summaryrefslogtreecommitdiffstats
path: root/libclc
Commit message (Collapse)AuthorAgeFilesLines
...
* amdgcn: Convert get_local_size to clcJan Vesely2018-11-0413-75/+16
| | | | | | Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-By: Aaron Watry <awatry@gmail.com> llvm-svn: 346079
* r600: Convert barrier to clcJan Vesely2018-11-0412-35/+10
| | | | | | Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry llvm-svn: 346078
* r600: Convert get_num_groups to clcJan Vesely2018-11-0412-49/+16
| | | | | | Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry llvm-svn: 346077
* r600: Convert get_global_size to clcJan Vesely2018-11-0412-49/+16
| | | | | | Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry llvm-svn: 346076
* r600: Convert get_local_size to clcJan Vesely2018-11-0412-49/+16
| | | | | | Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry llvm-svn: 346075
* configure: Rework support for gfx9+ devices that were added post LLVM 3.9Jan Vesely2018-09-151-2/+12
| | | | | | | | v2: Fix reference to Vega12/20 enabling commit Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry llvm-svn: 342341
* .travis: Add llvm-7 buildJan Vesely2018-09-151-0/+20
| | | | | | Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry llvm-svn: 342338
* .travis: Use source whitelist alias for llvm-6 repositoryJan Vesely2018-09-151-1/+1
| | | | | | | | Fixes issue with unauthenticated packages. Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry llvm-svn: 342337
* amdgcn: Use __constant AS for amdgcn builtins.Jan Vesely2018-08-034-4/+12
| | | | | | | | Fixes build after clang r338707. Reviewer: Matthew.Arsenault@amd.com Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 338898
* atom: Use volatile pointers for ↵Jan Vesely2018-06-2114-20/+20
| | | | | | | | | | | | | | | | cl_khr_{global,local}_int32_{base,extended}_atomics int64 versions were switched to volatile pointers in cl1.1 cl1.1 also renamed atom_ functions to atomic_ that use volatile pointers. CTS and applications use volatile pointers. Passes CTS on carrizo no return piglit tests still pass on turks. 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: 335280
* atom: Consolidate cl_khr_{local,global}_int32_{base,extended}_atomics ↵Jan Vesely2018-06-2121-148/+66
| | | | | | | | | | | | implementation These are just atomic_* wrappers. Switch inc, dec to use atomic_* wrappers as well. 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: 335279
* atomic: Provide function implementation of atomic_{dec,inc}Jan Vesely2018-06-215-2/+34
| | | | | | | 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
* atom: Consolidate cl_khr_int64_{base,extended}_atomics declarationsJan Vesely2018-06-219-32/+27
| | | | | | | 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: 335277
* atom: Consolidate cl_khr_{local,global}_int32_{base,extended}_atomics ↵Jan Vesely2018-06-2117-32/+58
| | | | | | | | | declarations 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: 335276
* atomic: Cleanup atomic_cmpxchg headerJan Vesely2018-06-211-15/+4
| | | | | | | | | It's easier to just list the four function declarations 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: 335275
* atomic: Move define cleanup to shared includeJan Vesely2018-06-219-26/+8
| | | | | | | 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: 335274
* Update copyright year to 2018.Paul Robinson2018-06-181-1/+1
| | | | llvm-svn: 334936
* r600/fmin: Flush denormals before calling builtin.Jan Vesely2018-06-072-0/+31
| | | | | | | | | Same reason as amdgcn. Fixes fmin, minmag CTS on turks. Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 334228
* r600/fmax: Flush denormals before calling builtin.Jan Vesely2018-06-072-0/+30
| | | | | | | | | Same reason as amdgcn. Fixes fmax, maxmag CTS on turks. Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 334227
* math/fma: Add fp32 software implementationJan Vesely2018-06-077-5/+192
| | | | | | | | 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
* Add initial support for half precision builtinsJan Vesely2018-05-1757-29/+690
| | | | | | | | | | | | | | v2: fix fmax implementation use consistent checks for __CLC_FP_SIZE add missing TODOs fix whitespace in definitions.h v3: undef ZERO in modf.inc Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> reviewer: Jeroen Ketema <j.ketema@xs4all.nl> Reviewed-by: Aaron Watry <awatry@gmail.com> Tested-by: Aaron Watry <awatry@gmail.com> llvm-svn: 332677
* rootn: Use denormal path onlyJan Vesely2018-05-151-10/+1
| | | | | | | | | | | | It's OK to either flush to 0 or return denormal result if the device does not support denormals. See sec 7.2 and 7.5.3 of OCL specs Use 0.0f explicitly intead of relying on GPU to flush it. Fixes CTS on carrizo and turks Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Acked-by: Aaron Watry <awatry@gmail.com> Tested-by: Aaron Watry <awatry@gmail.com> llvm-svn: 332324
* remquo: Flush denormals if not supportedJan Vesely2018-05-031-0/+2
| | | | | | | | | | It's OK to either flush to 0 or return denormal result if the device does not support denormals. See sec 7.2 and 7.5.3 of OCL specs. Fixes CTS on carrizo and turks. Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry <awatry@gmail.com> llvm-svn: 331435
* remquo: Port from amd builtinsJan Vesely2018-05-038-0/+307
| | | | | | | | 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
* math: Add helper function to flush denormals if not supported.Jan Vesely2018-05-031-0/+19
| | | | | | Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry <awatry@gmail.com> llvm-svn: 331433
