575fb84cc3
OpenCL 1.1 does not define CL_VERSION_1_2 so use hardcoded number instead
...
Otherwise the test evaluates to true on OpenCL 1.1 and earlier. Since we
therefore cannot use the CL_VERSION_?_? macros move them to the proper
position in the top-level header.
llvm-svn: 211787
2014-06-26 15:26:38 +00:00
d7f158e006
relational: Fix signbit
...
The vector components were mistakenly using () instead of {}, which caused
all but the last vector component to be dropped on the floor.
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Jeroen Ketema <j.ketema@imperial.ac.uk>
llvm-svn: 211733
2014-06-25 21:08:38 +00:00
d9ee196eab
relational: Implement signbit
...
v2 Changes:
- use __builtin_signbit instead of shifting by hand
- significantly improve vector shuffling
- Works correctly now for signbit(float16) on radeonsi
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 211696
2014-06-25 13:29:23 +00:00
42df5d2a8f
Add exp10
...
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211680
2014-06-25 10:06:35 +00:00
dd1fbc0082
Add half limits
...
These are apparently only defined in OpenCL 1.2.
HALF_MAX, HALF_MIN and HALF_EPSILON are currently omitted. Clang does
not seem to support the ‘h’ suffix for half float constants even with
the cl_khr_fp16 extension enabled.
Reviewed-by: Tom Sellard <tom@stellard.net>
llvm-svn: 211579
2014-06-24 09:51:01 +00:00
046b47fbbe
Introduce CLC_VERSION macros v2
...
Add these out-of-order in clc.h so we can use these in other headers.
v2: Take into account the lack of a definition in OpenCL 1.0
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211578
2014-06-24 09:46:52 +00:00
985a1381b2
Add MAXFLOAT
...
Align definitions while we are here.
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211577
2014-06-24 09:41:28 +00:00
526fe2d501
Move clcmacro.h to avoid cluttering user namespace v2
...
v2: - use quotes instead of <>
- add include to r600/lib/math/nextafter.c changed
Reviewed-by: Tom Stellard <tom@stellard.net>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 211576
2014-06-24 09:36:32 +00:00
bfdb1c0c2f
Protect functions taking double by #ifdef cl_khr_fp64
...
Also change the order of the functions to be consistent with
the order in the header files.
llvm-svn: 211496
2014-06-23 14:15:39 +00:00
d253e66ec7
Fix breakage after r211259
...
While we are here introduce the proper headers for the error code.
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211432
2014-06-21 09:20:31 +00:00
09516fa27d
Add pown
...
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211211
2014-06-18 19:42:23 +00:00
fdee0d3efe
Add missing undefs
...
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211210
2014-06-18 19:37:34 +00:00
d9afe9def0
Fix definition of INFINITY and add NAN/HUGE_VAL[F]
...
v3: change __builtin_nanf() to __builtin_nanf("")
This doesn't work yet, but it was agreed to commit as-is with the logic
that "broken" is better than "completely missing" and this should be
fixed in clang.
v2: use __builtin_inff() and also add nan/huge_val definitions
Signed-off-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 211065
2014-06-16 22:32:58 +00:00
f3bd08ae63
Add remaining float constants
...
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 211062
2014-06-16 22:15:50 +00:00
50f518be65
Revert "clctypes.h: Don't rely on stddef.h for size_t and ptrdiff_t"
...
This reverts commit 4cf021ae67b6ea8cfd42aa76ce6f5e1c329e145a.
llvm-svn: 211049
2014-06-16 20:21:19 +00:00
6af2969a61
math: Implement mix builtin
...
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211047
2014-06-16 19:53:59 +00:00
f7f79d2a94
relational: Add isequal(floatN) builtin
...
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211046
2014-06-16 19:53:57 +00:00
e167db9238
Add all(igentype) builtin
...
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211045
2014-06-16 19:53:54 +00:00
c164fc384b
clctypes.h: Don't rely on stddef.h for size_t and ptrdiff_t
...
llvm-svn: 211044
2014-06-16 19:53:52 +00:00
bd37b6884c
Add intptr types
...
Based on clang's stdint.h
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 210933
2014-06-13 19:43:18 +00:00
e2a0f050d8
Add files forgotten in the previous commit
...
llvm-svn: 210896
2014-06-13 12:33:40 +00:00
82aaa41286
Implementations for exp(float) and exp(double) v2
...
Use separate implementations instead of a macro
to ensure the constant multiplied with is of
higher precision.
v2: Use the correct formula, spotted by Dan Liew <daniel.liew@imperial.ac.uk>
Reviewed-by: Aaron Warty <awatry@gmail.com>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 210891
2014-06-13 09:40:09 +00:00
0ab103422d
prepare-builtins: Use std:: prefix for error_code
...
This fixes the build with with newer LLVM.
llvm-svn: 210867
2014-06-13 01:30:14 +00:00
a3089bd7e5
Remove unused include which breaks build after r210803
...
Tested with llvm 3.4 and trunk.
llvm-svn: 210825
2014-06-12 21:10:17 +00:00
f3943efe17
Fix build broken by LLVM commit r209103
...
