maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
313,031 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

182 Commits

Author SHA1 Message Date
Jan Vesely ee555aa992 trunc: Remove llvm intrinsic from the header. 
Reviewer: Aaron Watry
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 356018
 2019-03-13 07:06:10 +00:00
Jan Vesely 1c395b74bf round: Remove llvm intrinsic from the header 
Reviewer: Aaron Watry
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 356017
 2019-03-13 07:06:08 +00:00
Jan Vesely b3d64e4a83 rint: Remove llvm intrinsic from the header. 
Reviewer: Aaron Watry
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 356016
 2019-03-13 07:06:06 +00:00
Jan Vesely fd199f0139 floor: Remove llvm isntrinsic from the header. 
Reviewer: Aaron Watry
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 356015
 2019-03-13 07:06:03 +00:00
Jan Vesely fda15e56a6 fabs: Remove llvm intrinsic from the header. 
Reviewer: Aaron Watry
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 356014
 2019-03-13 07:06:00 +00:00
Jan Vesely 54eb4d3a6d ceil: Remove llvm intrinsic from the header. 
Reviewer: Aaron Watry
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 356013
 2019-03-13 07:05:58 +00:00
Jan Vesely f965b46c8e atomic: Provide function implementation of atomic_{dec,inc} 
Reviewed-By: Aaron Watry <awatry@gmail.com>
Tested-By: Aaron Watry <awatry@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 335278
 2018-06-21 19:27:26 +00:00
Jan Vesely 6e85e6309d math/fma: Add fp32 software implementation 
Passes CTS on carrizo (when forced to use sw fma) and turks.
Reviewer: Tom Stellard <tstellar@redhat.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

llvm-svn: 334226
 2018-06-07 20:27:43 +00:00
Jan Vesely 8db45e4cf1 remquo: Port from amd builtins 
double version passes on carrizo. float version fails on denormals.

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewer: Aaron Watry <awatry@gmail.com>
llvm-svn: 331434
 2018-05-03 05:44:26 +00:00
Jan Vesely 15c388cd79 exp10: Port from amd builtins 
Passes CTS on carrizo and turks.
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed and Tested (on RX 580) by: Aaron Watry <awatry@gmail.com>

llvm-svn: 330197
 2018-04-17 18:08:08 +00:00
Jan Vesely 4be0339023 hypot: Port from amd builtins 
v2: Fix whitespace errors

Use only subnormal path.
Passes CTS on carrizo and turks.
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewer: Aaron Watry <awatry@gmail.com>

llvm-svn: 329647
 2018-04-10 00:11:58 +00:00
Jan Vesely 93af966747 fmod: Port from amd_builtins 
Uses only denormal path for fp32.
Passes CTS on carrizo and turks.

v2: whitespace fix

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewer: Aaron Watry <awatry@gmail.com>
llvm-svn: 329433
 2018-04-06 17:43:08 +00:00
Jan Vesely 5b10494fa8 remainder: Port from amd builtins 
Mostly ported from amd_builtins, uses only denormal path for fp32.
Passes CTS on carrizo and turks

Reviewer: Aaron Watry <awatry@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 327818
 2018-03-19 01:01:10 +00:00
Jan Vesely b672f7a251 nan: Implement 
Passes CTS on carrizo and turks

Reviewer: Aaron Watry <awatry@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 327324
 2018-03-12 19:46:52 +00:00
Jan Vesely 17e8679493 popcount: Provide function implementation rather than intrinsic redirect 
amdgcn will need to override this

Reviewer: Aaron Watry <awatry@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 327042
 2018-03-08 18:58:00 +00:00
Jan Vesely ae156b66f8 select: Add vector implementation 
Passes CTS on Carrizo

Reviewed-by: Aaron Watry <awatry@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 326819
 2018-03-06 17:48:43 +00:00
Jan Vesely 3b8b4eb64d half_powr: Implement using powr 
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 323942
 2018-02-01 03:00:35 +00:00
Jan Vesely 7013857f95 tanpi: Port from amd_builtins 
Passes piglit on turks and carrizo.
Passes CTS on carrizo.

