diff --git a/coreblas/eztrace_module/CMakeLists.txt b/coreblas/eztrace_module/CMakeLists.txt
new file mode 100644
index 0000000000000000000000000000000000000000..972ade489ed68dcb709aca78b5c0c7ab271281d1
--- /dev/null
+++ b/coreblas/eztrace_module/CMakeLists.txt
@@ -0,0 +1,78 @@
+###
+#
+# @copyright (c) 2009-2014 The University of Tennessee and The University
+# of Tennessee Research Foundation.
+# All rights reserved.
+# @copyright (c) 2012-2015 Inria. All rights reserved.
+# @copyright (c) 2012-2014 Bordeaux INP, CNRS (LaBRI UMR 5800), Inria, Univ. Bordeaux. All rights reserved.
+#
+###
+#
+# @file CMakeLists.txt
+#
+# @project MORSE
+# MORSE is a software package provided by:
+# Inria Bordeaux - Sud-Ouest,
+# Univ. of Tennessee,
+# King Abdullah Univesity of Science and Technology
+# Univ. of California Berkeley,
+# Univ. of Colorado Denver.
+#
+# @version 0.9.0
+# @author Florent Pruvost
+# @date 14-09-2015
+#
+###
+
+if (NOT EZTRACE_FOUND)
+ find_package(EZTRACE)
+endif()
+
+if (EZTRACE_FOUND AND EZTRACE_DIR_FOUND)
+
+ set(EZTRACE_eztrace_create_plugin_DIR "EZTRACE_eztrace_create_plugin_DIR-NOTFOUND")
+ find_path(EZTRACE_eztrace_create_plugin_DIR
+ NAMES eztrace_create_plugin
+ HINTS ${EZTRACE_DIR_FOUND}/bin)
+
+ if (EZTRACE_eztrace_create_plugin_DIR)
+
+ set(EZTRACE_CREATE_PLUGIN "${EZTRACE_eztrace_create_plugin_DIR}/eztrace_create_plugin")
+
+ add_custom_command(
+ OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/output
+ COMMAND ${EZTRACE_CREATE_PLUGIN}
+ ARGS ${CMAKE_CURRENT_SOURCE_DIR}/coreblas_eztrace_module
+ DEPENDS ${CMAKE_CURRENT_SOURCE_DIR}/coreblas_eztrace_module
+ )
+ add_custom_target(
+ eztrace-module-chameleon_cpu_func-dir ALL
+ DEPENDS ${CMAKE_CURRENT_BINARY_DIR}/output
+ )
+ add_custom_command(
+ OUTPUT libeztrace-autostart-chameleon_cpu_func.so libeztrace-chameleon_cpu_func.so libeztrace-convert-chameleon_cpu_func.so
+ COMMAND make
+ WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/output
+ DEPENDS ${CMAKE_CURRENT_BINARY_DIR}/output
+ )
+ add_custom_target(
+ eztrace-module-chameleon_cpu_func-libs ALL
+ DEPENDS libeztrace-autostart-chameleon_cpu_func.so libeztrace-chameleon_cpu_func.so libeztrace-convert-chameleon_cpu_func.so
+ )
+ # installation
+ # ------------
+ install(
+ FILES
+ ${CMAKE_CURRENT_BINARY_DIR}/output/libeztrace-autostart-chameleon_cpu_func.so
+ ${CMAKE_CURRENT_BINARY_DIR}/output/libeztrace-chameleon_cpu_func.so
+ ${CMAKE_CURRENT_BINARY_DIR}/output/libeztrace-convert-chameleon_cpu_func.so
+ DESTINATION ${EZTRACE_LIBRARY_DIRS}
+ )
+
+ endif (EZTRACE_eztrace_create_plugin_DIR)
+
+endif (EZTRACE_FOUND AND EZTRACE_DIR_FOUND)
+
+###
+### END CMakeLists.txt
+###
diff --git a/coreblas/eztrace_module/coreblas_eztrace_module b/coreblas/eztrace_module/coreblas_eztrace_module
new file mode 100644
index 0000000000000000000000000000000000000000..fbc4950c5324d0014fb59578d069e872eebe397e
--- /dev/null
+++ b/coreblas/eztrace_module/coreblas_eztrace_module
@@ -0,0 +1,1356 @@
+BEGIN_MODULE
+NAME chameleon_cpu_func
+DESC "Module for Chameleon CPU functions"
+ID 7770
+
+void CORE_scasum(int storev, int uplo, int M, int N,
+ void *A, int lda, float *work);
+void CORE_cbrdalg(int uplo, int N, int NB,
+ void *pA, void *C, void *S,
+ int i, int j, int m, int grsiz);
+int CORE_cgbelr(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+int CORE_cgbrce(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+int CORE_cgblrx(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+int CORE_cgeadd(int M, int N, void *alpha,
+ void *A, int LDA,
+ void *B, int LDB);
+int CORE_cgelqt(int M, int N, int IB,
+ void *A, int LDA,
+ void *T, int LDT,
+ void *TAU,
+ void *WORK);
+void CORE_cgemm(int transA, int transB,
+ int M, int N, int K,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB,
+ void *beta, void *C, int LDC);
+int CORE_cgeqrt(int M, int N, int IB,
+ void *A, int LDA,
+ void *T, int LDT,
+ void *TAU, void *WORK);
+int CORE_cgesplit(int side, int diag,
+ int M, int N,
+ void *A, int LDA,
+ void *B, int LDB);
+int CORE_cgessm(int M, int N, int K, int IB,
+ const int *IPIV,
+ void *L, int LDL,
+ void *A, int LDA);
+int CORE_cgessq(int M, int N,
+ void *A, int LDA,
+ float *scale, float *sumsq);
+int CORE_cgetf2_nopiv(int M, int N,
+ void *A, int LDA);
+int CORE_cgetrf(int M, int N,
+ void *A, int LDA,
+ int *IPIV, int *INFO);
+int CORE_cgetrf_incpiv(int M, int N, int IB,
+ void *A, int LDA,
+ int *IPIV, int *INFO);
+int CORE_cgetrf_nopiv(int M, int N, int IB,
+ void *A, int LDA,
+ int *INFO);
+int CORE_cgetrf_reclap(int M, int N,
+ void *A, int LDA,
+ int *IPIV, int *info);
+int CORE_cgetrf_rectil(void *A, int *IPIV, int *info);
+void CORE_cgetrip(int m, int n, void *A,
+ void *work);
+int CORE_chbelr(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+int CORE_chblrx(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+int CORE_chbrce(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+void CORE_chbtype1cb(int N, int NB,
+ void *A, int LDA,
+ void *V, void *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ void *WORK);
+void CORE_chbtype2cb(int N, int NB,
+ void *A, int LDA,
+ void *V, void *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ void *WORK);
