00:00
fmax.cl
Add initial support for half precision builtins
2018-05-17 22:55:30 +00:00
fmax.inc
Add initial support for half precision builtins
2018-05-17 22:55:30 +00:00
fmin.cl
Add initial support for half precision builtins
2018-05-17 22:55:30 +00:00
fmin.inc
Add initial support for half precision builtins
2018-05-17 22:55:30 +00:00
fmod.cl
fmod: Port from amd_builtins
2018-04-06 17:43:08 +00:00
fract.cl
Move cl_khr_fp64 exntension enablement to gentype include lists
2018-03-06 17:48:35 +00:00
fract.inc
Add initial support for half precision builtins
2018-05-17 22:55:30 +00:00
frexp.cl
frexp: Reuse types provided by gentype.inc
2018-03-06 17:48:45 +00:00
frexp.inc
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
half_binary.inc
half_divide: Implement using x/y
2018-01-18 21:12:06 +00:00
half_cos.cl
half_cos: Implement using cos
2018-01-18 21:11:40 +00:00
half_divide.cl
half_divide: Implement using x/y
2018-01-18 21:12:06 +00:00
half_exp2.cl
half_exp2: Implement using exp2
2018-01-18 21:11:45 +00:00
half_exp10.cl
half_exp10: Implement using exp10
2018-01-18 21:11:48 +00:00
half_exp.cl
half_exp: Implement using exp
2018-01-18 21:11:43 +00:00
half_log2.cl
half_log2: Implement using log2
2018-01-18 21:11:56 +00:00
half_log10.cl
half_log10: Implement using log10
2018-01-18 21:11:53 +00:00
half_log.cl
half_log: Implement using log
2018-01-18 21:11:50 +00:00
half_powr.cl
…
half_recip.cl
half_recip: Implement using 1/x
2018-01-18 21:11:58 +00:00
half_rsqrt.cl
…
half_sin.cl
half_sin: Implement using sin
2018-01-18 21:12:01 +00:00
half_sqrt.cl
half_sqrt: Cleanup implementation
2018-01-18 21:11:38 +00:00
half_tan.cl
half_tan: Implement using tan
2018-01-18 21:12:04 +00:00
half_unary.inc
half_rsqrt: Cleanup implementation
2018-01-18 21:11:35 +00:00
hypot.cl
hypot: Port from amd builtins
2018-04-10 00:11:58 +00:00
ilogb.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
ldexp.cl
Add initial support for half precision builtins
2018-05-17 22:55:30 +00:00
ldexp.inc
Add initial support for half precision builtins
2018-05-17 22:55:30 +00:00
lgamma_r.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
lgamma_r.inc
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
lgamma.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
log1p.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
log2.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
log10.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
log_base.h
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
log.cl
Fix double implementation of log
2015-07-24 18:07:14 +00:00
logb.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
mad.cl
Move cl_khr_fp64 exntension enablement to gentype include lists
2018-03-06 17:48:35 +00:00
mad.inc
Add __CLC_ prefix to all macro definitions in headers
2013-07-08 17:27:02 +00:00
math.h
libclc: Add a __builtin to let SPIRV targets select between SW and HW FMA
2020-09-16 01:37:22 -04:00
maxmag.cl
maxmag: Condition variable needs to be the same bitwidth as operands
2018-03-06 17:48:38 +00:00
maxmag.inc
maxmag: Condition variable needs to be the same bitwidth as operands
2018-03-06 17:48:38 +00:00
minmag.cl
minmag: Condition variable needs to be the same bitwidth as operands
2018-03-06 17:48:40 +00:00
minmag.inc
…
modf.cl
Move cl_khr_fp64 exntension enablement to gentype include lists
2018-03-06 17:48:35 +00:00
modf.inc
Add initial support for half precision builtins
2018-05-17 22:55:30 +00:00
nan.cl
nan: Implement
2018-03-12 19:46:52 +00:00
nan.inc
Add initial support for half precision builtins
2018-05-17 22:55:30 +00:00
native_cos.cl
native_cos: Switch implementation to llvm intrinsic
2017-11-10 22:16:33 +00:00
native_divide.cl
