Skip to content

Commit 3c451b9

Browse files
authored
Upgrade gensymbol (#125)
* Upgrade gensymbol * Update CI scripts
1 parent a46dbfb commit 3c451b9

File tree

4 files changed

+351
-49
lines changed

4 files changed

+351
-49
lines changed

.buildkite/pipeline.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@ steps:
99
}
1010
1111
# We'll test on the following julia versions
12-
for JULIA_VERSION in 1.8 nightly; do
12+
for JULIA_VERSION in 1.10 nightly; do
1313
# First, linux
1414
OS="linux"
1515

.cirrus.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@ task:
22
matrix:
33
- name: FreeBSD
44
freebsd_instance:
5-
image: freebsd-13-1-release-amd64
5+
image: freebsd-13-2-release-amd64
66
env:
77
matrix:
88
- JULIA_VERSION: 1

ext/gensymbol/gensymbol

100755100644
Lines changed: 184 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -17,38 +17,38 @@
1717
# removed blas_thread_shutdown_
1818
#
1919
@blasobjsc = (
20-
caxpy,caxpby,ccopy,cdotc,cdotu,cgbmv,cgemm,cgemmt,cgemv,cgerc,cgeru,
20+
caxpy,caxpby,ccopy,cdotc,cdotu,cgbmv,cgemm,cgemv,cgerc,cgeru,
2121
chbmv,chemm,chemv,cher2,cher2k,cher,cherk,scabs1,scamax,
2222
chpmv,chpr2,chpr,crotg,cscal,csrot,csscal,cswap,scamin,scasum,scnrm2,
2323
csymm,csyr2k,csyrk,ctbmv,ctbsv,ctpmv,ctpsv,ctrmm,ctrmv,ctrsm,
24-
ctrsv,icamax,icamin,cimatcopy,comatcopy,cgeadd,scsum);
24+
ctrsv,icamax,icamin,cimatcopy,comatcopy,cgeadd,scsum,cgemmt);
2525

2626
@blasobjsd = (
27-
damax,damin,dasum,daxpy,daxpby,dcabs1,dcopy,ddot,dgbmv,dgemm,dgemmt,
27+
damax,damin,dasum,daxpy,daxpby,dcabs1,dcopy,ddot,dgbmv,dgemm,
2828
dgemv,dger,dmax,dmin,dnrm2,drot,drotg,drotm,drotmg,dsbmv,
2929
dscal,dsdot,dspmv,dspr2,dimatcopy,domatcopy,
3030
dspr,dswap,dsymm,dsymv,dsyr2,dsyr2k,dsyr,dsyrk,dtbmv,dtbsv,
3131
dtpmv,dtpsv,dtrmm,dtrmv,dtrsm,dtrsv,
32-
idamax,idamin,idmax,idmin,dgeadd,dsum);
32+
idamax,idamin,idmax,idmin,dgeadd,dsum,dgemmt);
3333

3434
@blasobjss = (
3535
isamax,isamin,ismax,ismin,
3636
samax,samin,sasum,saxpy, saxpby,
37-
scopy,sdot,sdsdot,sgbmv,sgemm,sgemmt,sgemv,sger,
37+
scopy,sdot,sdsdot,sgbmv,sgemm,sgemv,sger,
3838
smax,smin,snrm2,simatcopy,somatcopy,
3939
srot,srotg,srotm,srotmg,ssbmv,sscal,sspmv,sspr2,sspr,sswap,
4040
ssymm,ssymv,ssyr2,ssyr2k,ssyr,ssyrk,stbmv,stbsv,stpmv,stpsv,
41-
strmm,strmv,strsm,strsv, sgeadd,ssum);
41+
strmm,strmv,strsm,strsv, sgeadd,ssum,sgemmt);
4242

4343
@blasobjsz = (
4444
izamax,izamin,,
4545
zaxpy,zaxpby,zcopy,zdotc,zdotu,zdrot,
46-
zdscal,zgbmv,zgemm,zgemmt,zgemv,zgerc,zgeru,
46+
zdscal,zgbmv,zgemm,zgemv,zgerc,zgeru,
4747
zhbmv,zhemm,zhemv,zher2,zher2k,zher,zherk,zhpmv,zhpr2,
4848
zhpr,zrotg,zscal,zswap,zsymm,zsyr2k,zsyrk,ztbmv,
4949
ztbsv,ztpmv,ztpsv,ztrmm,ztrmv,ztrsm,ztrsv,
50-
zomatcopy, zimatcopy,dzamax,dzamin,dzasum,dznrm2,
51-
zgeadd, dzsum);
50+
zomatcopy,zimatcopy,dzamax,dzamin,dzasum,dznrm2,
51+
zgeadd,dzsum,zgemmt);
5252