+void CORE_chbtype3cb(int N, int NB,
+ void *A, int LDA,
+ void *V, void *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ void *WORK);
+void CORE_chegst(int itype, int uplo, int N,
+ void *A, int LDA,
+ void *B, int LDB, int *INFO);
+
+void CORE_chemm(int side, int uplo,
+ int M, int N,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB,
+ void *beta, void *C, int LDC);
+void CORE_cherk(int uplo, int trans,
+ int N, int K,
+ float alpha, void *A, int LDA,
+ float beta, void *C, int LDC);
+void CORE_cher2k(int uplo, int trans,
+ int N, int K,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB,
+ float beta, void *C, int LDC);
+int CORE_chessq(int uplo, int N,
+ void *A, int LDA,
+ float *scale, float *sumsq);
+
+int CORE_cherfb(int uplo, int N, int K, int IB, int NB,
+ void *A, int LDA,
+ void *T, int LDT,
+ void *C, int LDC,
+ void *WORK, int LDWORK);
+void CORE_clacpy(int uplo, int M, int N,
+ void *A, int LDA,
+ void *B, int LDB);
+void CORE_clange(int norm, int M, int N,
+ void *A, int LDA,
+ float *work, float *normA);
+
+void CORE_clanhe(int norm, int uplo, int N,
+ void *A, int LDA,
+ float *work, float *normA);
+
+void CORE_clansy(int norm, int uplo, int N,
+ void *A, int LDA,
+ float *work, float *normA);
+void CORE_clantr(int norm, int uplo, int diag, int M, int N,
+ void *A, int LDA,
+ float *work, float *normA);
+int CORE_clarfb_gemm(int side, int trans, int direct, int storev,
+ int M, int N, int K,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *C, int LDC,
+ void *WORK, int LDWORK);
+int CORE_clarfx2(int side, int N,
+ void *V,
+ void *TAU,
+ void *C1, int LDC1,
+ void *C2, int LDC2);
+int CORE_clarfx2c(int uplo,
+ void *V,
+ void *TAU,
+ void *C1,
+ void *C2,
+ void *C3);
+int CORE_clarfx2ce(int uplo,
+ void *V,
+ void *TAU,
+ void *C1,
+ void *C2,
+ void *C3);
+void CORE_clarfy(int N,
+ void *A, int LDA,
+ void *V,
+ void *TAU,
+ void *WORK);
+void CORE_claset(int uplo, int n1, int n2,
+ void *alpha, void *beta,
+ void *tileA, int ldtilea);
+void CORE_claset2(int uplo, int n1, int n2, void *alpha,
+ void *tileA, int ldtilea);
+void CORE_claswp(int N, void *A, int LDA,
+ int I1, int I2, const int *IPIV, int INC);
+int CORE_claswp_ontile( void *descA, int i1, int i2, const int *ipiv, int inc);
+int CORE_claswpc_ontile(void *descA, int i1, int i2, const int *ipiv, int inc);
+int CORE_clatro(int uplo, int trans,
+ int M, int N,
+ void *A, int LDA,
+ void *B, int LDB);
+void CORE_clauum(int uplo, int N, void *A, int LDA);
+int CORE_cpamm(int op, int side, int storev,
+ int M, int N, int K, int L,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *W, int LDW);
+int CORE_cparfb(int side, int trans, int direct, int storev,
+ int M1, int N1, int M2, int N2, int K, int L,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *WORK, int LDWORK);
+int CORE_cpemv(int trans, int storev,
+ int M, int N, int L,
+ void *ALPHA,
+ void *A, int LDA,
+ void *X, int INCX,
+ void *BETA,
+ void *Y, int INCY,
+ void *WORK);
+void CORE_cplghe(float bump, int m, int n, void *A, int lda,
+ int bigM, int m0, int n0, unsigned long long int seed );
+void CORE_cplgsy(void *bump, int m, int n, void *A, int lda,
+ int bigM, int m0, int n0, unsigned long long int seed );
+void CORE_cplrnt(int m, int n, void *A, int lda,
+ int bigM, int m0, int n0, unsigned long long int seed );
+void CORE_cpotrf(int uplo, int N, void *A, int LDA, int *INFO);
+void CORE_cshift(int s, int m, int n, int L,
+ void *A);
+void CORE_cshiftw(int s, int cl, int m, int n, int L,
+ void *A, void *W);
+int CORE_cssssm(int M1, int N1, int M2, int N2, int K, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *L1, int LDL1,
+ void *L2, int LDL2,
+ const int *IPIV);
+void CORE_csymm(int side, int uplo,
+ int M, int N,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB,
+ void *beta, void *C, int LDC);
+void CORE_csyrk(int uplo, int trans,
+ int N, int K,
+ void *alpha, void *A, int LDA,
+ void *beta, void *C, int LDC);
+void CORE_csyr2k(int uplo, int trans,
+ int N, int K,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB,
+ void *beta, void *C, int LDC);
+int CORE_csyssq(int uplo, int N,
+ void *A, int LDA,
+ float *scale, float *sumsq);
+int CORE_csytf2_nopiv(int uplo, int n, void *A, int lda);
+void CORE_cswpab(int i, int n1, int n2,
+ void *A, void *work);
+int CORE_cswptr_ontile(void *descA, int i1, int i2, const int *ipiv, int inc,
+ void *Akk, int ldak);
+void CORE_ctrdalg(int uplo, int N, int NB,
+ void *pA, void *V, void *TAU,
+ int i, int j, int m, int grsiz);
+void CORE_ctrmm(int side, int uplo,
+ int transA, int diag,
+ int M, int N,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB);
+void CORE_ctrsm(int side, int uplo,
+ int transA, int diag,
+ int M, int N,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB);
+void CORE_ctrtri(int uplo, int diag, int N,
+ void *A, int LDA, int *info);
+int CORE_ctslqt(int M, int N, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *T, int LDT,
+ void *TAU, void *WORK);
+int CORE_ctsmlq(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *WORK, int LDWORK);
+int CORE_ctsmlq_corner( int m1, int n1, int m2, int n2, int m3, int n3,
+ int k, int ib, int nb,
