Author: jvesely
Date: Thu Nov 2 12:48:53 2017
New Revision: 317256
URL: http://llvm.org/viewvc/llvm-project?rev=317256&view=rev
Log:
sinpi: Use unary_decl instead of custom inc file
Signed-off-by: Jan Vesely
Reviewed-By: Aaron Watry
Removed:
libclc/trunk/generic/include/clc/math/sinpi.inc
Author: jvesely
Date: Thu Nov 2 12:48:55 2017
New Revision: 317257
URL: http://llvm.org/viewvc/llvm-project?rev=317257&view=rev
Log:
sqrt: Use unary_decl instead of custom inc file
Signed-off-by: Jan Vesely
Reviewed-By: Aaron Watry
Removed:
libclc/trunk/generic/include/clc/math/sqrt.inc
M
Author: jvesely
Date: Thu Nov 2 12:49:00 2017
New Revision: 317260
URL: http://llvm.org/viewvc/llvm-project?rev=317260&view=rev
Log:
tgamma: Use unary_decl instead of custom inc file
Signed-off-by: Jan Vesely
Reviewed-By: Aaron Watry
Removed:
libclc/trunk/generic/include/clc/math/tgamma.i
Author: jvesely
Date: Thu Nov 2 12:48:58 2017
New Revision: 317259
URL: http://llvm.org/viewvc/llvm-project?rev=317259&view=rev
Log:
tanh: Use unary_decl instead of custom inc file
Signed-off-by: Jan Vesely
Reviewed-By: Aaron Watry
Removed:
libclc/trunk/generic/include/clc/math/tanh.inc
M
Author: jvesely
Date: Fri Nov 10 14:16:15 2017
New Revision: 317932
URL: http://llvm.org/viewvc/llvm-project?rev=317932&view=rev
Log:
native_log2: Switch to generic native intrinsic inc file
v2: Add __CLC_XCONCAT instead of function name redirection
Use __CLC_XCONCAT for intrinsic functions a
Author: jvesely
Date: Fri Nov 10 14:16:20 2017
New Revision: 317933
URL: http://llvm.org/viewvc/llvm-project?rev=317933&view=rev
Log:
native_log: Switch to generic native intrinsic inc file
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Removed:
libclc/trunk/generic/lib/math/native_log.i
Author: jvesely
Date: Fri Nov 10 14:16:22 2017
New Revision: 317934
URL: http://llvm.org/viewvc/llvm-project?rev=317934&view=rev
Log:
native_log10: Switch to generic native intrinsic inc file
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Removed:
libclc/trunk/generic/lib/math/native_log
Author: jvesely
Date: Fri Nov 10 14:16:25 2017
New Revision: 317935
URL: http://llvm.org/viewvc/llvm-project?rev=317935&view=rev
Log:
amdgpu: Add workaround for unimplemented llvm.exp intrinsic
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/amdgpu/lib/math/native_exp.