* clc_sqrt: Reuse unary_decl.incJan Vesely2018-05-022-50/+3
| | | | | | | Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Aaron Watry <awatry@gmail.com> Tested-by: Aaron Watry <awatry@gmail.com> llvm-svn: 331366
* relational/select: Condition types for half are short/ushort, not char/ucharJan Vesely2018-04-251-2/+2
| | | | | | Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Aaron Watry <awatry@gmail.com> llvm-svn: 330851
* log10: Use sw implementation from amd builtinsJan Vesely2018-04-235-19/+173
| | | | | | | | | | Add missing table. Fixes log10d CTS on carrizo. Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Acked-by: Aaron Watry <awatry@gmail.com> Tested-by: Aaron Watry <awatry@gmail.com> llvm-svn: 330649
* powr: Use denormal path onlyJan Vesely2018-04-171-11/+1
| | | | | | | | | | It's OK to either flush to 0 or return denormal result if the device does not support denormals. See sec 7.2 and 7.5.3 of OCL specs Fixes CTS on carrizo and turks. Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry <awatry@gmail.com> llvm-svn: 330207
* pown: Use denormal path onlyJan Vesely2018-04-171-11/+1
| | | | | | | | | | It's OK to either flush to 0 or return denormal result if the device does not support denormals. See sec 7.2 and 7.5.3 of OCL specs Fixes CTS on carrizo and turks. Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry <awatry@gmail.com> llvm-svn: 330206
* pow: Use denormal path onlyJan Vesely2018-04-171-11/+1
| | | | | | | | | | It's OK to either flush to 0 or return denormal result if the device does not support denormals. See sec 7.2 and 7.5.3 of OCL specs Fixes CTS on carrizo and turks. Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Aaron Watry <awatry@gmail.com> llvm-svn: 330205
* amdgcn/fmin: Fix typos that reduced precisionJan Vesely2018-04-171-3/+3
| | | | | | | | | Not sure how these sneaked in. Fixes fminD and few other tests(fractD, cosD) on carrizo Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Aaron Watry <awatry@gmail.com> llvm-svn: 330198
* exp10: Port from amd builtinsJan Vesely2018-04-175-11/+157
| | | | | | | | 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
* hypot: Port from amd builtinsJan Vesely2018-04-105-4/+108
| | | | | | | | | | | 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
* select: simplify implementation and fix fp16Jan Vesely2018-04-061-18/+4
| | | | | | | | | | Fix half precision implementation Vector ?: operator should behave exactly as select Passes CTS on carrizo Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewer: Jeroen Ketema <j.ketema@xs4all.nl> llvm-svn: 329462
* fmod: Port from amd_builtinsJan Vesely2018-04-066-12/+196
| | | | | | | | | | | 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
* r600: Update datalayout after LLVM r328656Jan Vesely2018-04-054-4/+4
| | | | | | Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Aaron Watry <awatry@gmail.com> llvm-svn: 329291
* amdgcn: Update datalayout after LLVM r328656Jan Vesely2018-04-054-4/+4
| | | | | | Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Aaron Watry <awatry@gmail.com> llvm-svn: 329290
* remainder: Port from amd builtinsJan Vesely2018-03-196-0/+235
| | | | | | | | | 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
* nan: ImplementJan Vesely2018-03-126-0/+52
| | | | | | | | Passes CTS on carrizo and turks Reviewer: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 327324
* travis: Add build using llvm-6Jan Vesely2018-03-121-0/+22
| | | | | | Acked-by: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 327323
* amdgcn/fmax: fcanonicalize operandsJan Vesely2018-03-082-0/+32
| | | | | | | | | v_max instruction needs canonicalized operands. Passes CTS on carrizo Reviewer: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 327076
* amdgcn/fmin: fcanonicalize operandsJan Vesely2018-03-082-0/+32
| | | | | | | | | v_min instruction needs canonicalized operands. Passes CTS on carrizo Reviewer: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 327075
* amdgcn,popcount: Workaround broken llvm.ctpop intrinsic on some GCN ASICsJan Vesely2018-03-083-0/+24
| | | | | | | | | | This is only really needed for VI+ ASICs. However, llvm would cast the value to i32 for older asics anyway. The proper fix is in LLVM-7 (r326535). Fixes CTS popcount on carrizo. Reviewer: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 327044
* integer/gentype: Add __CLC_VECSIZE macroJan Vesely2018-03-081-0/+96
| | | | | | Reviewer: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 327043
* popcount: Provide function implementation rather than intrinsic redirectJan Vesely2018-03-087-6/+21
| | | | | | | | amdgcn will need to override this Reviewer: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 327042
* lgamma_r: Move code from .inc to .cl fileJan Vesely2018-03-062-475/+496
| | | | | | Reviewed-by: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 326821
* frexp: Reuse types provided by gentype.incJan Vesely2018-03-062-78/+53
| | | | | | | | | | | v2: Use select instead of bitselect to consolidate scalar and vector versions Passes CTS on Carrizo Reviewed-by: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 326820
* select: Add vector implementationJan Vesely2018-03-065-1/+91
| | | | | | | | Passes CTS on Carrizo Reviewed-by: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 326819
* minmag: Condition variable needs to be the same bitwidth as operandsJan Vesely2018-03-062-2/+21
| | | | | | | | No changes wrt CTS Reviewed-by: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 326818
OpenPOWER on IntegriCloud