+ void *A1, int lda1,
+ void *A2, int lda2,
+ void *A3, int lda3,
+ void *V, int ldv,
+ void *T, int ldt,
+ void *WORK, int ldwork);
+int CORE_ctsmlq_hetra1( int side, int trans,
+ int m1, int n1, int m2, int n2,
+ int k, int ib,
+ void *A1, int lda1,
+ void *A2, int lda2,
+ void *V, int ldv,
+ void *T, int ldt,
+ void *WORK, int ldwork);
+int CORE_ctsmqr(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *WORK, int LDWORK);
+int CORE_ctsmqr_corner( int m1, int n1, int m2, int n2, int m3, int n3,
+ int k, int ib, int nb,
+ void *A1, int lda1,
+ void *A2, int lda2,
+ void *A3, int lda3,
+ void *V, int ldv,
+ void *T, int ldt,
+ void *WORK, int ldwork);
+int CORE_ctsmqr_hetra1( int side, int trans,
+ int m1, int n1, int m2, int n2,
+ int k, int ib,
+ void *A1, int lda1,
+ void *A2, int lda2,
+ void *V, int ldv,
+ void *T, int ldt,
+ void *WORK, int ldwork);
+int CORE_ctsqrt(int M, int N, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *T, int LDT,
+ void *TAU, void *WORK);
+int CORE_ctstrf(int M, int N, int IB, int NB,
+ void *U, int LDU,
+ void *A, int LDA,
+ void *L, int LDL,
+ int *IPIV, void *WORK,
+ int LDWORK, int *INFO);
+int CORE_cttmqr(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *WORK, int LDWORK);
+int CORE_cttqrt(int M, int N, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *T, int LDT,
+ void *TAU,
+ void *WORK);
+int CORE_cttmlq(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *WORK, int LDWORK);
+int CORE_cttlqt(int M, int N, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *T, int LDT,
+ void *TAU,
+ void *WORK);
+int CORE_cunmlq(int side, int trans,
+ int M, int N, int IB, int K,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *C, int LDC,
+ void *WORK, int LDWORK);
+int CORE_cunmqr(int side, int trans,
+ int M, int N, int K, int IB,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *C, int LDC,
+ void *WORK, int LDWORK);
+
+void CORE_dasum(int storev, int uplo, int M, int N,
+ const double *A, int lda, double *work);
+void CORE_dbrdalg(int uplo, int N, int NB,
+ void *pA, double *C, double *S,
+ int i, int j, int m, int grsiz);
+int CORE_dgbelr(int uplo, int N,
+ void **A, double *V, double *TAU,
+ int st, int ed, int eltsize);
+int CORE_dgbrce(int uplo, int N,
+ void **A, double *V, double *TAU,
+ int st, int ed, int eltsize);
+int CORE_dgblrx(int uplo, int N,
+ void **A, double *V, double *TAU,
+ int st, int ed, int eltsize);
+int CORE_dgeadd(int M, int N, double alpha,
+ const double *A, int LDA,
+ double *B, int LDB);
+int CORE_dgelqt(int M, int N, int IB,
+ double *A, int LDA,
+ double *T, int LDT,
+ double *TAU,
+ double *WORK);
+void CORE_dgemm(int transA, int transB,
+ int M, int N, int K,
+ double alpha, const double *A, int LDA,
+ const double *B, int LDB,
+ double beta, double *C, int LDC);
+int CORE_dgeqrt(int M, int N, int IB,
+ double *A, int LDA,
+ double *T, int LDT,
+ double *TAU, double *WORK);
+int CORE_dgesplit(int side, int diag,
+ int M, int N,
+ double *A, int LDA,
+ double *B, int LDB);
+int CORE_dgessm(int M, int N, int K, int IB,
+ const int *IPIV,
+ const double *L, int LDL,
+ double *A, int LDA);
+int CORE_dgessq(int M, int N,
+ const double *A, int LDA,
+ double *scale, double *sumsq);
+int CORE_dgetf2_nopiv(int M, int N,
+ double *A, int LDA);
+int CORE_dgetrf(int M, int N,
+ double *A, int LDA,
+ int *IPIV, int *INFO);
+int CORE_dgetrf_incpiv(int M, int N, int IB,
+ double *A, int LDA,
+ int *IPIV, int *INFO);
+int CORE_dgetrf_nopiv(int M, int N, int IB,
+ double *A, int LDA,
+ int *INFO);
+int CORE_dgetrf_reclap(int M, int N,
+ double *A, int LDA,
+ int *IPIV, int *info);
+int CORE_dgetrf_rectil(void *A, int *IPIV, int *info);
+void CORE_dgetrip(int m, int n, double *A,
+ double *work);
+int CORE_dhbelr(int uplo, int N,
+ void **A, double *V, double *TAU,
+ int st, int ed, int eltsize);
+int CORE_dhblrx(int uplo, int N,
+ void **A, double *V, double *TAU,
+ int st, int ed, int eltsize);
+int CORE_dhbrce(int uplo, int N,
+ void **A, double *V, double *TAU,
+ int st, int ed, int eltsize);
+void CORE_dhbtype1cb(int N, int NB,
+ double *A, int LDA,
+ double *V, double *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ double *WORK);
+void CORE_dhbtype2cb(int N, int NB,
+ double *A, int LDA,
+ double *V, double *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ double *WORK);
+void CORE_dhbtype3cb(int N, int NB,
+ double *A, int LDA,
+ const double *V, const double *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ double *WORK);
+void CORE_dsygst(int itype, int uplo, int N,
+ double *A, int LDA,
+ double *B, int LDB, int *INFO);
+
+void CORE_dsymm(int side, int uplo,
+ int M, int N,
+ double alpha, const double *A, int LDA,
+ const double *B, int LDB,
+ double beta, double *C, int LDC);
+void CORE_dsyrk(int uplo, int trans,
+ int N, int K,
+ double alpha, const double *A, int LDA,
+ double beta, double *C, int LDC);
+void CORE_dsyr2k(int uplo, int trans,
+ int N, int K,
+ double alpha, const double *A, int LDA,
+ const double *B, int LDB,
+ double beta, double *C, int LDC);
+int CORE_dsyssq(int uplo, int N,
+ const double *A, int LDA,
+ double *scale, double *sumsq);
+
+int CORE_dsyrfb(int uplo, int N, int K, int IB, int NB,