Author: jvesely
Date: Fri Nov 10 14:16:31 2017
New Revision: 317937
URL: http://llvm.org/viewvc/llvm-project?rev=317937&view=rev
Log:
native_exp2: Switch implementation to llvm intrinsic
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/lib/math/native_exp2.cl
Mo
Author: jvesely
Date: Fri Nov 10 14:16:33 2017
New Revision: 317938
URL: http://llvm.org/viewvc/llvm-project?rev=317938&view=rev
Log:
native_cos: Switch implementation to llvm intrinsic
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/lib/math/native_cos.cl
Modi
Author: jvesely
Date: Fri Nov 10 14:16:36 2017
New Revision: 317939
URL: http://llvm.org/viewvc/llvm-project?rev=317939&view=rev
Log:
native_sin: Switch implementation to llvm intrinsic
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/lib/math/native_sin.cl
Modi
Author: jvesely
Date: Fri Nov 10 14:16:28 2017
New Revision: 317936
URL: http://llvm.org/viewvc/llvm-project?rev=317936&view=rev
Log:
native_exp: Switch implementation to llvm intrinsic
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/lib/math/native_exp.cl
Modi
Author: jvesely
Date: Fri Nov 10 14:16:39 2017
New Revision: 317940
URL: http://llvm.org/viewvc/llvm-project?rev=317940&view=rev
Log:
native_sqrt: Switch implementation to llvm intrinsic
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/lib/math/native_sqrt.cl
Mo
Author: jvesely
Date: Fri Nov 10 14:16:41 2017
New Revision: 317941
URL: http://llvm.org/viewvc/llvm-project?rev=317941&view=rev
Log:
native_exp10: Switch implementation to llvm intrinsic
v2: Use native_log2 instead of wrong constant
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
Author: jvesely
Date: Mon Nov 13 10:28:48 2017
New Revision: 318064
URL: http://llvm.org/viewvc/llvm-project?rev=318064&view=rev
Log:
native_tan: Switch implementation to use native_sin/native_cos
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/lib/math/native_
Author: jvesely
Date: Mon Nov 13 10:28:45 2017
New Revision: 318063
URL: http://llvm.org/viewvc/llvm-project?rev=318063&view=rev
Log:
math: Use precomputed constant for log2(10.0)
exp10 CTS fails with or without this change
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Modified:
libclc
Author: jvesely
Date: Mon Nov 13 10:28:51 2017
New Revision: 318065
URL: http://llvm.org/viewvc/llvm-project?rev=318065&view=rev
Log:
native_rsqrt: Switch implementation to 1 / native_sqrt
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/lib/math/native_rsqrt.cl
Author: jvesely
Date: Mon Nov 13 10:28:53 2017
New Revision: 318066
URL: http://llvm.org/viewvc/llvm-project?rev=318066&view=rev
Log:
native_recip: provide function implementation instead of macro
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/lib/math/native_
Author: jvesely
Date: Mon Nov 13 10:28:56 2017
New Revision: 318067
URL: http://llvm.org/viewvc/llvm-project?rev=318067&view=rev
Log:
native_divide: provide function implementation instead of macro
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/include/clc/mat
Author: jvesely
Date: Tue Nov 14 13:55:41 2017
New Revision: 318204
URL: http://llvm.org/viewvc/llvm-project?rev=318204&view=rev
Log:
native_powr: Switch implementation to native_exp2 and native_log2
v2: don't use assume
check only for x<0, the other conditions are handled transparently
v3: d
Author: jvesely
Date: Tue Nov 14 20:10:39 2017
New Revision: 318265
URL: http://llvm.org/viewvc/llvm-project?rev=318265&view=rev
Log:
math: Implement minmag
Reviewer: Aaron Watry
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/include/clc/math/minmag.h
libclc/trunk/generic/lib/mat
Author: jvesely
Date: Tue Nov 14 20:10:37 2017
New Revision: 318264
URL: http://llvm.org/viewvc/llvm-project?rev=318264&view=rev
Log:
math: Implement maxmag
Reviewer: Aaron Watry
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/include/clc/math/maxmag.h
libclc/trunk/generic/lib/mat
Author: jvesely
Date: Wed Aug 17 15:02:11 2016
New Revision: 278962
URL: http://llvm.org/viewvc/llvm-project?rev=278962&view=rev
Log:
Implement vstore_half{,n}
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/lib/shared/vstore_half.inc
Modified:
libclc/trunk/generic/include/clc/sha
jvesely added a subscriber: jvesely.
jvesely added a comment.
This change breaks OpenCL(libclc). CLC expects signed/unsigned overloads to be
non-ambiguous.
For example:
atomic_max(global int *p, int val);
atomic_max(global unsigned int *p, unsigned int val);
need to work and be unambiguous (they
jvesely added a comment.
In https://reviews.llvm.org/D24113#535255, @george.burgess.iv wrote:
> Thanks for the heads-up!
>
> I'm assuming that below is an example of code that this patch broke?