5353
@blasobjs = (lsame, xerbla);
5454
@bfblasobjs = (sbgemm, sbgemv, sbdot, sbstobf16, sbdtobf16, sbf16tos, dbf16tod);
@@ -59,17 +59,17 @@
5959
cblas_csscal, cblas_cswap, cblas_csymm, cblas_csyr2k, cblas_csyrk, cblas_ctbmv, cblas_cgeadd,
6060
cblas_ctbsv, cblas_ctpmv, cblas_ctpsv, cblas_ctrmm, cblas_ctrmv, cblas_ctrsm, cblas_ctrsv,
6161
cblas_scnrm2, cblas_scasum,
62-
cblas_icamax, cblas_icamin, cblas_icmin, cblas_icmax, cblas_scsum,cblas_cimatcopy,cblas_comatcopy
63-
);
62+
cblas_icamax, cblas_icamin, cblas_icmin, cblas_icmax, cblas_scsum,cblas_cimatcopy,cblas_comatcopy,
63+
cblas_cgemmt, cblas_caxpyc, cblas_crotg, cblas_csrot, cblas_scamax, cblas_scamin);
6464
@cblasobjsd = (
6565
cblas_dasum, cblas_daxpy, cblas_dcopy, cblas_ddot,
6666
cblas_dgbmv, cblas_dgemm, cblas_dgemv, cblas_dger, cblas_dnrm2,
6767
cblas_drot, cblas_drotg, cblas_drotm, cblas_drotmg, cblas_dsbmv, cblas_dscal, cblas_dsdot,
6868
cblas_dspmv, cblas_dspr2, cblas_dspr, cblas_dswap, cblas_dsymm, cblas_dsymv, cblas_dsyr2,
6969
cblas_dsyr2k, cblas_dsyr, cblas_dsyrk, cblas_dtbmv, cblas_dtbsv, cblas_dtpmv, cblas_dtpsv,
7070
cblas_dtrmm, cblas_dtrmv, cblas_dtrsm, cblas_dtrsv, cblas_daxpby, cblas_dgeadd,
71-
cblas_idamax, cblas_idamin, cblas_idmin, cblas_idmax, cblas_dsum,cblas_dimatcopy,cblas_domatcopy
72-
);
71+
cblas_idamax, cblas_idamin, cblas_idmin, cblas_idmax, cblas_dsum,cblas_dimatcopy,cblas_domatcopy,
72+
cblas_dgemmt, cblas_damax, cblas_damin);
7373

7474
@cblasobjss = (
7575
cblas_sasum, cblas_saxpy, cblas_saxpby,
@@ -79,8 +79,8 @@
7979
cblas_sswap, cblas_ssymm, cblas_ssymv, cblas_ssyr2, cblas_ssyr2k, cblas_ssyr, cblas_ssyrk,
8080
cblas_stbmv, cblas_stbsv, cblas_stpmv, cblas_stpsv, cblas_strmm, cblas_strmv, cblas_strsm,
8181
cblas_strsv, cblas_sgeadd,
82-
cblas_isamax, cblas_isamin, cblas_ismin, cblas_ismax, cblas_ssum,cblas_simatcopy,cblas_somatcopy
83-
);
82+
cblas_isamax, cblas_isamin, cblas_ismin, cblas_ismax, cblas_ssum,cblas_simatcopy,cblas_somatcopy,
83+
cblas_sgemmt, cblas_samax, cblas_samin);
8484
@cblasobjsz = (
8585
cblas_dzasum, cblas_dznrm2, cblas_zaxpy, cblas_zcopy, cblas_zdotc, cblas_zdotu, cblas_zdscal,
8686
cblas_zgbmv, cblas_zgemm, cblas_zgemv, cblas_zgerc, cblas_zgeru, cblas_zhbmv, cblas_zhemm,
@@ -89,8 +89,8 @@
8989
cblas_ztbmv, cblas_ztbsv, cblas_ztpmv, cblas_ztpsv, cblas_ztrmm, cblas_ztrmv, cblas_ztrsm,
9090
cblas_ztrsv, cblas_cdotc_sub, cblas_cdotu_sub, cblas_zdotc_sub, cblas_zdotu_sub,
9191
cblas_zaxpby, cblas_zgeadd,
92-
cblas_izamax, cblas_izamin, cblas_izmin, cblas_izmax, cblas_dzsum,cblas_zimatcopy,cblas_zomatcopy
93-
);
92+
cblas_izamax, cblas_izamin, cblas_izmin, cblas_izmax, cblas_dzsum,cblas_zimatcopy,cblas_zomatcopy,
93+
cblas_zgemmt, cblas_dzamax, cblas_dzamin);
9494

