yggdrasil/gcc
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Files
4b9af57eae30f32d26ddf3489b8a81e89da846e1
gcc/libgomp/testsuite/libgomp.c
T
History
Kwok Cheung Yeung ce9cd7258d amdgcn: Enable SIMD vectorization of math functions 
Calls to vectorized versions of routines in the math library will now
be inserted when vectorizing code containing supported math functions.

2023-03-02  Kwok Cheung Yeung  <kcy@codesourcery.com>
	    Paul-Antoine Arras  <pa@codesourcery.com>

	gcc/
	* builtins.cc (mathfn_built_in_explicit): New.
	* config/gcn/gcn.cc: Include case-cfn-macros.h.
	(mathfn_built_in_explicit): Add prototype.
	(gcn_vectorize_builtin_vectorized_function): New.
	(gcn_libc_has_function): New.
	(TARGET_LIBC_HAS_FUNCTION): Define.
	(TARGET_VECTORIZE_BUILTIN_VECTORIZED_FUNCTION): Define.

	gcc/testsuite/
	* gcc.target/gcn/simd-math-1.c: New testcase.
	* gcc.target/gcn/simd-math-2.c: New testcase.

	libgomp/
	* testsuite/libgomp.c/simd-math-1.c: New testcase.
2023-03-02 20:56:53 +00:00
..
appendix-a
…
examples-4
…
address-space-1.c
Host and offload targets have no common meaning of address spaces
2022-01-13 11:16:20 +01:00
affinity-1.c
Update copyright years.
2023-01-16 11:52:17 +01:00
affinity-2.c
…
atomic-1.c
…
atomic-2.c
…
atomic-3.c
…
atomic-4.c
…
atomic-5.c
…
atomic-6.c
…
atomic-10.c
…
atomic-11.c
…
atomic-12.c
…
atomic-13.c
…
atomic-14.c
…
atomic-15.c
…
atomic-16.c
…
atomic-17.c
…
autopar-1.c
…
autopar-2.c
…
autopar-3.c
…
autopar-4.c
…
autopar-5.c
…
autopar-6.c
…
autopar-7.c
…
autopar-8.c
…
barrier-1.c
…
c.exp
…
cancel-for-1.c
…
cancel-for-2.c
…
cancel-parallel-1.c
…
cancel-parallel-2.c
…
cancel-parallel-3.c
…
cancel-sections-1.c
…
collapse-1.c
…
collapse-2.c
…
collapse-3.c
…
copyin-1.c
…
copyin-2.c
…
copyin-3.c
…
critical-1.c
…
critical-2.c
…
debug-1.c
…
declare-variant-1.c
…
declare-variant-2.c
openmp: Fix up handling of kind(host) and kind(nohost) in ACCEL_COMPILERs [PR103384]
2021-11-24 10:30:32 +01:00
declare-variant-3-sm30.c
[libgomp, testsuite, nvptx] Add -mptx=_ in declare-variant-3-sm*.c
2022-02-28 10:10:51 +01:00
declare-variant-3-sm35.c
[libgomp, testsuite, nvptx] Add -mptx=_ in declare-variant-3-sm*.c
2022-02-28 10:10:51 +01:00
declare-variant-3-sm53.c
[libgomp, testsuite, nvptx] Add -mptx=_ in declare-variant-3-sm*.c
2022-02-28 10:10:51 +01:00
declare-variant-3-sm70.c
[libgomp, testsuite, nvptx] Add -mptx=_ in declare-variant-3-sm*.c
2022-02-28 10:10:51 +01:00
declare-variant-3-sm75.c
[libgomp, testsuite, nvptx] Add -mptx=_ in declare-variant-3-sm*.c
2022-02-28 10:10:51 +01:00
declare-variant-3-sm80.c
[libgomp, testsuite, nvptx] Add -mptx=_ in declare-variant-3-sm*.c
2022-02-28 10:10:51 +01:00
declare-variant-3.h
[libgomp, testsuite, nvptx] Add libgomp.c/declare-variant-3-sm*.c
2022-02-24 11:41:03 +01:00
declare-variant-4-fiji.c
amdgcn: Support AMD-specific 'isa' traits in OpenMP context selectors
2022-11-30 10:51:42 +01:00
declare-variant-4-gfx90a.c
amdgcn: Support AMD-specific 'isa' traits in OpenMP context selectors
2022-11-30 10:51:42 +01:00
declare-variant-4-gfx803.c
amdgcn: Support AMD-specific 'isa' traits in OpenMP context selectors
2022-11-30 10:51:42 +01:00
declare-variant-4-gfx900.c
amdgcn: Support AMD-specific 'isa' traits in OpenMP context selectors
2022-11-30 10:51:42 +01:00
declare-variant-4-gfx906.c