>
> void foo(int *a, int) __attribute__((overloadable));
> void foo(unsigned int *a, unsigned int)
Author: jvesely
Date: Wed Sep 7 17:11:02 2016
New Revision: 280871
URL: http://llvm.org/viewvc/llvm-project?rev=280871&view=rev
Log:
Avoid ambiguity in calling atom_add functions.
clang (since r280553) allows pointer casts in function overloads,
so we need to disambiguate the second argument.
c
Author: jvesely
Date: Thu Jul 27 20:39:03 2017
New Revision: 309358
URL: http://llvm.org/viewvc/llvm-project?rev=309358&view=rev
Log:
add __kernel_exec macros
also consolidate macros into one file, and rename to clcmacros.h
Signed-off-by: Jan Vesely
Reviewed-by: Aaron Watry
Added:
libclc/
Author: jvesely
Date: Wed Jan 17 13:21:35 2018
New Revision: 322760
URL: http://llvm.org/viewvc/llvm-project?rev=322760&view=rev
Log:
pow: Port from amd_builtins
Passes piglit on turks and carrizo
fp64 passes CTS on carrizo
v2: fix formatting
check fp32 denormal support at runtime
Reviewer:
Author: jvesely
Date: Wed Jan 17 13:22:03 2018
New Revision: 322761
URL: http://llvm.org/viewvc/llvm-project?rev=322761&view=rev
Log:
pown: Port from amd_builtins
Passes piglit on turks and carrizo
fp64 passes CTS on carrizo
v2: fix formatting
check fp32 denormal support at runtime
Reviewer
Author: jvesely
Date: Wed Jan 17 13:22:06 2018
New Revision: 322762
URL: http://llvm.org/viewvc/llvm-project?rev=322762&view=rev
Log:
powr: Port from amd_builtins
Passes piglit on turks and carrizo
fp64 passes cts on carrizo
v2: fix formatting
check fp32 denormal support at runtime
Reviewer
Author: jvesely
Date: Wed Jan 17 13:22:14 2018
New Revision: 322763
URL: http://llvm.org/viewvc/llvm-project?rev=322763&view=rev
Log:
rootn: Port from amd_builtins
Passes piglit on turks and carrizo
fp64 passes ctx on carrizo
v2: fix formatting
check fp32 denormal support at runtime
Reviewe
Author: jvesely
Date: Thu Jan 18 13:11:38 2018
New Revision: 322888
URL: http://llvm.org/viewvc/llvm-project?rev=322888&view=rev
Log:
half_sqrt: Cleanup implementation
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Removed:
li
Author: jvesely
Date: Thu Jan 18 13:11:35 2018
New Revision: 322887
URL: http://llvm.org/viewvc/llvm-project?rev=322887&view=rev
Log:
half_rsqrt: Cleanup implementation
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
lib
Author: jvesely
Date: Thu Jan 18 13:11:40 2018
New Revision: 322889
URL: http://llvm.org/viewvc/llvm-project?rev=322889&view=rev
Log:
half_cos: Implement using cos
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/t
Author: jvesely
Date: Thu Jan 18 13:11:45 2018
New Revision: 322891
URL: http://llvm.org/viewvc/llvm-project?rev=322891&view=rev
Log:
half_exp2: Implement using exp2
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc
Author: jvesely
Date: Thu Jan 18 13:11:48 2018
New Revision: 322892
URL: http://llvm.org/viewvc/llvm-project?rev=322892&view=rev
Log:
half_exp10: Implement using exp10
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libc
Author: jvesely
Date: Thu Jan 18 13:11:43 2018
New Revision: 322890
URL: http://llvm.org/viewvc/llvm-project?rev=322890&view=rev
Log:
half_exp: Implement using exp
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/t
Author: jvesely
Date: Thu Jan 18 13:11:56 2018
New Revision: 322895
URL: http://llvm.org/viewvc/llvm-project?rev=322895&view=rev
Log:
half_log2: Implement using log2
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc
Author: jvesely
Date: Thu Jan 18 13:11:58 2018