+ const double *A, int LDA,
+ const double *T, int LDT,
+ double *C, int LDC,
+ double *WORK, int LDWORK);
+void CORE_dlacpy(int uplo, int M, int N,
+ const double *A, int LDA,
+ double *B, int LDB);
+void CORE_dlange(int norm, int M, int N,
+ const double *A, int LDA,
+ double *work, double *normA);
+
+void CORE_dlansy(int norm, int uplo, int N,
+ const double *A, int LDA,
+ double *work, double *normA);
+
+void CORE_dlantr(int norm, int uplo, int diag, int M, int N,
+ const double *A, int LDA,
+ double *work, double *normA);
+int CORE_dlarfb_gemm(int side, int trans, int direct, int storev,
+ int M, int N, int K,
+ const double *V, int LDV,
+ const double *T, int LDT,
+ double *C, int LDC,
+ double *WORK, int LDWORK);
+int CORE_dlarfx2(int side, int N,
+ double V,
+ double TAU,
+ double *C1, int LDC1,
+ double *C2, int LDC2);
+int CORE_dlarfx2c(int uplo,
+ double V,
+ double TAU,
+ double *C1,
+ double *C2,
+ double *C3);
+int CORE_dlarfx2ce(int uplo,
+ double *V,
+ double *TAU,
+ double *C1,
+ double *C2,
+ double *C3);
+void CORE_dlarfy(int N,
+ double *A, int LDA,
+ const double *V,
+ const double *TAU,
+ double *WORK);
+void CORE_dlaset(int uplo, int n1, int n2,
+ double alpha, double beta,
+ double *tileA, int ldtilea);
+void CORE_dlaset2(int uplo, int n1, int n2, double alpha,
+ double *tileA, int ldtilea);
+void CORE_dlaswp(int N, double *A, int LDA,
+ int I1, int I2, const int *IPIV, int INC);
+int CORE_dlaswp_ontile( void *descA, int i1, int i2, const int *ipiv, int inc);
+int CORE_dlaswpc_ontile(void *descA, int i1, int i2, const int *ipiv, int inc);
+int CORE_dlatro(int uplo, int trans,
+ int M, int N,
+ const double *A, int LDA,
+ double *B, int LDB);
+void CORE_dlauum(int uplo, int N, double *A, int LDA);
+int CORE_dpamm(int op, int side, int storev,
+ int M, int N, int K, int L,
+ const double *A1, int LDA1,
+ double *A2, int LDA2,
+ const double *V, int LDV,
+ double *W, int LDW);
+int CORE_dparfb(int side, int trans, int direct, int storev,
+ int M1, int N1, int M2, int N2, int K, int L,
+ double *A1, int LDA1,
+ double *A2, int LDA2,
+ const double *V, int LDV,
+ const double *T, int LDT,
+ double *WORK, int LDWORK);
+int CORE_dpemv(int trans, int storev,
+ int M, int N, int L,
+ double ALPHA,
+ const double *A, int LDA,
+ const double *X, int INCX,
+ double BETA,
+ double *Y, int INCY,
+ double *WORK);
+void CORE_dplgsy(double bump, int m, int n, double *A, int lda,
+ int bigM, int m0, int n0, unsigned long long int seed );
+void CORE_dplrnt(int m, int n, double *A, int lda,
+ int bigM, int m0, int n0, unsigned long long int seed );
+void CORE_dpotrf(int uplo, int N, double *A, int LDA, int *INFO);
+void CORE_dshift(int s, int m, int n, int L,
+ double *A);
+void CORE_dshiftw(int s, int cl, int m, int n, int L,
+ double *A, double *W);
+int CORE_dssssm(int M1, int N1, int M2, int N2, int K, int IB,
+ double *A1, int LDA1,
+ double *A2, int LDA2,
+ const double *L1, int LDL1,
+ const double *L2, int LDL2,
+ const int *IPIV);
+int CORE_dsytf2_nopiv(int uplo, int n, double *A, int lda);
+void CORE_dswpab(int i, int n1, int n2,
+ double *A, double *work);
+int CORE_dswptr_ontile(void *descA, int i1, int i2, const int *ipiv, int inc,
+ const double *Akk, int ldak);
+void CORE_dtrdalg(int uplo, int N, int NB,
+ void *pA, double *V, double *TAU,
+ int i, int j, int m, int grsiz);
+void CORE_dtrmm(int side, int uplo,
+ int transA, int diag,
+ int M, int N,
+ double alpha, const double *A, int LDA,
+ double *B, int LDB);
+void CORE_dtrsm(int side, int uplo,
+ int transA, int diag,
+ int M, int N,
+ double alpha, const double *A, int LDA,
+ double *B, int LDB);
+void CORE_dtrtri(int uplo, int diag, int N,
+ double *A, int LDA, int *info);
+int CORE_dtslqt(int M, int N, int IB,
+ double *A1, int LDA1,
+ double *A2, int LDA2,
+ double *T, int LDT,
+ double *TAU, double *WORK);
+int CORE_dtsmlq(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ double *A1, int LDA1,
+ double *A2, int LDA2,
+ const double *V, int LDV,
+ const double *T, int LDT,
+ double *WORK, int LDWORK);
+int CORE_dtsmlq_corner( int m1, int n1, int m2, int n2, int m3, int n3,
+ int k, int ib, int nb,
+ double *A1, int lda1,
+ double *A2, int lda2,
+ double *A3, int lda3,
+ const double *V, int ldv,
+ const double *T, int ldt,
+ double *WORK, int ldwork);
+int CORE_dtsmlq_sytra1( int side, int trans,
+ int m1, int n1, int m2, int n2,
+ int k, int ib,
+ double *A1, int lda1,
+ double *A2, int lda2,
+ const double *V, int ldv,
+ const double *T, int ldt,
+ double *WORK, int ldwork);
+int CORE_dtsmqr(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ double *A1, int LDA1,
+ double *A2, int LDA2,
+ const double *V, int LDV,
+ const double *T, int LDT,
+ double *WORK, int LDWORK);
+int CORE_dtsmqr_corner( int m1, int n1, int m2, int n2, int m3, int n3,
+ int k, int ib, int nb,
+ double *A1, int lda1,
+ double *A2, int lda2,
+ double *A3, int lda3,
+ const double *V, int ldv,
+ const double *T, int ldt,
+ double *WORK, int ldwork);
+int CORE_dtsmqr_sytra1( int side, int trans,
+ int m1, int n1, int m2, int n2,
+ int k, int ib,
+ double *A1, int lda1,
+ double *A2, int lda2,
