| Commit message (Collapse) | Author | Age | Files | Lines |
... | |
|
|
|
|
|
| |
This has been tested with piglit, OpenCV, and the ocl conformance tests.
llvm-svn: 230970
|
|
|
|
|
|
|
|
|
| |
This has been tested with piglit, OpenCV, and the ocl conformance tests.
v2:
- Fix typo in smoothstep.h
llvm-svn: 230969
|
|
|
|
|
|
|
|
|
| |
This has been tested with piglit, OpenCV, and the ocl conformance tests.
v2:
- Move to the common/ directory
llvm-svn: 230968
|
|
|
|
|
|
|
|
|
| |
This has been tested with piglit, OpenCV, and the ocl conformance tests.
v2:
- Move to the common/ directory
llvm-svn: 230967
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Ported from the libclc/amd-builtins branch
v2: Rename sincos_f_piby4 to __libclc__sincosf_piby4
Add cospi(double) implementation instead of using llvm.cos
Notes:
The sincosD_piby4.h file is mostly the same as the builtin implementation
released by AMD. The inline attribute declaration is changed, and M_PI is
used instead of a constant double. Otherwise, the only difference is that
the header explicitly enables the fp64 pragma.
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Jeroen Ketema <j.ketema@imperial.ac.uk>
CC: Tom Stellard <tom@stellard.net>
CC: Matt Arsenault <Matthew.Arsenault@amd.com>
llvm-svn: 230641
|
|
|
|
|
|
|
|
| |
v2: Use constant and multiplication instead of division
v3: Use hex constants
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 227585
|
|
|
|
| |
llvm-svn: 219230
|
|
|
|
|
|
|
| |
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Tom Stellard <tom@stellard.net>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 219087
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This is a simple implementation which just copies data synchronously.
v2:
- Use size_t.
v3:
- Fix possible race condition by splitting the copy among multiple
work items.
llvm-svn: 219008
|
|
|
|
|
|
|
|
|
| |
This is a simple implementation which just copies data synchronously.
v2:
- Use size_t.
llvm-svn: 219007
|
|
|
|
|
|
|
|
|
| |
This is a simple default implemetation which just calls barrier().
v2:
- Only call barrier() once.
llvm-svn: 219006
|
|
|
|
|
|
| |
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 217918
|
|
|
|
|
|
| |
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 217917
|
|
|
|
|
|
| |
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 217916
|
|
|
|
|
|
| |
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 217915
|
|
|
|
|
|
| |
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 217914
|
|
|
|
|
|
|
|
| |
Not used yet.
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 217913
|
|
|
|
|
|
|
|
|
|
| |
Not used yet...
v2: Correct int/uint behavior
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 217912
|
|
|
|
|
|
|
|
| |
We were missing the local versions of the atom_* before
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 217911
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Uses the algorithm:
tan(x) = sin(x) / sqrt(1-sin^2(x))
An alternative is:
tan(x) = sin(x) / cos(x)
Which produces more verbose bitcode and longer assembly.
Either way, the generated bitcode seems pretty nasty and a more optimized
but still precise-enough solution is welcome.
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 217511
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
asin(x) = atan2(x, sqrt( 1-x^2 ))
alternatively:
asin(x) = PI/2 - acos(x)
Use the atan2 implementation since it produces slightly shorter bitcode and
R600 machine code.
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 217510
|
|
|
|
|
|
|
|
|
|
| |
Passes the tests that were submitted to the piglit list
Tested on R600 (Pitcairn)
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 217509
|
|
|
|
|
|
| |
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 217247
|
|
|
|
|
|
|
|
| |
v2: remove trailing newline
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 217246
|
|
|
|
|
|
|
|
| |
v2: remove trailing newline
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 217245
|
|
|
|
|
|
|
|
|
| |
v2: simplify and remove isnan leftovers
remove trailing newline
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 217244
|
|
|
|
|
|
|
|
|
| |
v2: simplify and remove isinf leftovers
remove trailing newline
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 217243
|
|
|
|
| |
llvm-svn: 217046
|
|
|
|
|
|
|
|
|
| |
This was previously implemented with a macro and we were using
__builtin_copysign(), which takes double inputs for the float
version of copysign().
Reviewed-and-Tested-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 217045
|
|
|
|
|
|
|
|
|
|
|
|
| |
v2: Fix trailing whitespace
Fix signed long overflow
improve comment
v3: fix typo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 216923
|
|
|
|
|
|
|
|
| |
This reverts commit cf62eded8b623a1c10d3692d25e5882b7939f564.
I didn't mean to commit this... Jan has a v3 incoming
llvm-svn: 216322
|
|
|
|
|
|
|
|
|
| |
v2: Fix trailing whitespace
Fix signed long overflow
improve comment
Signed-off-by: Jan Vesely <jan.vesely at rutgers.edu>
llvm-svn: 216320
|
|
|
|
|
|
|
| |
The default implementation is a no-op. Targets should override this
with their own implementations.
llvm-svn: 216127
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This generates bitcode which is indistinguishable from what was
hand-written for int32 types in v[load|store]_impl.ll.
v4: Use vec2+scalar for vec3 load/stores to prevent corruption (per Tom)
v3: Also remove unused generic/lib/shared/v[load|store]_impl.ll
v2: (Per Matt Arsenault) Fix alignment issues with vector load stores
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
CC: Matt Arsenault <Matthew.Arsenault@amd.com>
CC: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 216069
|
|
|
|
|
|
|
|
| |
v2: remove the initial undef
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 214568
|
|
|
|
|
|
|
|
| |
v2: remove the initial undef
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 214567
|
|
|
|
|
|
| |
This double version still uses @llvm.sin.
llvm-svn: 213762
|
|
|
|
|
|
| |
The double version still uses @llvm.cos.
llvm-svn: 213761
|
|
|
|
| |
llvm-svn: 213760
|
|
|
|
| |
llvm-svn: 213759
|
|
|
|
|
|
|
|
| |
v2: Use relational macros instead of hand-rolled ones
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 213320
|
|
|
|
|
|
|
|
| |
v2: Use relational macros instead of hand-rolled macros
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 213319
|
|
|
|
|
|
|
|
| |
v2: Use relational macros instead of hand-rolled macros
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 213318
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
| |
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211680
|
|
|
|
|
| |
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211211
|
|
|
|
|
|
| |
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211047
|
|
|
|
|
|
| |
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211046
|
|
|
|
|
|
| |
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 211045
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|