New Revision: 322896
URL: http://llvm.org/viewvc/llvm-project?rev=322896&view=rev
Log:
half_recip: Implement using 1/x
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc
Author: jvesely
Date: Thu Jan 18 13:11:53 2018
New Revision: 322894
URL: http://llvm.org/viewvc/llvm-project?rev=322894&view=rev
Log:
half_log10: Implement using log10
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libc
Author: jvesely
Date: Thu Jan 18 13:11:50 2018
New Revision: 322893
URL: http://llvm.org/viewvc/llvm-project?rev=322893&view=rev
Log:
half_log: Implement using log
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/t
Author: jvesely
Date: Thu Jan 18 13:12:04 2018
New Revision: 322898
URL: http://llvm.org/viewvc/llvm-project?rev=322898&view=rev
Log:
half_tan: Implement using tan
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/include/c
Author: jvesely
Date: Thu Jan 18 13:12:06 2018
New Revision: 322899
URL: http://llvm.org/viewvc/llvm-project?rev=322899&view=rev
Log:
half_divide: Implement using x/y
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libcl
Author: jvesely
Date: Thu Jan 18 13:12:01 2018
New Revision: 322897
URL: http://llvm.org/viewvc/llvm-project?rev=322897&view=rev
Log:
half_sin: Implement using sin
Passes CTS on carrizo
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/t
Author: jvesely
Date: Fri Jan 19 10:57:19 2018
New Revision: 322979
URL: http://llvm.org/viewvc/llvm-project?rev=322979&view=rev
Log:
tan: Port from amd_builtins
v2: fixup constant precision
Passes piglit on turks and carrizo.
Passes CTS on carrizo
Fixes half_tan to pass CTS on carrizo
Acked-By:
Author: jvesely
Date: Fri Jan 19 10:57:22 2018
New Revision: 322980
URL: http://llvm.org/viewvc/llvm-project?rev=322980&view=rev
Log:
tanpi: Port from amd_builtins
Passes piglit on turks and carrizo.
Passes CTS on carrizo.
Acked-By: Aaron Watry
Tested-By: Aaron Watry
Signed-off-by: Jan Vesely
Author: jvesely
Date: Mon Jan 29 11:05:08 2018
New Revision: 323677
URL: http://llvm.org/viewvc/llvm-project?rev=323677&view=rev
Log:
math.h: Set HAVE_HW_FMA32 based on compiler provided macro
Fixes sin/cos piglits on non-FMA capable asics.
Bugzilla: https://bugs.llvm.org/show_bug.cgi?id=35983
R
On Mon, 2018-01-29 at 22:15 +0300, Roman Lebedev via cfe-commits wrote:
> On Mon, Jan 29, 2018 at 10:05 PM, Jan Vesely via cfe-commits
> wrote:
> > Author: jvesely
> > Date: Mon Jan 29 11:05:08 2018
> > New Revision: 323677
> >
> > URL: http://llvm.org/vie
Author: jvesely
Date: Wed Jan 31 13:53:42 2018
New Revision: 323920
URL: http://llvm.org/viewvc/llvm-project?rev=323920&view=rev
Log:
math.h: Use logical operations instead of bit operations for readability
Trivial.
Reported-by: Roman Lebedev
Signed-off-by: Jan Vesely
Modified:
libclc/tru
Author: jvesely
Date: Wed Jan 31 19:00:35 2018
New Revision: 323942
URL: http://llvm.org/viewvc/llvm-project?rev=323942&view=rev
Log:
half_powr: Implement using powr
v2: Use full precision implementation
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely
Added:
libclc/trunk/generic/include
Author: jvesely
Date: Wed Feb 22 09:01:42 2017
New Revision: 295843
URL: http://llvm.org/viewvc/llvm-project?rev=295843&view=rev
Log:
[OpenCL] r600 needs OpenCL kernel calling convention
Differential Revision: https://reviews.llvm.org/D30236
Modified:
cfe/trunk/lib/Sema/SemaType.cpp
cfe/
Hi Hans,
I'd like this commit to make it to 4.0. I'm not sure if it falls under
OpenCL or AMDGPU so I've added both Matt and Anastasia to cc.