+ const double *V, int ldv,
+ const double *T, int ldt,
+ double *WORK, int ldwork);
+int CORE_dtsqrt(int M, int N, int IB,
+ double *A1, int LDA1,
+ double *A2, int LDA2,
+ double *T, int LDT,
+ double *TAU, double *WORK);
+int CORE_dtstrf(int M, int N, int IB, int NB,
+ double *U, int LDU,
+ double *A, int LDA,
+ double *L, int LDL,
+ int *IPIV, double *WORK,
+ int LDWORK, int *INFO);
+int CORE_dttmqr(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ double *A1, int LDA1,
+ double *A2, int LDA2,
+ const double *V, int LDV,
+ const double *T, int LDT,
+ double *WORK, int LDWORK);
+int CORE_dttqrt(int M, int N, int IB,
+ double *A1, int LDA1,
+ double *A2, int LDA2,
+ double *T, int LDT,
+ double *TAU,
+ double *WORK);
+int CORE_dttmlq(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ double *A1, int LDA1,
+ double *A2, int LDA2,
+ const double *V, int LDV,
+ const double *T, int LDT,
+ double *WORK, int LDWORK);
+int CORE_dttlqt(int M, int N, int IB,
+ double *A1, int LDA1,
+ double *A2, int LDA2,
+ double *T, int LDT,
+ double *TAU,
+ double *WORK);
+int CORE_dormlq(int side, int trans,
+ int M, int N, int IB, int K,
+ const double *V, int LDV,
+ const double *T, int LDT,
+ double *C, int LDC,
+ double *WORK, int LDWORK);
+int CORE_dormqr(int side, int trans,
+ int M, int N, int K, int IB,
+ const double *V, int LDV,
+ const double *T, int LDT,
+ double *C, int LDC,
+ double *WORK, int LDWORK);
+
+void CORE_slag2d(int m, int n,
+ const float *A, int lda,
+ double *B, int ldb);
+void CORE_dlag2s(int m, int n,
+ const double *A, int lda,
+ float *B, int ldb, int *info);
+
+void CORE_sasum(int storev, int uplo, int M, int N,
+ const float *A, int lda, float *work);
+void CORE_sbrdalg(int uplo, int N, int NB,
+ void *pA, float *C, float *S,
+ int i, int j, int m, int grsiz);
+int CORE_sgbelr(int uplo, int N,
+ void **A, float *V, float *TAU,
+ int st, int ed, int eltsize);
+int CORE_sgbrce(int uplo, int N,
+ void **A, float *V, float *TAU,
+ int st, int ed, int eltsize);
+int CORE_sgblrx(int uplo, int N,
+ void **A, float *V, float *TAU,
+ int st, int ed, int eltsize);
+int CORE_sgeadd(int M, int N, float alpha,
+ const float *A, int LDA,
+ float *B, int LDB);
+int CORE_sgelqt(int M, int N, int IB,
+ float *A, int LDA,
+ float *T, int LDT,
+ float *TAU,
+ float *WORK);
+void CORE_sgemm(int transA, int transB,
+ int M, int N, int K,
+ float alpha, const float *A, int LDA,
+ const float *B, int LDB,
+ float beta, float *C, int LDC);
+int CORE_sgeqrt(int M, int N, int IB,
+ float *A, int LDA,
+ float *T, int LDT,
+ float *TAU, float *WORK);
+int CORE_sgesplit(int side, int diag,
+ int M, int N,
+ float *A, int LDA,
+ float *B, int LDB);
+int CORE_sgessm(int M, int N, int K, int IB,
+ const int *IPIV,
+ const float *L, int LDL,
+ float *A, int LDA);
+int CORE_sgessq(int M, int N,
+ const float *A, int LDA,
+ float *scale, float *sumsq);
+int CORE_sgetf2_nopiv(int M, int N,
+ float *A, int LDA);
+int CORE_sgetrf(int M, int N,
+ float *A, int LDA,
+ int *IPIV, int *INFO);
+int CORE_sgetrf_incpiv(int M, int N, int IB,
+ float *A, int LDA,
+ int *IPIV, int *INFO);
+int CORE_sgetrf_nopiv(int M, int N, int IB,
+ float *A, int LDA,
+ int *INFO);
+int CORE_sgetrf_reclap(int M, int N,
+ float *A, int LDA,
+ int *IPIV, int *info);
+int CORE_sgetrf_rectil(void *A, int *IPIV, int *info);
+void CORE_sgetrip(int m, int n, float *A,
+ float *work);
+int CORE_shbelr(int uplo, int N,
+ void **A, float *V, float *TAU,
+ int st, int ed, int eltsize);
+int CORE_shblrx(int uplo, int N,
+ void **A, float *V, float *TAU,
+ int st, int ed, int eltsize);
+int CORE_shbrce(int uplo, int N,
+ void **A, float *V, float *TAU,
+ int st, int ed, int eltsize);
+void CORE_shbtype1cb(int N, int NB,
+ float *A, int LDA,
+ float *V, float *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ float *WORK);
+void CORE_shbtype2cb(int N, int NB,
+ float *A, int LDA,
+ float *V, float *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ float *WORK);
+void CORE_shbtype3cb(int N, int NB,
+ float *A, int LDA,
+ const float *V, const float *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ float *WORK);
+void CORE_ssygst(int itype, int uplo, int N,
+ float *A, int LDA,
+ float *B, int LDB, int *INFO);
+
+void CORE_ssymm(int side, int uplo,
+ int M, int N,
+ float alpha, const float *A, int LDA,
+ const float *B, int LDB,
+ float beta, float *C, int LDC);
+void CORE_ssyrk(int uplo, int trans,
+ int N, int K,
+ float alpha, const float *A, int LDA,
+ float beta, float *C, int LDC);
+void CORE_ssyr2k(int uplo, int trans,
+ int N, int K,
+ float alpha, const float *A, int LDA,
+ const float *B, int LDB,
+ float beta, float *C, int LDC);
+int CORE_ssyssq(int uplo, int N,
+ const float *A, int LDA,
+ float *scale, float *sumsq);
+
+int CORE_ssyrfb(int uplo, int N, int K, int IB, int NB,
+ const float *A, int LDA,
+ const float *T, int LDT,
+ float *C, int LDC,
+ float *WORK, int LDWORK);
+void CORE_slacpy(int uplo, int M, int N,
+ const float *A, int LDA,
+ float *B, int LDB);
+void CORE_slange(int norm, int M, int N,
+ const float *A, int LDA,
+ float *work, float *normA);
+
+void CORE_slansy(int norm, int uplo, int N,
+ const float *A, int LDA,