native_divide: provide function implementation instead of macro
2017-11-13 18:28:56 +00:00
native_divide.inc
native_divide: provide function implementation instead of macro
2017-11-13 18:28:56 +00:00
native_exp2.cl
native_exp2: Switch implementation to llvm intrinsic
2017-11-10 22:16:31 +00:00
native_exp10.cl
native_exp10: Switch implementation to llvm intrinsic
2017-11-10 22:16:41 +00:00
native_exp10.inc
math: Use precomputed constant for log2(10.0)
2017-11-13 18:28:45 +00:00
native_exp.cl
native_exp: Switch implementation to llvm intrinsic
2017-11-10 22:16:28 +00:00
native_log2.cl
native_log2: Switch to generic native intrinsic inc file
2017-11-10 22:16:15 +00:00
native_log10.cl
native_log10: Switch to generic native intrinsic inc file
2017-11-10 22:16:22 +00:00
native_log.cl
native_log: Switch to generic native intrinsic inc file
2017-11-10 22:16:20 +00:00
native_powr.cl
native_powr: Switch implementation to native_exp2 and native_log2
2017-11-14 21:55:41 +00:00
native_powr.inc
…
native_recip.cl
native_recip: provide function implementation instead of macro
2017-11-13 18:28:53 +00:00
native_recip.inc
native_recip: provide function implementation instead of macro
2017-11-13 18:28:53 +00:00
native_rsqrt.cl
native_rsqrt: Switch implementation to 1 / native_sqrt
2017-11-13 18:28:51 +00:00
native_rsqrt.inc
native_rsqrt: Switch implementation to 1 / native_sqrt
2017-11-13 18:28:51 +00:00
native_sin.cl
native_sin: Switch implementation to llvm intrinsic
2017-11-10 22:16:36 +00:00
native_sqrt.cl
native_sqrt: Switch implementation to llvm intrinsic
2017-11-10 22:16:39 +00:00
native_tan.cl
native_tan: Switch implementation to use native_sin/native_cos
2017-11-13 18:28:48 +00:00
native_tan.inc
native_tan: Switch implementation to use native_sin/native_cos
2017-11-13 18:28:48 +00:00
native_unary_intrinsic.inc
…
nextafter.cl
Move clcmacro.h to avoid cluttering user namespace v2
2014-06-24 09:36:32 +00:00
pow.cl
pow: Port from amd_builtins
2018-01-17 21:21:35 +00:00
pown.cl
pown: Port from amd_builtins
2018-01-17 21:22:03 +00:00
pown.inc
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
powr.cl
powr: Port from amd_builtins
2018-01-17 21:22:06 +00:00
remainder.cl
remainder: Port from amd builtins
2018-03-19 01:01:10 +00:00
remquo.cl
…
remquo.inc
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
rint.cl
Move unary_instrinsic.inc to private headers.
2019-03-13 07:06:19 +00:00
rootn.cl
rootn: Port from amd_builtins
2018-01-17 21:22:14 +00:00
rootn.inc
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
round.cl
Move unary_instrinsic.inc to private headers.
2019-03-13 07:06:19 +00:00
rsqrt.cl
libclc: Move rsqrt implementation to a .cl file
2020-02-09 14:42:09 -05:00
sin.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
sincos_helpers.cl
…
sincos_helpers.h
…
sincos.cl
Move cl_khr_fp64 exntension enablement to gentype include lists
2018-03-06 17:48:35 +00:00
sincos.inc
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
sincosD_piby4.h
…
sincospiF_piby4.h
…
sinh.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
sinpi.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
sqrt.cl
sqrt: Split function generation to a shared inc file.
2019-03-13 07:05:56 +00:00
tables.cl
log10: Use sw implementation from amd builtins
2018-04-23 21:10:42 +00:00
tables.h
log10: Use sw implementation from amd builtins
2018-04-23 21:10:42 +00:00
tan.cl
tan: Port from amd_builtins
2018-01-19 18:57:19 +00:00
tanh.cl
libclc: increase fp16 support (#98149)
2024-07-18 12:00:41 +01:00
tanpi.cl
tanpi: Port from amd_builtins
2018-01-19 18:57:22 +00:00
tgamma.cl
…
trunc.cl
Move unary_instrinsic.inc to private headers.
2019-03-13 07:06:19 +00:00
unary_builtin.inc
…