thank you,
Jan
On Wed, 2017-02-22 at 15:01 +0000, Jan Vesely via cfe-commits wrote:
> Author: jvesely
> Date: Wed Feb 22 09:01:4
Author: jvesely
Date: Fri Feb 24 14:32:18 2017
New Revision: 296164
URL: http://llvm.org/viewvc/llvm-project?rev=296164&view=rev
Log:
.gitignore: Ignore amdgcn-mesa object directory
Modified:
libclc/trunk/.gitignore
Modified: libclc/trunk/.gitignore
URL:
http://llvm.org/viewvc/llvm-project/
Author: jvesely
Date: Fri Feb 24 20:46:53 2017
New Revision: 296233
URL: http://llvm.org/viewvc/llvm-project?rev=296233&view=rev
Log:
math: Implement sinh function
mostly copied form amd_builtins
Added:
libclc/trunk/generic/include/clc/math/sinh.h
libclc/trunk/generic/include/clc/math/si
Author: jvesely
Date: Fri Feb 24 22:20:20 2017
New Revision: 296239
URL: http://llvm.org/viewvc/llvm-project?rev=296239&view=rev
Log:
AMDGPU: export s_waitcnt builtin
Differential Revision: https://reviews.llvm.org/D30359
Modified:
cfe/trunk/include/clang/Basic/BuiltinsAMDGPU.def
cfe/tru
Author: jvesely
Date: Fri Feb 24 22:20:22 2017
New Revision: 296240
URL: http://llvm.org/viewvc/llvm-project?rev=296240&view=rev
Log:
AMDGPU: export l1 cache invalidation intrinsics
Differential Revision: https://reviews.llvm.org/D30360
Modified:
cfe/trunk/include/clang/Basic/BuiltinsAMDGPU.
Author: jvesely
Date: Fri Feb 24 22:20:24 2017
New Revision: 296241
URL: http://llvm.org/viewvc/llvm-project?rev=296241&view=rev
Log:
AMDGPU: export s_sendmsg{halt} instrinsics
Differential Revision: https://reviews.llvm.org/D30366
Modified:
cfe/trunk/include/clang/Basic/BuiltinsAMDGPU.def
Hi,
I think this change breaks cmake build. Please consider the attached fix (I
can't push atm).
thank you,
Jan
On Wed, Sep 30, 2015 at 8:59 AM, Daniel Jasper via cfe-commits <
cfe-commits@lists.llvm.org> wrote:
> Author: djasper
> Date: Wed Sep 30 08:59:29 2015
> New Revision: 248904
>
> URL: h
This change breaks cmake build:
undefined reference to `clang::DiagnosticIDs::DiagnosticIDs()'
/home/jvesely/llvm/tools/clang/unittests/Driver/ToolChainTest.cpp:33:
undefined reference to
`clang::DiagnosticsEngine::DiagnosticsEngine(llvm::IntrusiveRefCntPtr
const&, clang::DiagnosticOptions*, clang:
Author: jvesely
Date: Fri Jul 22 10:00:08 2016
New Revision: 276423
URL: http://llvm.org/viewvc/llvm-project?rev=276423&view=rev
Log:
ptx: Fix builtin names after clang r274770
Signed-off-by: Jan Vesely
Acked-By: Aaron Watry
Modified:
libclc/trunk/ptx-nvidiacl/lib/synchronization/barrier.c
Author: jvesely
Date: Fri Jul 22 12:24:20 2016
New Revision: 276442
URL: http://llvm.org/viewvc/llvm-project?rev=276442&view=rev
Log:
AMDGPU: Use clang intrinsics for workitem builtins
v2: split into 2 patches
use clang builtins for other intrinsics as well
v3: Fix warnings
Switch r600 t
Author: jvesely
Date: Fri Jul 22 12:24:24 2016
New Revision: 276443
URL: http://llvm.org/viewvc/llvm-project?rev=276443&view=rev
Log:
AMDGPU: Implement get_global_offset builtin
Also fix get_global_id to consider offset
No idea how to add this for ptx, so they are stuck with the old get_global_id
Author: jvesely
Date: Mon Jul 25 17:36:22 2016
New Revision: 276704
URL: http://llvm.org/viewvc/llvm-project?rev=276704&view=rev
Log:
Make min follow the OCL 1.0 specs
OpenCL 1.0: "Returns y if y < x, otherwise it returns x. If x *and* y
are infinite or NaN, the return values are undefined."