amdgcn: Support AMD-specific 'isa' traits in OpenMP context selectors
2022-11-30 10:51:42 +01:00
declare-variant-4-gfx908.c
amdgcn: Support AMD-specific 'isa' traits in OpenMP context selectors
2022-11-30 10:51:42 +01:00
declare-variant-4.h
amdgcn: Support AMD-specific 'isa' traits in OpenMP context selectors
2022-11-30 10:51:42 +01:00
depend-1.c
…
depend-2.c
…
depend-3.c
…
depend-4.c
…
depend-5.c
…
depend-6.c
…
depend-7.c
…
depend-8.c
…
depend-9.c
…
depend-10.c
…
doacross-1.c
…
doacross-2.c
…
doacross-3.c
…
doacross-4.c
openmp: Implement doacross(sink: omp_cur_iteration - 1)
2022-09-08 13:32:51 +02:00
doacross-5.c
openmp: Implement doacross(sink: omp_cur_iteration - 1)
2022-09-08 13:32:51 +02:00
doacross-6.c
openmp: Implement doacross(sink: omp_cur_iteration - 1)
2022-09-08 13:32:51 +02:00
doacross-7.c
openmp: Implement doacross(sink: omp_cur_iteration - 1)
2022-09-08 13:32:51 +02:00
icv-1.c
…
icv-2.c
…
lib-1.c
…
lib-2.c
…
linear-1.c
…
linear-2.c
OpenMP: Fix var replacement with 'simd' and linear-step vars [PR106548]
2022-08-17 15:45:56 +02:00
lock-1.c
…
lock-2.c
…
lock-3.c
…
loop-1.c
…
loop-2.c
…
loop-3.c
…
loop-4.c
…
loop-5.c
…
loop-6.c
…
loop-7.c
…
loop-8.c
…
loop-9.c
…
loop-10.c
…
loop-11.c
…
loop-12.c
…
loop-16.c
…
loop-17.c
…
loop-18.c
…
loop-19.c
…
loop-20.c
…
loop-21.c
…
loop-22.c
…
loop-23.c
…
loop-24.c
…
loop-25.c
…
loop-26.c
openmp: Allow non-rectangular loops with pointer iterators
2021-10-27 09:22:07 +02:00
loop-27.c
openmp: Allow non-rectangular loops with pointer iterators
2021-10-27 09:22:07 +02:00
nested-1.c
…
nested-2.c
…
nested-3.c
…
nestedfn-1.c
…
nestedfn-2.c
…
nestedfn-3.c
…
nestedfn-4.c
…
nestedfn-5.c
…
nestedfn-6.c
…
nqueens-1.c
…
omp_hello.c
…
omp_matvec.c
…
omp_orphan.c
…
omp_reduction.c
…
omp_workshare1.c
…
omp_workshare2.c
…
omp_workshare3.c
…
omp_workshare4.c
…
omp-loop01.c
…
omp-loop02.c
…
omp-loop03.c
…
omp-nested-1.c
…
omp-nested-2.c
…
omp-nested-3.c
testsuite: prune new LTO warning
2021-05-13 09:24:23 +02:00
omp-parallel-for.c
…
omp-parallel-if.c
…
omp-single-1.c
…
omp-single-2.c
…
omp-single-3.c
…
ordered-1.c
…
ordered-2.c
…
ordered-3.c
…
ordered-5.c
…
parallel-1.c
…
parloops-exit-first-loop-alt-2.c
…
parloops-exit-first-loop-alt-3.c
…
parloops-exit-first-loop-alt-4.c
…
parloops-exit-first-loop-alt-5.c
…
parloops-exit-first-loop-alt-6.c
…
parloops-exit-first-loop-alt-7.c
…
parloops-exit-first-loop-alt.c
…
places-1.c
openmp: Add support for OMP_PLACES=ll_caches
2021-10-15 12:06:51 +02:00
places-2.c
openmp: Add support for OMP_PLACES=ll_caches
2021-10-15 12:06:51 +02:00
places-3.c
openmp: Add support for OMP_PLACES=ll_caches
2021-10-15 12:06:51 +02:00
places-4.c
openmp: Add support for OMP_PLACES=ll_caches
2021-10-15 12:06:51 +02:00
places-5.c
openmp: Add support for OMP_PLACES=numa_domains
2021-10-15 12:16:50 +02:00
places-6.c
openmp: Fix up handling of OMP_PLACES=threads(1)
2021-10-15 16:25:25 +02:00
places-7.c
openmp: Fix up handling of OMP_PLACES=threads(1)
2021-10-15 16:25:25 +02:00
places-8.c
openmp: Fix up handling of OMP_PLACES=threads(1)
2021-10-15 16:25:25 +02:00
places-9.c
openmp: Fix up handling of OMP_PLACES=threads(1)
2021-10-15 16:25:25 +02:00
places-10.c
openmp: Fix up handling of OMP_PLACES=threads(1)
2021-10-15 16:25:25 +02:00
pr24455-1.c
…
pr24455.c
…
pr26171.c
…
pr26943-1.c
…
pr26943-2.c
…
pr26943-3.c
…
pr26943-4.c
…
pr29947-1.c
…
pr29947-2.c
…