+ float *work, float *normA);
+
+void CORE_slantr(int norm, int uplo, int diag, int M, int N,
+ const float *A, int LDA,
+ float *work, float *normA);
+int CORE_slarfb_gemm(int side, int trans, int direct, int storev,
+ int M, int N, int K,
+ const float *V, int LDV,
+ const float *T, int LDT,
+ float *C, int LDC,
+ float *WORK, int LDWORK);
+int CORE_slarfx2(int side, int N,
+ float V,
+ float TAU,
+ float *C1, int LDC1,
+ float *C2, int LDC2);
+int CORE_slarfx2c(int uplo,
+ float V,
+ float TAU,
+ float *C1,
+ float *C2,
+ float *C3);
+int CORE_slarfx2ce(int uplo,
+ float *V,
+ float *TAU,
+ float *C1,
+ float *C2,
+ float *C3);
+void CORE_slarfy(int N,
+ float *A, int LDA,
+ const float *V,
+ const float *TAU,
+ float *WORK);
+void CORE_slaset(int uplo, int n1, int n2,
+ float alpha, float beta,
+ float *tileA, int ldtilea);
+void CORE_slaset2(int uplo, int n1, int n2, float alpha,
+ float *tileA, int ldtilea);
+void CORE_slaswp(int N, float *A, int LDA,
+ int I1, int I2, const int *IPIV, int INC);
+int CORE_slaswp_ontile( void *descA, int i1, int i2, const int *ipiv, int inc);
+int CORE_slaswpc_ontile(void *descA, int i1, int i2, const int *ipiv, int inc);
+int CORE_slatro(int uplo, int trans,
+ int M, int N,
+ const float *A, int LDA,
+ float *B, int LDB);
+void CORE_slauum(int uplo, int N, float *A, int LDA);
+int CORE_spamm(int op, int side, int storev,
+ int M, int N, int K, int L,
+ const float *A1, int LDA1,
+ float *A2, int LDA2,
+ const float *V, int LDV,
+ float *W, int LDW);
+int CORE_sparfb(int side, int trans, int direct, int storev,
+ int M1, int N1, int M2, int N2, int K, int L,
+ float *A1, int LDA1,
+ float *A2, int LDA2,
+ const float *V, int LDV,
+ const float *T, int LDT,
+ float *WORK, int LDWORK);
+int CORE_spemv(int trans, int storev,
+ int M, int N, int L,
+ float ALPHA,
+ const float *A, int LDA,
+ const float *X, int INCX,
+ float BETA,
+ float *Y, int INCY,
+ float *WORK);
+void CORE_splgsy(float bump, int m, int n, float *A, int lda,
+ int bigM, int m0, int n0, unsigned long long int seed );
+void CORE_splrnt(int m, int n, float *A, int lda,
+ int bigM, int m0, int n0, unsigned long long int seed );
+void CORE_spotrf(int uplo, int N, float *A, int LDA, int *INFO);
+void CORE_sshift(int s, int m, int n, int L,
+ float *A);
+void CORE_sshiftw(int s, int cl, int m, int n, int L,
+ float *A, float *W);
+int CORE_sssssm(int M1, int N1, int M2, int N2, int K, int IB,
+ float *A1, int LDA1,
+ float *A2, int LDA2,
+ const float *L1, int LDL1,
+ const float *L2, int LDL2,
+ const int *IPIV);
+int CORE_ssytf2_nopiv(int uplo, int n, float *A, int lda);
+void CORE_sswpab(int i, int n1, int n2,
+ float *A, float *work);
+int CORE_sswptr_ontile(void *descA, int i1, int i2, const int *ipiv, int inc,
+ const float *Akk, int ldak);
+void CORE_strdalg(int uplo, int N, int NB,
+ void *pA, float *V, float *TAU,
+ int i, int j, int m, int grsiz);
+void CORE_strmm(int side, int uplo,
+ int transA, int diag,
+ int M, int N,
+ float alpha, const float *A, int LDA,
+ float *B, int LDB);
+void CORE_strsm(int side, int uplo,
+ int transA, int diag,
+ int M, int N,
+ float alpha, const float *A, int LDA,
+ float *B, int LDB);
+void CORE_strtri(int uplo, int diag, int N,
+ float *A, int LDA, int *info);
+int CORE_stslqt(int M, int N, int IB,
+ float *A1, int LDA1,
+ float *A2, int LDA2,
+ float *T, int LDT,
+ float *TAU, float *WORK);
+int CORE_stsmlq(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ float *A1, int LDA1,
+ float *A2, int LDA2,
+ const float *V, int LDV,
+ const float *T, int LDT,
+ float *WORK, int LDWORK);
+int CORE_stsmlq_corner( int m1, int n1, int m2, int n2, int m3, int n3,
+ int k, int ib, int nb,
+ float *A1, int lda1,
+ float *A2, int lda2,
+ float *A3, int lda3,
+ const float *V, int ldv,
+ const float *T, int ldt,
+ float *WORK, int ldwork);
+int CORE_stsmlq_sytra1( int side, int trans,
+ int m1, int n1, int m2, int n2,
+ int k, int ib,
+ float *A1, int lda1,
+ float *A2, int lda2,
+ const float *V, int ldv,
+ const float *T, int ldt,
+ float *WORK, int ldwork);
+int CORE_stsmqr(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ float *A1, int LDA1,
+ float *A2, int LDA2,
+ const float *V, int LDV,
+ const float *T, int LDT,
+ float *WORK, int LDWORK);
+int CORE_stsmqr_corner( int m1, int n1, int m2, int n2, int m3, int n3,
+ int k, int ib, int nb,
+ float *A1, int lda1,
+ float *A2, int lda2,
+ float *A3, int lda3,
+ const float *V, int ldv,
+ const float *T, int ldt,
+ float *WORK, int ldwork);
+int CORE_stsmqr_sytra1( int side, int trans,
+ int m1, int n1, int m2, int n2,
+ int k, int ib,
+ float *A1, int lda1,
+ float *A2, int lda2,
+ const float *V, int ldv,
+ const float *T, int ldt,
+ float *WORK, int ldwork);
+int CORE_stsqrt(int M, int N, int IB,
+ float *A1, int LDA1,
+ float *A2, int LDA2,
+ float *T, int LDT,
+ float *TAU, float *WORK);
+int CORE_ststrf(int M, int N, int IB, int NB,
+ float *U, int LDU,
+ float *A, int LDA,
+ float *L, int LDL,
+ int *IPIV, float *WORK,
+ int LDWORK, int *INFO);
+int CORE_sttmqr(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ float *A1, int LDA1,
+ float *A2, int LDA2,
+ const float *V, int LDV,