Ope
Author: jvesely
Date: Tue Feb 9 16:17:42 2016
New Revision: 260301
URL: http://llvm.org/viewvc/llvm-project?rev=260301&view=rev
Log:
math: Fix log2 vectorization on non-fp64 hw
reviewer: tstellard
Signed-off-by: Jan Vesely
Modified:
libclc/trunk/generic/lib/math/log2.cl
Modified: libclc/t
Author: jvesely
Date: Tue Feb 9 16:17:46 2016
New Revision: 260303
URL: http://llvm.org/viewvc/llvm-project?rev=260303&view=rev
Log:
configure: Remove cl_khr_fp64 for device that don't support doubles
Also remove definitions if provided by clang (3.7+)
This halves the size of builtin.opt.{cedar,
Author: jvesely
Date: Tue Feb 9 16:17:45 2016
New Revision: 260302
URL: http://llvm.org/viewvc/llvm-project?rev=260302&view=rev
Log:
configure: Introduce per device defines
Make cl_khr_fp64 define per-device.
This patch does not change the generated Makefile (for llvm 3.6, 3.7)
v2: Make the dev
Author: jvesely
Date: Tue Feb 9 16:17:48 2016
New Revision: 260304
URL: http://llvm.org/viewvc/llvm-project?rev=260304&view=rev
Log:
configure: Remove llvm 3.6 defines
we require llvm 3.7
reviewer: tstellard
Signed-off-by: Jan Vesely
Modified:
libclc/trunk/configure.py
Modified: libclc/t
Author: jvesely
Date: Fri May 6 13:02:30 2016
New Revision: 268766
URL: http://llvm.org/viewvc/llvm-project?rev=268766&view=rev
Log:
math: Add erf ported from amd-builtins
The scalar float/double function bodies are a direct copy/paste,
aside from the removed (optional) code in float function bo
Author: jvesely
Date: Tue May 17 14:44:01 2016
New Revision: 269807
URL: http://llvm.org/viewvc/llvm-project?rev=269807&view=rev
Log:
math: Use single precision fmax in sp path
Fixes fdim piglit on Turks
v2: use CL fmax instead of __builtin
Signed-off-by: Jan Vesely
Reviewed-by: Tom Stellard
jvesely retitled this revision from "[OpenCL] cl_khr_msaa_sharing is OpenCL1.2
extension" to "[OpenCL] Fixup extension list".
jvesely added a subscriber: cfe-commits.
jvesely updated this revision to Diff 58130.
jvesely added a comment.
I went through the specs and fixed up all I could find.
adde
jvesely added inline comments.
Comment at: test/SemaOpenCL/extension-version.cl:11
@@ +10,3 @@
+#endif
+#pragma OPENCL EXTENSION cl_clang_storage_class_specifiers: enable
+
Anastasia wrote:
> Could you use standard diagnostic check please:
> expected-warning{{un
jvesely added inline comments.
Comment at: test/SemaOpenCL/extension-version.cl:11
@@ +10,3 @@
+#endif
+#pragma OPENCL EXTENSION cl_clang_storage_class_specifiers: enable
+
Anastasia wrote:
> jvesely wrote:
> > Anastasia wrote:
> > > Could you use standard diagnos
jvesely updated this revision to Diff 58806.
jvesely added a comment.
add detection of extensions in early CL versions to test.
Repository:
rL LLVM
http://reviews.llvm.org/D20447
Files:
include/clang/Basic/OpenCLExtensions.def
test/SemaOpenCL/extension-version.cl
Index: test/SemaOpenCL/
jvesely created this revision.
jvesely added reviewers: Anastasia, yaxunl.
jvesely added subscribers: cfe-commits, arsenm.
jvesely set the repository for this revision to rL LLVM.