pr30494.c
…
pr32362-1.c
…
pr32362-2.c
…
pr32362-3.c
…
pr32468.c
…
pr33880.c
…
pr34513.c
…
pr35130.c
…
pr35196.c
…
pr35549.c
…
pr35625.c
…
pr36802-1.c
…
pr36802-2.c
…
pr36802-3.c
…
pr38650.c
…
pr39154.c
…
pr39591-1.c
…
pr39591-2.c
…
pr39591-3.c
…
pr42029.c
…
pr42942.c
…
pr43893.c
…
pr46032-2.c
testsuite: prune new LTO warning
2021-05-13 09:24:23 +02:00
pr46032.c
…
pr46193.c
…
pr46886.c
…
pr48591.c
…
pr49897-1.c
…
pr49897-2.c
…
pr49898-1.c
…
pr49898-2.c
…
pr52547.c
…
pr58392.c
…
pr58756.c
…
pr61200.c
…
pr64734.c
…
pr66133.c
…
pr66714.c
…
pr68960.c
…
pr69110.c
…
pr69805.c
…
pr70680-1.c
…
pr70680-2.c
…
pr79940.c
…
pr80394.c
…
pr80809-1.c
…
pr80809-2.c
…
pr80809-3.c
…
pr80853.c
…
pr81687-1.c
…
pr81687-2.c
…
pr81778.c
[omp, simt] Handle alternative IV
2021-04-29 14:37:32 +02:00
pr86416-1.c
libgomp/testsuite: Fix checks for dg-excess-errors
2021-04-21 20:07:19 +02:00
pr86416-2.c
libgomp/testsuite: Fix checks for dg-excess-errors
2021-04-21 20:07:19 +02:00
pr86660.c
…
pr89002.c
…
pr90779.c
…
pr90811.c
…
pr93566.c
…
pr95620.c
…
pr99555-1.c
[libgomp, nvptx] Fix hang in gomp_team_barrier_wait_end
2022-02-22 15:48:03 +01:00
pr104385.c
libgomp: Fix segfault with posthumous orphan tasks [PR104385]
2022-02-08 09:30:17 +01:00
pr104783-2.c
[nvptx] Add warp sync at simt exit
2022-03-22 14:35:34 +01:00
pr104783.c
[nvptx] Disable warp sync in simt region
2022-03-10 12:20:44 +01:00
pr104952-1.c
[openmp] Fix SIMT reduction using TRUTH_{AND,OR}IF_EXPR
2022-03-18 15:45:13 +01:00
pr104952-2.c
[openmp] Fix SIMT reduction using TRUTH_{AND,OR}IF_EXPR
2022-03-18 15:45:13 +01:00
pr108459.c
openmp: Fix up OpenMP expansion of non-rectangular loops [PR108459]
2023-01-19 21:00:08 +01:00
priority.c
…
private-1.c
…
reduction-1.c
…
reduction-2.c
…
reduction-3.c
…
reduction-4.c
…
reduction-5.c
…
reduction-6.c
…
reduction-7.c
…
reduction-8.c
…
reduction-9.c
…
reduction-10.c
…
reduction-11.c
…
reduction-12.c
…
reduction-13.c
…
reduction-14.c
…
reduction-15.c
…
reverse-offload-sm30.c
Fix nvptx-specific '-foffload-options' syntax in 'libgomp.c/reverse-offload-sm30.c'
2022-10-17 13:50:57 +02:00
scan-1.c
…
scan-2.c
…
scan-3.c
…
scan-4.c
…
scan-5.c
…
scan-6.c
…
scan-7.c
…
scan-8.c
…
scan-9.c
…
scan-10.c
…
scan-11.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
scan-12.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
scan-13.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
scan-14.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
scan-15.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
scan-16.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
scan-17.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
scan-18.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
scan-19.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
scan-20.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
scan-21.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
scan-22.c
vectorizer: Fix up -fsimd-cost-model= handling
2021-10-12 09:28:10 +02:00
sections-1.c
…
sections-2.c
…
shared-1.c
…
shared-2.c
…
shared-3.c
…
simd-1.c
…
simd-2.c
…
simd-3.c
…
simd-4.c
…
simd-5.c
…
simd-6.c
…
simd-7.c
…
simd-8.c
…
simd-9.c
…
simd-10.c
…
simd-11.c
…
simd-12.c
…
simd-13.c
…
simd-math-1.c
amdgcn: Enable SIMD vectorization of math functions
2023-03-02 20:56:53 +00:00
single-1.c
…
single-2.c
…
sort-1.c
Update copyright years.