+ const float *T, int LDT,
+ float *WORK, int LDWORK);
+int CORE_sttqrt(int M, int N, int IB,
+ float *A1, int LDA1,
+ float *A2, int LDA2,
+ float *T, int LDT,
+ float *TAU,
+ float *WORK);
+int CORE_sttmlq(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ float *A1, int LDA1,
+ float *A2, int LDA2,
+ const float *V, int LDV,
+ const float *T, int LDT,
+ float *WORK, int LDWORK);
+int CORE_sttlqt(int M, int N, int IB,
+ float *A1, int LDA1,
+ float *A2, int LDA2,
+ float *T, int LDT,
+ float *TAU,
+ float *WORK);
+int CORE_sormlq(int side, int trans,
+ int M, int N, int IB, int K,
+ const float *V, int LDV,
+ const float *T, int LDT,
+ float *C, int LDC,
+ float *WORK, int LDWORK);
+int CORE_sormqr(int side, int trans,
+ int M, int N, int K, int IB,
+ const float *V, int LDV,
+ const float *T, int LDT,
+ float *C, int LDC,
+ float *WORK, int LDWORK);
+
+void CORE_dzasum(int storev, int uplo, int M, int N,
+ void *A, int lda, double *work);
+void CORE_zbrdalg(int uplo, int N, int NB,
+ void *pA, void *C, void *S,
+ int i, int j, int m, int grsiz);
+int CORE_zgbelr(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+int CORE_zgbrce(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+int CORE_zgblrx(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+int CORE_zgeadd(int M, int N, void *alpha,
+ void *A, int LDA,
+ void *B, int LDB);
+int CORE_zgelqt(int M, int N, int IB,
+ void *A, int LDA,
+ void *T, int LDT,
+ void *TAU,
+ void *WORK);
+void CORE_zgemm(int transA, int transB,
+ int M, int N, int K,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB,
+ void *beta, void *C, int LDC);
+int CORE_zgeqrt(int M, int N, int IB,
+ void *A, int LDA,
+ void *T, int LDT,
+ void *TAU, void *WORK);
+int CORE_zgesplit(int side, int diag,
+ int M, int N,
+ void *A, int LDA,
+ void *B, int LDB);
+int CORE_zgessm(int M, int N, int K, int IB,
+ const int *IPIV,
+ void *L, int LDL,
+ void *A, int LDA);
+int CORE_zgessq(int M, int N,
+ void *A, int LDA,
+ double *scale, double *sumsq);
+int CORE_zgetf2_nopiv(int M, int N,
+ void *A, int LDA);
+int CORE_zgetrf(int M, int N,
+ void *A, int LDA,
+ int *IPIV, int *INFO);
+int CORE_zgetrf_incpiv(int M, int N, int IB,
+ void *A, int LDA,
+ int *IPIV, int *INFO);
+int CORE_zgetrf_nopiv(int M, int N, int IB,
+ void *A, int LDA,
+ int *INFO);
+int CORE_zgetrf_reclap(int M, int N,
+ void *A, int LDA,
+ int *IPIV, int *info);
+int CORE_zgetrf_rectil(void *A, int *IPIV, int *info);
+void CORE_zgetrip(int m, int n, void *A,
+ void *work);
+int CORE_zhbelr(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+int CORE_zhblrx(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+int CORE_zhbrce(int uplo, int N,
+ void **A, void *V, void *TAU,
+ int st, int ed, int eltsize);
+void CORE_zhbtype1cb(int N, int NB,
+ void *A, int LDA,
+ void *V, void *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ void *WORK);
+void CORE_zhbtype2cb(int N, int NB,
+ void *A, int LDA,
+ void *V, void *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ void *WORK);
+void CORE_zhbtype3cb(int N, int NB,
+ void *A, int LDA,
+ void *V, void *TAU,
+ int st, int ed, int sweep, int Vblksiz, int WANTZ,
+ void *WORK);
+void CORE_zhegst(int itype, int uplo, int N,
+ void *A, int LDA,
+ void *B, int LDB, int *INFO);
+
+void CORE_zhemm(int side, int uplo,
+ int M, int N,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB,
+ void *beta, void *C, int LDC);
+void CORE_zherk(int uplo, int trans,
+ int N, int K,
+ double alpha, void *A, int LDA,
+ double beta, void *C, int LDC);
+void CORE_zher2k(int uplo, int trans,
+ int N, int K,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB,
+ double beta, void *C, int LDC);
+int CORE_zhessq(int uplo, int N,
+ void *A, int LDA,
+ double *scale, double *sumsq);
+
+int CORE_zherfb(int uplo, int N, int K, int IB, int NB,
+ void *A, int LDA,
+ void *T, int LDT,
+ void *C, int LDC,
+ void *WORK, int LDWORK);
+void CORE_zlacpy(int uplo, int M, int N,
+ void *A, int LDA,
+ void *B, int LDB);
+void CORE_zlange(int norm, int M, int N,
+ void *A, int LDA,
+ double *work, double *normA);
+
+void CORE_zlanhe(int norm, int uplo, int N,
+ void *A, int LDA,
+ double *work, double *normA);
+
+void CORE_zlansy(int norm, int uplo, int N,
+ void *A, int LDA,
+ double *work, double *normA);
+void CORE_zlantr(int norm, int uplo, int diag, int M, int N,
+ void *A, int LDA,
+ double *work, double *normA);
+int CORE_zlarfb_gemm(int side, int trans, int direct, int storev,
+ int M, int N, int K,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *C, int LDC,
+ void *WORK, int LDWORK);
+int CORE_zlarfx2(int side, int N,
+ void *V,
+ void *TAU,
+ void *C1, int LDC1,
+ void *C2, int LDC2);
+int CORE_zlarfx2c(int uplo,
+ void *V,
+ void *TAU,
+ void *C1,
+ void *C2,
+ void *C3);
+int CORE_zlarfx2ce(int uplo,
+ void *V,
+ void *TAU,
+ void *C1,
+ void *C2,
+ void *C3);
+void CORE_zlarfy(int N,
+ void *A, int LDA,
+ void *V,
+ void *TAU,
+ void *WORK);
+void CORE_zlaset(int uplo, int n1, int n2,
+ void *alpha, void *beta,
+ void *tileA, int ldtilea);
+void CORE_zlaset2(int uplo, int n1, int n2, void *alpha,
+ void *tileA, int ldtilea);
+void CORE_zlaswp(int N, void *A, int LDA,