Repository:
rL LLVM
http://reviews.llvm.org/D20744
Files:
include/clang/Basic/DiagnosticParseKinds.td
test/Sem
jvesely marked 7 inline comments as done.
Comment at: test/SemaOpenCL/extension-version.cl:12
@@ +11,3 @@
+#ifndef cl_clang_storage_class_specifiers
+#error "Missing cl_clang_storage_class_specifiers define"
+#endif
arsenm wrote:
> When the AMD compiler added thes
jvesely updated the summary for this revision.
jvesely added a subscriber: cfe-commits.
jvesely updated this revision to Diff 58849.
jvesely added a comment.
Report only clinfo exported extensions.
Repository:
rL LLVM
http://reviews.llvm.org/D20389
Files:
lib/Basic/Targets.cpp
test/Misc/
jvesely marked an inline comment as done.
jvesely added a comment.
Repository:
rL LLVM
http://reviews.llvm.org/D20388
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
jvesely updated the summary for this revision.
jvesely added a subscriber: cfe-commits.
jvesely updated this revision to Diff 58850.
jvesely marked an inline comment as done.
jvesely added a comment.
report only exported extensions.
int64 atomics, fp16, and 3d image writes are actually not curren
jvesely added inline comments.
Comment at: test/Misc/r600.languageOptsOpenCL.cl:4
@@ +3,3 @@
+// RUN: %clang_cc1 -x cl -cl-std=CL %s -verify -triple r600-unknown-unknown
-target-cpu cypress
+// RUN: %clang_cc1 -x cl -cl-std=CL %s -verify -triple r600-unknown-unknown
-target-cpu
jvesely updated this revision to Diff 59079.
jvesely added a comment.
fixup additional tests that checked for the warning
Repository:
rL LLVM
http://reviews.llvm.org/D20744
Files:
include/clang/Basic/DiagnosticParseKinds.td
test/Parser/opencl-atomics-cl20.cl
test/SemaOpenCL/extension-v
jvesely updated the summary for this revision.
jvesely updated this revision to Diff 59080.
jvesely added a comment.
add has_fp64 macro
Repository:
rL LLVM
http://reviews.llvm.org/D20388
Files:
lib/Basic/Targets.cpp
test/Misc/amdgcn.languageOptsOpenCL.cl
test/Misc/r600.languageOptsOpen
jvesely marked 2 inline comments as done.
jvesely added a comment.
Repository:
rL LLVM
http://reviews.llvm.org/D20388
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
jvesely added inline comments.
Comment at: lib/Basic/Targets.cpp:2024-2025
@@ -2023,2 +2023,4 @@
Builder.defineMacro("__HAS_LDEXPF__");
+if (hasFP64)
+ Builder.defineMacro("__HAS_FP64__");
}
arsenm wrote:
> I don't think we need this. I want dev
jvesely marked 2 inline comments as done.
Comment at: test/SemaOpenCL/extension-version.cl:73
@@ +72,3 @@
+
+#endif
+
Anastasia wrote:
> Could you put a comment to make it more readable, something like
>
> #endif // (__OPENCL_C_VERSION__ < 110)
These large block
jvesely updated this revision to Diff 59240.
jvesely added a comment.
Fix typo: COre -> Core
Repository:
rL LLVM
http://reviews.llvm.org/D20447
Files:
include/clang/Basic/OpenCLExtensions.def
test/SemaOpenCL/extension-version.cl
Index: test/SemaOpenCL/extension-version.cl
==
This revision was automatically updated to reflect the committed changes.
jvesely marked 5 inline comments as done.
Closed by commit rL271413: Fixup list of available extensions (authored by
jvesely).
Changed prior to commit:
http://reviews.llvm.org/D20447?vs=59240&id=59254#toc
Repository:
r
This revision was automatically updated to reflect the committed changes.
Closed by commit rL271414: Disable warning about core features by default
(authored by jvesely).