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 210111
2014-06-03 15:43:57 +00:00
75c1a0c6e2
Add more log related float constants
...
llvm-svn: 209850
2014-05-29 21:30:28 +00:00
d1bb82a722
Fix _F definitions
...
The 'f' was missing and, hence, the values were
considered to be doubles instead of floats.
Reviewed by: Tom Stellard
llvm-svn: 209849
2014-05-29 21:29:34 +00:00
a16fdbfac2
Add definition for M_PI
...
Reviewed by: Tom Stellard
llvm-svn: 209848
2014-05-29 21:24:57 +00:00
98dccb109b
Fix build broken by LLVM commit r207593
...
llvm-svn: 207685
2014-04-30 18:35:20 +00:00
998602dac2
Remove clc/gentype.inc
...
This file duplicates clc/math/gentype.inc and is not
actually being used.
Patch by: Jeroen Ketema
llvm-svn: 207684
2014-04-30 18:35:17 +00:00
f83fe5a6dc
Introduce M_LOG2E_F and M_LOG2E
...
Patch by: Jeroen Ketema
llvm-svn: 205055
2014-03-28 21:19:03 +00:00
ce43db105e
Replace tabs by spaces
...
Patch by: Jeroen Ketema
llvm-svn: 205054
2014-03-28 21:19:00 +00:00
6378f7a5e2
Add definition for M_PI_F v3
...
v2:
- Use a hexadecimal constant.
v3:
- Use a hexadecimal constant in floating-point notation.
llvm-svn: 204666
2014-03-24 20:36:44 +00:00
3a12fc6a07
Add sincos
...
Patch by: Jeroen Ketema
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 204478
2014-03-21 16:22:01 +00:00
074e7a8ed0
Add cross for double3 and double4
...
Patch by: Jeroen Ketema
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 204477
2014-03-21 16:21:58 +00:00
7aee1cfa99
Fix build since r202052
...
sys::fs_F_Binary has been replaced with sys::fs_F_Text
llvm-svn: 202081
2014-02-24 21:31:56 +00:00
d873c8e05a
Add generic nvptx targets
...
These do not import the code specific to nvidiacl
Patch by: Jeroen Ketema
llvm-svn: 201431
2014-02-14 20:33:53 +00:00
55d3746dbe
Revert "Enforce python2 for systems that use python3 as their default."
...
This reverts commit r200413.
This was breaking the build on systems where the python 2.x executable
was called python.
llvm-svn: 201239
2014-02-12 14:54:17 +00:00
0d35ed912a
Updated README.TXT with information about using DESTDIR and building with Ninja.
...
Patch by: Dan Liew
llvm-svn: 200416
2014-01-29 20:03:28 +00:00
8a3770ab97
Fixed rules names so they are unique when aliases are present.
...
This is necessary for building with Ninja because it does not allow
duplicate rule names.
Patch by: Dan Liew
llvm-svn: 200415
2014-01-29 20:03:27 +00:00
91d51db800
Fixed ninja build issues relating to use of $(DESTDIR)
...
We use ${DESTDIR} syntax now instead of $(DESTDIR) because that syntax
works both is the shell (at least it does for bash) and for make (at
least it does for GNU Make)
Patch By: Dan Liew
llvm-svn: 200414
2014-01-29 20:03:26 +00:00
ac0fb621ce
Enforce python2 for systems that use python3 as their default.
...
Patch by: Dan Liew
llvm-svn: 200413
2014-01-29 20:03:24 +00:00
8a63b15b3c
Fix build broken by LLVM commit r199279
...
Patch by: Udo van den Heuvel
Tom Stellard:
- Added ifdef and error handling
llvm-svn: 199687
2014-01-20 20:28:48 +00:00
d40d387fb1
Update the copyright credits -- Happy new year 2014!
...
FIXME: Dragonegg may be updated at non-trivial changes.
llvm-svn: 198274
2014-01-01 08:27:31 +00:00
8ef48d07ef
Pass -fno-builtin flag to clang to silence warnings
...
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 198168
2013-12-29 16:39:55 +00:00
b38037f7b7
Fix build with LLVM 3.5
...
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 198167
2013-12-29 16:39:53 +00:00
ce0709aa61
Add floating-point macro definitions v2
...
v2:
- Fix typo.
Reviewed-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 197784
2013-12-20 05:13:42 +00:00
1f3c9ba9f1
Implement trunc builtin.
...
OpenCL C lang says that trunc rounds towards zero.
llvm.trunc.* intrinsic rounds to integer not larger in magnitude.
These definitions are equivalent.
Patch by: Jan Vesely
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 197769
2013-12-20 02:08:46 +00:00
8bb6cb8009
Fix a C&P error in r195021 (65a950abab3cb8435ccb2646ac4773986c995c81)
...
Patch by: Kai Wasserbäch
Signed-off-by: Kai Wasserbäch <kai@dev.carbon-project.org>
llvm-svn: 195898
2013-11-28 00:17:29 +00:00
eedd3064de
R600: Add aliases for Sea Islands GPUs
...
llvm-svn: 195023
2013-11-18 18:21:30 +00:00
Jeroen Ketema