2023-01-16 11:52:17 +01:00
static-chunk-size-one.c
…
switch-conversion-2.c
…
switch-conversion.c
…
target-3.c
OpenMP: Add strictly nested API call check [PR102972]
2021-10-30 23:45:32 +02:00
target-4.c
…
target-5.c
OpenMP: Add strictly nested API call check [PR102972]
2021-10-30 23:45:32 +02:00
target-6.c
OpenMP: Add strictly nested API call check [PR102972]
2021-10-30 23:45:32 +02:00
target-7.c
…
target-8.c
…
target-9.c
…
target-11.c
…
target-12.c
…
target-14.c
…
target-15.c
…
target-16.c
…
target-17.c
…
target-18.c
…
target-19.c
…
target-20.c
…
target-21.c
…
target-22.c
…
target-23.c
OpenMP 5.0: Remove array section base-pointer mapping semantics and other front-end adjustments
2021-12-09 00:01:10 +08:00
target-24.c
…
target-25.c
…
target-26.c
…
target-27.c
…
target-28.c
…
target-29.c
OpenMP 5.0: Remove array section base-pointer mapping semantics and other front-end adjustments
2021-12-09 00:01:10 +08:00
target-30.c
…
target-31.c
libgomp: Fix up target-31.c test [PR106045]
2022-06-21 17:51:08 +02:00
target-32.c
…
target-33.c
…
target-34.c
…
target-35.c
…
target-36.c
…
target-37.c
…
target-38.c
…
target-39.c
…
target-40.c
…
target-41.c
openmp: Conforming device numbers and omp_{initial,invalid}_device
2022-06-13 14:02:37 +02:00
target-42.c
…
target-43.c
'libgomp.c/target-43.c': '-latomic' for nvptx offloading
2021-09-06 11:51:13 +02:00
target-44.c
Add 'default' to -foffload=; document that flag [PR67300]
2021-06-29 16:00:04 +02:00
target-45.c
openmp: Conforming device numbers and omp_{initial,invalid}_device
2022-06-13 14:02:37 +02:00
target-46.c
openmp: Conforming device numbers and omp_{initial,invalid}_device
2022-06-13 14:02:37 +02:00
target-47.c
openmp: Conforming device numbers and omp_{initial,invalid}_device
2022-06-13 14:02:37 +02:00
target-critical-1.c
…
target-has-device-addr-3.c
C, C++, Fortran, OpenMP: Add 'has_device_addr' clause to 'target' construct.
2022-02-09 23:47:12 -08:00
target-link-1.c
…
target-print-1.c
…
target-simd-clone-1.c
OpenMP: Generate SIMD clones for functions with "declare target"
2022-11-25 18:13:22 +00:00
target-simd-clone-2.c
OpenMP: Generate SIMD clones for functions with "declare target"
2022-11-25 18:13:22 +00:00
target-simd-clone-3.c
OpenMP: Generate SIMD clones for functions with "declare target"
2022-11-25 18:13:22 +00:00
target-teams-1.c
OpenMP: Add strictly nested API call check [PR102972]
2021-10-30 23:45:32 +02:00
task-1.c
…
task-2.c
…
task-3.c
…
task-4.c
…
task-5.c
…
task-6.c
…
task-7.c
libgomp: Fix up creation of artificial teams
2022-10-12 17:54:08 +02:00
task-8.c
libgomp: Fix up creation of artificial teams
2022-10-12 17:54:08 +02:00
task-reduction-1.c
…
task-reduction-2.c
…
task-reduction-3.c
…
task-reduction-4.c
openmp: Fix up taskloop reduction ICE if taskloop has no iterations [PR100471]
2021-05-11 09:07:47 +02:00
teams-1.c
OpenMP: Add strictly nested API call check [PR102972]
2021-10-30 23:45:32 +02:00
teams-2.c
…
teams-3.c
…
teams-4.c
openmp: Honor OpenMP 5.1 num_teams lower bound
2021-11-12 12:41:22 +01:00
teams-5.c
libgomp: Add a testcase for omp_get_num_teams inside of target inside of host teams
2021-11-15 08:58:39 +01:00
thread-limit-1.c
…
thread-limit-2.c
OpenMP: Add strictly nested API call check [PR102972]
2021-10-30 23:45:32 +02:00
thread-limit-3.c
OpenMP: Add strictly nested API call check [PR102972]
2021-10-30 23:45:32 +02:00
thread-limit-4.c
OpenMP: Add strictly nested API call check [PR102972]
2021-10-30 23:45:32 +02:00
thread-limit-5.c
OpenMP: Add strictly nested API call check [PR102972]
2021-10-30 23:45:32 +02:00
udr-2.c
…
udr-3.c
…
uns-outer-4.c
…
usleep.h
…
vla-1.c
…