Changed prior to commit:
http://reviews.llvm.org/D20744?vs=59079&id=59255#toc
Repository:
rL LLVM
http://reviews.llvm.or
Author: jvesely
Date: Wed Jun 1 13:04:53 2016
New Revision: 271414
URL: http://llvm.org/viewvc/llvm-project?rev=271414&view=rev
Log:
Disable warning about core features by default
Reviewers: Anastasia, yaxunl
Differential Revision: http://reviews.llvm.org/D20744
Modified:
cfe/trunk/include
Author: jvesely
Date: Wed Jun 1 13:04:50 2016
New Revision: 271413
URL: http://llvm.org/viewvc/llvm-project?rev=271413&view=rev
Log:
Fixup list of available extensions
Reviewers: Anastasia
Differential Revision: http://reviews.llvm.org/D20447
Added:
cfe/trunk/test/SemaOpenCL/extension-vers
jvesely added inline comments.
Comment at: test/Misc/nvptx.languageOptsOpenCL.cl:1
@@ +1,2 @@
+// REQUIRES: nvptx-registered-target
+// RUN: %clang_cc1 -x cl -cl-std=CL %s -verify -triple nvptx-unknown-unknown
Anastasia wrote:
> Should we check for errors on unsup
d to OpenCL. :)
>
> Thanks,
> Anastasia
>
> -Original Message-
> From: cfe-commits [mailto:cfe-commits-boun...@lists.llvm.org] On
> Behalf Of Jan Vesely via cfe-commits
> Sent: 01 June 2016 19:05
> To: cfe-commits@lists.llvm.org
> Subject: r271413 - Fixup list of ava
jvesely updated this revision to Diff 60226.
jvesely added a comment.
Test all known extensions against expected nvptx outcome (add negative tests)
Repository:
rL LLVM
http://reviews.llvm.org/D20389
Files:
lib/Basic/Targets.cpp
test/Misc/nvptx.languageOptsOpenCL.cl
Index: test/Misc/nvpt
jvesely marked 2 inline comments as done.
jvesely added a comment.
Repository:
rL LLVM
http://reviews.llvm.org/D20389
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
jvesely updated this revision to Diff 60257.
jvesely added a comment.
add back require registered target
Repository:
rL LLVM
http://reviews.llvm.org/D20389
Files:
lib/Basic/Targets.cpp
test/Misc/nvptx.languageOptsOpenCL.cl
Index: test/Misc/nvptx.languageOptsOpenCL.cl
===
jvesely updated this revision to Diff 60259.
jvesely added a comment.
tests all extensions against expected outcome (add negative tests)
enable cl_khr_icd (works ok with mesa)
Repository:
rL LLVM
http://reviews.llvm.org/D20388
Files:
lib/Basic/Targets.cpp
test/Misc/amdgcn.languageOptsOpe
jvesely marked an inline comment as done.
jvesely added a comment.
Repository:
rL LLVM
http://reviews.llvm.org/D20388
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
jvesely added a comment.
ping
@jholewinski, is the exported list of features OK with you?
@Anastasia, are the tests OK now?
Repository:
rL LLVM
http://reviews.llvm.org/D20389
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.
jvesely added a comment.
ping
Repository:
rL LLVM
http://reviews.llvm.org/D20388
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
This revision was automatically updated to reflect the committed changes.
Closed by commit rL272986: AMDGPU: Fix supported CL features (authored by
jvesely).
Changed prior to commit:
http://reviews.llvm.org/D20388?vs=60259&id=61060#toc
Repository:
rL LLVM
http://reviews.llvm.org/D20388
Fil
Author: jvesely
Date: Thu Jun 16 21:25:03 2016
New Revision: 272986
URL: http://llvm.org/viewvc/llvm-project?rev=272986&view=rev
Log:
AMDGPU: Fix supported CL features
Reviewers: arsenm
Differential Revision: http://reviews.llvm.org/D20388
Added:
cfe/trunk/test/Misc/amdgcn.languageOptsOpenC
201 - 300 of 311 matches
Mail list logo