Acked-By: Aaron Watry <awatry@gmail.com>
Tested-By: Aaron Watry <awatry@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322980
 2018-01-19 18:57:22 +00:00
Jan Vesely 03937bdec3 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: Aaron Watry <awatry@gmail.com>
Tested-By: Aaron Watry <awatry@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322979
 2018-01-19 18:57:19 +00:00
Jan Vesely 44e0522c09 half_divide: Implement using x/y 
Passes CTS on carrizo
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322899
 2018-01-18 21:12:06 +00:00
Jan Vesely 2813b4f8d9 half_tan: Implement using tan 
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322898
 2018-01-18 21:12:04 +00:00
Jan Vesely bf38fae8de half_sin: Implement using sin 
Passes CTS on carrizo
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322897
 2018-01-18 21:12:01 +00:00
Jan Vesely 398108b91e half_recip: Implement using 1/x 
Passes CTS on carrizo
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322896
 2018-01-18 21:11:58 +00:00
Jan Vesely a1aba44ffa half_log2: Implement using log2 
Passes CTS on carrizo
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322895
 2018-01-18 21:11:56 +00:00
Jan Vesely b3b72af4b9 half_log10: Implement using log10 
Passes CTS on carrizo
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322894
 2018-01-18 21:11:53 +00:00
Jan Vesely 6852023802 half_log: Implement using log 
Passes CTS on carrizo
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322893
 2018-01-18 21:11:50 +00:00
Jan Vesely aa4c3899b5 half_exp10: Implement using exp10 
Passes CTS on carrizo
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322892
 2018-01-18 21:11:48 +00:00
Jan Vesely 3c0e19b61a half_exp2: Implement using exp2 
Passes CTS on carrizo
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322891
 2018-01-18 21:11:45 +00:00
Jan Vesely caa9000b1c half_exp: Implement using exp 
Passes CTS on carrizo
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322890
 2018-01-18 21:11:43 +00:00
Jan Vesely b5d556061d half_cos: Implement using cos 
Passes CTS on carrizo
v2: Use full precision implementation

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322889
 2018-01-18 21:11:40 +00:00
Jan Vesely fe8e00bc3c 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

Reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322763
 2018-01-17 21:22:14 +00:00
Jan Vesely c45ec604f5 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: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322762
 2018-01-17 21:22:06 +00:00
Jan Vesely 5efc8fe321 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: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322761
 2018-01-17 21:22:03 +00:00
Jan Vesely cc5c65b2c2 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: Jeroen Ketema <j.ketema@xs4all.nl>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 322760
 2018-01-17 21:21:35 +00:00
Jan Vesely fe7c045753 math: Implement minmag 
Reviewer: Aaron Watry
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 318265
 2017-11-15 04:10:39 +00:00
Jan Vesely 7ba243cc3d math: Implement maxmag 
Reviewer: Aaron Watry
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 318264
 2017-11-15 04:10:37 +00:00
Jan Vesely 383fbd050c 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: don't check inputs at all, nan propagation works as expected

Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 318204
 2017-11-14 21:55:41 +00:00
Jan Vesely f38b40daf7 native_divide: provide function implementation instead of macro 
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 318067
 2017-11-13 18:28:56 +00:00
Jan Vesely 1b9825f982 native_recip: provide function implementation instead of macro 
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 318066
 2017-11-13 18:28:53 +00:00
Jan Vesely a6758c94ef native_rsqrt: Switch implementation to 1 / native_sqrt 
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 318065
 2017-11-13 18:28:51 +00:00
Jan Vesely 541a3f0758 native_tan: Switch implementation to use native_sin/native_cos 
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 318064
 2017-11-13 18:28:48 +00:00
Jan Vesely 6b4a625438 native_exp10: Switch implementation to llvm intrinsic 
v2: Use native_log2 instead of wrong constant

Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 317941
 2017-11-10 22:16:41 +00:00
Jan Vesely 4301e6d0c9 native_sqrt: Switch implementation to llvm intrinsic 
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 317940
 2017-11-10 22:16:39 +00:00
Jan Vesely 1f34c851e0 native_sin: Switch implementation to llvm intrinsic 
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 317939
 2017-11-10 22:16:36 +00:00
Jan Vesely 0750b7df51 native_cos: Switch implementation to llvm intrinsic 
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 317938
 2017-11-10 22:16:33 +00:00
Jan Vesely edbde58de0 native_exp2: Switch implementation to llvm intrinsic 
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 317937
 2017-11-10 22:16:31 +00:00
Jan Vesely 504f85c551 native_exp: Switch implementation to llvm intrinsic 
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 317936
 2017-11-10 22:16:28 +00:00
Jan Vesely 47e093da9b math: Implement native_log10 
Use llvm instrinsic by default
Provide amdgpu workaround

v2: drop old amd copyrights

Reviewer: Aaron Watry
Reviewed-by: Vedran Miletić <vedran@miletic.net>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 316588
 2017-10-25 16:49:22 +00:00
Jan Vesely 3d349ea98e Make image builtins r600/llvm-3.9 only 
The implementation uses r600 sepcific intrinsics
LLVM-4 switched to _ro_t and _rw_t image types
Portions of the code can be moved back as more targets/llvm versions add image support

Reviewer: Aaron Watry
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 315341
 2017-10-10 18:10:21 +00:00
Jan Vesely a02d0e2c50 integer/sub_sat: Use clang builtin instead of llvm asm 
reviewer: Tom Stellard

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 314703
 2017-10-02 18:39:03 +00:00