9595
@cblasobjs = ( cblas_xerbla );
9696

@@ -709,6 +709,7 @@ zpotri,
709709
# functions added for lapack-3.7.0
710710
@lapackobjs2s = (@lapackobjs2s,
711711
slarfy,
712+
ssyconvf,
712713
strevc3,
713714
sgelqt,
714715
sgelqt3,
@@ -813,7 +814,86 @@ zpotri,
813814
@lapackobjs2z = (@lapackobjs2z,
814815
zgesvdq,
815816
zungtsqr
816-
);
817+
);
818+
#functions added for lapack-3.10
819+
@lapackobjs2c = (@lapackobjs2c,
820+
cgetsqrhrt,
821+
cungtsqr_row
822+
);
823+
@lapackobjs2d = (@lapackobjs2d,
824+
dgetsqrhrt,
825+
dorgtsqr_row
826+
);
827+
@lapackobjs2s = (@lapackobjs2s,
828+
sgetsqrhrt,
829+
sorgtsqr_row
830+
);
831+
@lapackobjs2z = (@lapackobjs2z,
832+
zgetsqrhrt,
833+
zungtsqr_row
834+
);
835+
#functions added for lapack-3.11
836+
@lapackobjs2c = (@lapackobjs2c,
837+
cgedmd,
838+
cgedmdq
839+
);
840+
@lapackobjs2d = (@lapackobjs2d,
841+
dgedmd,
842+
dgedmdq
843+
);
844+
@lapackobjs2s = (@lapackobjs2s,
845+
sgedmd,
846+
sgedmdq
847+
);
848+
@lapackobjs2z = (@lapackobjs2z,
849+
zgedmd,
850+
zgedmdq
851+
);
852+
#functions added for lapack-3.12
853+
@lapackobjs2c = (@lapackobjs2c,
854+
cgelqs,
855+
cgelst,
856+
cgeqp3rk,
857+
cgeqrs,
858+
claqp2rk,
859+
claqp3rk,
860+
clatrs3,
861+
ctrsyl3,
862+
crscl,
863+
);
864+
@lapackobjs2d = (@lapackobjs2d,
865+
dgelqs,
866+
dgelst,
867+
dgeqp3rk,
868+
dgeqrs,
869+
dlaqp2rk,
870+
dlaqp3rk,
871+
dlatrs3,
872+
dtrsyl3,
873+
dlarmm,
874+
);
875+
@lapackobjs2s = (@lapackobjs2s,
876+
sgelqs,
877+
sgelst,
878+
sgeqp3rk,
879+
sgeqrs,
880+
slaqp2rk,
881+
slaqp3rk,
882+
slatrs3,
883+
strsyl3,
884+
slarmm,
885+
);
886+
@lapackobjs2z = (@lapackobjs2z,
887+
zgelqs,
888+
zgelst,
889+
zgeqp3rk,
890+
zgeqrs,
891+
zlaqp2rk,
892+
zlaqp3rk,
893+
zlatrs3,
894+
ztrsyl3,
895+
zrscl,
896+
);
817897

818898
@lapack_extendedprecision_objs = (
819899
zposvxx, clagge, clatms, chesvxx, cposvxx, cgesvxx, ssyrfssx, csyrfsx,
@@ -841,7 +921,8 @@ zpotri,
841921
dggsvp,
842922
dlahrd,
843923
dlatzm,
844-
dtzrqf);
924+
dtzrqf,
925+
);
845926