+ int I1, int I2, const int *IPIV, int INC);
+int CORE_zlaswp_ontile( void *descA, int i1, int i2, const int *ipiv, int inc);
+int CORE_zlaswpc_ontile(void *descA, int i1, int i2, const int *ipiv, int inc);
+int CORE_zlatro(int uplo, int trans,
+ int M, int N,
+ void *A, int LDA,
+ void *B, int LDB);
+void CORE_zlauum(int uplo, int N, void *A, int LDA);
+int CORE_zpamm(int op, int side, int storev,
+ int M, int N, int K, int L,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *W, int LDW);
+int CORE_zparfb(int side, int trans, int direct, int storev,
+ int M1, int N1, int M2, int N2, int K, int L,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *WORK, int LDWORK);
+int CORE_zpemv(int trans, int storev,
+ int M, int N, int L,
+ void *ALPHA,
+ void *A, int LDA,
+ void *X, int INCX,
+ void *BETA,
+ void *Y, int INCY,
+ void *WORK);
+void CORE_zplghe(double bump, int m, int n, void *A, int lda,
+ int bigM, int m0, int n0, unsigned long long int seed );
+void CORE_zplgsy(void *bump, int m, int n, void *A, int lda,
+ int bigM, int m0, int n0, unsigned long long int seed );
+void CORE_zplrnt(int m, int n, void *A, int lda,
+ int bigM, int m0, int n0, unsigned long long int seed );
+void CORE_zpotrf(int uplo, int N, void *A, int LDA, int *INFO);
+void CORE_zshift(int s, int m, int n, int L,
+ void *A);
+void CORE_zshiftw(int s, int cl, int m, int n, int L,
+ void *A, void *W);
+int CORE_zssssm(int M1, int N1, int M2, int N2, int K, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *L1, int LDL1,
+ void *L2, int LDL2,
+ const int *IPIV);
+void CORE_zsymm(int side, int uplo,
+ int M, int N,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB,
+ void *beta, void *C, int LDC);
+void CORE_zsyrk(int uplo, int trans,
+ int N, int K,
+ void *alpha, void *A, int LDA,
+ void *beta, void *C, int LDC);
+void CORE_zsyr2k(int uplo, int trans,
+ int N, int K,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB,
+ void *beta, void *C, int LDC);
+int CORE_zsyssq(int uplo, int N,
+ void *A, int LDA,
+ double *scale, double *sumsq);
+int CORE_zsytf2_nopiv(int uplo, int n, void *A, int lda);
+void CORE_zswpab(int i, int n1, int n2,
+ void *A, void *work);
+int CORE_zswptr_ontile(void *descA, int i1, int i2, const int *ipiv, int inc,
+ void *Akk, int ldak);
+void CORE_ztrdalg(int uplo, int N, int NB,
+ void *pA, void *V, void *TAU,
+ int i, int j, int m, int grsiz);
+void CORE_ztrmm(int side, int uplo,
+ int transA, int diag,
+ int M, int N,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB);
+void CORE_ztrsm(int side, int uplo,
+ int transA, int diag,
+ int M, int N,
+ void *alpha, void *A, int LDA,
+ void *B, int LDB);
+void CORE_ztrtri(int uplo, int diag, int N,
+ void *A, int LDA, int *info);
+int CORE_ztslqt(int M, int N, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *T, int LDT,
+ void *TAU, void *WORK);
+int CORE_ztsmlq(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *WORK, int LDWORK);
+int CORE_ztsmlq_corner( int m1, int n1, int m2, int n2, int m3, int n3,
+ int k, int ib, int nb,
+ void *A1, int lda1,
+ void *A2, int lda2,
+ void *A3, int lda3,
+ void *V, int ldv,
+ void *T, int ldt,
+ void *WORK, int ldwork);
+int CORE_ztsmlq_hetra1( int side, int trans,
+ int m1, int n1, int m2, int n2,
+ int k, int ib,
+ void *A1, int lda1,
+ void *A2, int lda2,
+ void *V, int ldv,
+ void *T, int ldt,
+ void *WORK, int ldwork);
+int CORE_ztsmqr(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *WORK, int LDWORK);
+int CORE_ztsmqr_corner( int m1, int n1, int m2, int n2, int m3, int n3,
+ int k, int ib, int nb,
+ void *A1, int lda1,
+ void *A2, int lda2,
+ void *A3, int lda3,
+ void *V, int ldv,
+ void *T, int ldt,
+ void *WORK, int ldwork);
+int CORE_ztsmqr_hetra1( int side, int trans,
+ int m1, int n1, int m2, int n2,
+ int k, int ib,
+ void *A1, int lda1,
+ void *A2, int lda2,
+ void *V, int ldv,
+ void *T, int ldt,
+ void *WORK, int ldwork);
+int CORE_ztsqrt(int M, int N, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *T, int LDT,
+ void *TAU, void *WORK);
+int CORE_ztstrf(int M, int N, int IB, int NB,
+ void *U, int LDU,
+ void *A, int LDA,
+ void *L, int LDL,
+ int *IPIV, void *WORK,
+ int LDWORK, int *INFO);
+int CORE_zttmqr(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *WORK, int LDWORK);
+int CORE_zttqrt(int M, int N, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *T, int LDT,
+ void *TAU,
+ void *WORK);
+int CORE_zttmlq(int side, int trans,
+ int M1, int N1, int M2, int N2, int K, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *WORK, int LDWORK);
+int CORE_zttlqt(int M, int N, int IB,
+ void *A1, int LDA1,
+ void *A2, int LDA2,
+ void *T, int LDT,
+ void *TAU,
+ void *WORK);
+int CORE_zunmlq(int side, int trans,
+ int M, int N, int IB, int K,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *C, int LDC,
+ void *WORK, int LDWORK);
+int CORE_zunmqr(int side, int trans,
+ int M, int N, int K, int IB,
+ void *V, int LDV,
+ void *T, int LDT,
+ void *C, int LDC,
+ void *WORK, int LDWORK);
+
+void CORE_clag2z(int m, int n,
+ void *A, int lda,
+ void *B, int ldb);
+void CORE_zlag2c(int m, int n,
+ void *A, int lda,
+ void *B, int ldb, int *info);
+
+END_MODULE