846927
@lapack_deprecated_objss = (
847928
sgelsx,
@@ -989,6 +1070,10 @@ zpotri,
9891070
LAPACKE_cgebrd_work,
9901071
LAPACKE_cgecon,
9911072
LAPACKE_cgecon_work,
1073+
LAPACKE_cgedmd,
1074+
LAPACKE_cgedmd_work,
1075+
LAPACKE_cgedmdq,
1076+
LAPACKE_cgedmdq_work,
9921077
LAPACKE_cgeequ,
9931078
LAPACKE_cgeequ_work,
9941079
LAPACKE_cgeequb,
@@ -1571,6 +1656,20 @@ zpotri,
15711656
LAPACKE_csytrf_aa_2stage_work,
15721657
LAPACKE_csytrs_aa_2stage,
15731658
LAPACKE_csytrs_aa_2stage_work,
1659+
LAPACKE_cgesvdq,
1660+
LAPACKE_cgesvdq_work,
1661+
LAPACKE_cgetsqrhrt,
1662+
LAPACKE_cgetsqrhrt_work,
1663+
LAPACKE_cungtsqr_row,
1664+
LAPACKE_cungtsqr_row_work,
1665+
LAPACKE_clangb,
1666+
LAPACKE_clangb_work,
1667+
LAPACKE_ctrsyl3,
1668+
LAPACKE_ctrsyl3_work,
1669+
LAPACKE_ctz_nancheck,
1670+
LAPACKE_ctz_trans,
1671+
LAPACKE_cunhr_col,
1672+
LAPACKE_cunhr_col_work,
15741673
);
15751674
@lapackeobjsd = (
15761675
LAPACKE_dgb_nancheck,
@@ -1641,6 +1740,10 @@ zpotri,
16411740
LAPACKE_dgebrd_work,
16421741
LAPACKE_dgecon,
16431742
LAPACKE_dgecon_work,
1743+
LAPACKE_dgedmd,
1744+
LAPACKE_dgedmd_work,
1745+
LAPACKE_dgedmdq,
1746+
LAPACKE_dgedmdq_work,
16441747
LAPACKE_dgeequ,
16451748
LAPACKE_dgeequ_work,
16461749
LAPACKE_dgeequb,
@@ -2179,6 +2282,18 @@ zpotri,
21792282
LAPACKE_dgesvdq_work,
21802283
LAPACKE_slag2d,
21812284
LAPACKE_slag2d_work,
2285+
LAPACKE_dgetsqrhrt,
2286+
LAPACKE_dgetsqrhrt_work,
2287+
LAPACKE_dorgtsqr_row,
2288+
LAPACKE_dorgtsqr_row_work,
2289+
LAPACKE_dlangb,
2290+
LAPACKE_dlangb_work,
2291+
LAPACKE_dorhr_col,
2292+
LAPACKE_dorhr_col_work,
2293+
LAPACKE_dtrsyl3,
2294+
LAPACKE_dtrsyl3_work,
2295+
LAPACKE_dtz_nancheck,
2296+
LAPACKE_dtz_trans,
21822297
);
21832298
@lapackeobjss = (
21842299
LAPACKE_sgb_nancheck,
@@ -2249,6 +2364,10 @@ zpotri,
22492364
LAPACKE_sgebrd_work,
22502365
LAPACKE_sgecon,
22512366
LAPACKE_sgecon_work,
2367+
LAPACKE_sgedmd,
2368+
LAPACKE_sgedmd_work,
2369+
LAPACKE_sgedmdq,
2370+
LAPACKE_sgedmdq_work,
22522371
LAPACKE_sgeequ,
22532372
LAPACKE_sgeequ_work,
22542373
LAPACKE_sgeequb,
@@ -2779,6 +2898,18 @@ zpotri,
27792898
LAPACKE_ssytrs_aa_2stage_work,
27802899
LAPACKE_sgesvdq,
27812900
LAPACKE_sgesvdq_work,
2901+
LAPACKE_sgetsqrhrt,
2902+
LAPACKE_sgetsqrhrt_work,
2903+
LAPACKE_sorgtsqr_row,
2904+
LAPACKE_sorgtsqr_row_work,
2905+
LAPACKE_slangb,
2906+
LAPACKE_slangb_work,
2907+
LAPACKE_sorhr_col,
2908+
LAPACKE_sorhr_col_work,
2909+
LAPACKE_strsyl3,
2910+
LAPACKE_strsyl3_work,
2911+
LAPACKE_stz_nancheck,
2912+
LAPACKE_stz_trans,
27822913
);
27832914
@lapackeobjsz = (
27842915
LAPACKE_zgb_nancheck,
@@ -2853,6 +2984,10 @@ zpotri,
28532984
LAPACKE_zgebrd_work,
28542985
LAPACKE_zgecon,
28552986
LAPACKE_zgecon_work,
2987+
LAPACKE_zgedmd,
2988+
LAPACKE_zgedmd_work,
2989+
LAPACKE_zgedmdq,
2990+
LAPACKE_zgedmdq_work,
28562991
LAPACKE_zgeequ,
28572992
LAPACKE_zgeequ_work,
28582993
LAPACKE_zgeequb,
@@ -3317,6 +3452,19 @@ zpotri,
33173452
LAPACKE_zupmtr_work,
33183453
LAPACKE_zsyr,
33193454
LAPACKE_zsyr_work,
3455+
LAPACKE_zgetsqrhrt,
3456+
LAPACKE_zgetsqrhrt_work,
3457+
LAPACKE_zungtsqr_row,
3458+
LAPACKE_zungtsqr_row_work,
3459+
LAPACKE_zlangb,
3460+
LAPACKE_zlangb_work,
3461+
LAPACKE_ztrsyl3,
3462+
LAPACKE_ztrsyl3_work,
3463+
LAPACKE_ztz_nancheck,
3464+
LAPACKE_ztz_trans,
3465+
LAPACKE_zunhr_col,
3466+
LAPACKE_zunhr_col_work,
3467+
33203468
## @(SRCX_OBJ) from `lapack-3.4.1/lapacke/src/Makefile`
33213469
## Not exported: requires LAPACKE_EXTENDED to be set and depends on the
33223470
## corresponding LAPACK extended precision routines.
@@ -3544,6 +3692,7 @@ zpotri,
35443692
ssysv_aa_2stage, ssytrf_aa_2stage,
35453693
ssytrs_aa_2stage,
35463694
slaorhr_col_getrfnp, slaorhr_col_getrfnp2, sorhr_col,
3695+
slarfb_gett,
35473696
);
35483697
@lapack_embeded_underscore_objs_c=(
35493698
chetf2_rook, chetrf_rook, chetri_rook,
@@ -3569,6 +3718,7 @@ zpotri,
35693718
csysv_aa_2stage, csytrf_aa_2stage,
35703719
csytrs_aa_2stage,
35713720
claunhr_col_getrfnp, claunhr_col_getrfnp2, cunhr_col,
3721+
clarfb_gett,
35723722
);
35733723
@lapack_embeded_underscore_objs_d=(
35743724
dlasyf_rook,
@@ -3586,6 +3736,7 @@ zpotri,
35863736
dsysv_aa_2stage,
35873737
dsytrf_aa_2stage, dsytrs_aa_2stage,
35883738
dlaorhr_col_getrfnp, dlaorhr_col_getrfnp2, dorhr_col,
3739+
dlarfb_gett,
35893740
);
35903741
@lapack_embeded_underscore_objs_z=(
35913742
zhetf2_rook, zhetrf_rook, zhetri_rook,
@@ -3609,7 +3760,8 @@ zpotri,
36093760
zhesv_aa_2stage, zhetrf_aa_2stage,
36103761
zhetrs_aa_2stage, zsysv_aa_2stage,
36113762
zsytrf_aa_2stage, zsytrs_aa_2stage,
3612-
zlaunhr_col_getrfnp, zlaunhr_col_getrfnp2, zunhr_col
3763+
zlaunhr_col_getrfnp, zlaunhr_col_getrfnp2, zunhr_col,
3764+
zlarfb_gett,
36133765
);
36143766

36153767

@@ -3930,6 +4082,18 @@ if ($ARGV[0] eq "linktest") {
39304082
@no_underscore_objs = (@no_underscore_objs, @misc_common_objs);
39314083

39324084
print "int main(void){\n";
4085+
foreach $objs (@underscore_objs) {
4086+
print "extern void ", $symbolprefix, $objs, $bu, $symbolsuffix, "();\n" if $objs ne "xerbla";
4087+
}
4088+
4089+
foreach $objs (@need_2underscore_objs) {
4090+
print "extern void ", $symbolprefix, $objs, $bu, $bu, $symbolsuffix, "();\n";
4091+
}
4092+
4093+
foreach $objs (@no_underscore_objs) {
4094+
print "extern void ", $symbolprefix, $objs, $symbolsuffix, "();\n";
4095+
}
4096+
39334097
foreach $objs (@underscore_objs) {
39344098
print $symbolprefix, $objs, $bu, $symbolsuffix, "();\n" if $objs ne "xerbla";
39354099
}

0 commit comments

Comments
 (0)