LAPACK 3.12.0
LAPACK: Linear Algebra PACKage
Loading...
Searching...
No Matches

◆ zlamswlq()

subroutine zlamswlq ( character  side,
character  trans,
integer  m,
integer  n,
integer  k,
integer  mb,
integer  nb,
complex*16, dimension( lda, * )  a,
integer  lda,
complex*16, dimension( ldt, * )  t,
integer  ldt,
complex*16, dimension(ldc, * )  c,
integer  ldc,
complex*16, dimension( * )  work,
integer  lwork,
integer  info 
)

ZLAMSWLQ

Purpose:
    ZLAMSWLQ overwrites the general complex M-by-N matrix C with


                    SIDE = 'L'     SIDE = 'R'
    TRANS = 'N':      Q * C          C * Q
    TRANS = 'C':      Q**H * C       C * Q**H
    where Q is a complex unitary matrix defined as the product of blocked
    elementary reflectors computed by short wide LQ
    factorization (ZLASWLQ)
Parameters
[in]SIDE
          SIDE is CHARACTER*1
          = 'L': apply Q or Q**H from the Left;
          = 'R': apply Q or Q**H from the Right.
[in]TRANS
          TRANS is CHARACTER*1
          = 'N':  No transpose, apply Q;
          = 'C':  Conjugate Transpose, apply Q**H.
[in]M
          M is INTEGER
          The number of rows of the matrix C.  M >=0.
[in]N
          N is INTEGER
          The number of columns of the matrix C. N >= 0.
[in]K
          K is INTEGER
          The number of elementary reflectors whose product defines
          the matrix Q.
          M >= K >= 0;
[in]MB
          MB is INTEGER
          The row block size to be used in the blocked LQ.
          M >= MB >= 1
[in]NB
          NB is INTEGER
          The column block size to be used in the blocked LQ.
          NB > M.
[in]A
          A is COMPLEX*16 array, dimension
                               (LDA,M) if SIDE = 'L',
                               (LDA,N) if SIDE = 'R'
          The i-th row must contain the vector which defines the blocked
          elementary reflector H(i), for i = 1,2,...,k, as returned by
          ZLASWLQ in the first k rows of its array argument A.
[in]LDA
          LDA is INTEGER
          The leading dimension of the array A. LDA >= MAX(1,K).
[in]T
          T is COMPLEX*16 array, dimension
          ( M * Number of blocks(CEIL(N-K/NB-K)),
          The blocked upper triangular block reflectors stored in compact form
          as a sequence of upper triangular blocks.  See below
          for further details.
[in]LDT
          LDT is INTEGER
          The leading dimension of the array T.  LDT >= MB.
[in,out]C
          C is COMPLEX*16 array, dimension (LDC,N)
          On entry, the M-by-N matrix C.
          On exit, C is overwritten by Q*C or Q**H*C or C*Q**H or C*Q.
[in]LDC
          LDC is INTEGER
          The leading dimension of the array C. LDC >= max(1,M).
[out]WORK
         (workspace) COMPLEX*16 array, dimension (MAX(1,LWORK))
[in]LWORK
          LWORK is INTEGER
          The dimension of the array WORK.
          If SIDE = 'L', LWORK >= max(1,NB) * MB;
          if SIDE = 'R', LWORK >= max(1,M) * MB.
          If LWORK = -1, then a workspace query is assumed; the routine
          only calculates the optimal size of the WORK array, returns
          this value as the first entry of the WORK array, and no error
          message related to LWORK is issued by XERBLA.
[out]INFO
          INFO is INTEGER
          = 0:  successful exit
          < 0:  if INFO = -i, the i-th argument had an illegal value
Author
Univ. of Tennessee
Univ. of California Berkeley
Univ. of Colorado Denver
NAG Ltd.
Further Details:
 Short-Wide LQ (SWLQ) performs LQ by a sequence of unitary transformations,
 representing Q as a product of other unitary matrices
   Q = Q(1) * Q(2) * . . . * Q(k)
 where each Q(i) zeros out upper diagonal entries of a block of NB rows of A:
   Q(1) zeros out the upper diagonal entries of rows 1:NB of A
   Q(2) zeros out the bottom MB-N rows of rows [1:M,NB+1:2*NB-M] of A
   Q(3) zeros out the bottom MB-N rows of rows [1:M,2*NB-M+1:3*NB-2*M] of A
   . . .

 Q(1) is computed by GELQT, which represents Q(1) by Householder vectors
 stored under the diagonal of rows 1:MB of A, and by upper triangular
 block reflectors, stored in array T(1:LDT,1:N).
 For more information see Further Details in GELQT.

 Q(i) for i>1 is computed by TPLQT, which represents Q(i) by Householder vectors
 stored in columns [(i-1)*(NB-M)+M+1:i*(NB-M)+M] of A, and by upper triangular
 block reflectors, stored in array T(1:LDT,(i-1)*M+1:i*M).
 The last Q(k) may use fewer rows.
 For more information see Further Details in TPLQT.

 For more details of the overall algorithm, see the description of
 Sequential TSQR in Section 2.2 of [1].

 [1] “Communication-Optimal Parallel and Sequential QR and LU Factorizations,”
     J. Demmel, L. Grigori, M. Hoemmen, J. Langou,
     SIAM J. Sci. Comput, vol. 34, no. 1, 2012

Definition at line 195 of file zlamswlq.f.

197*
198* -- LAPACK computational routine --
199* -- LAPACK is a software package provided by Univ. of Tennessee, --
200* -- Univ. of California Berkeley, Univ. of Colorado Denver and NAG Ltd..--
201*
202* .. Scalar Arguments ..
203 CHARACTER SIDE, TRANS
204 INTEGER INFO, LDA, M, N, K, MB, NB, LDT, LWORK, LDC
205* ..
206* .. Array Arguments ..
207 COMPLEX*16 A( LDA, * ), WORK( * ), C(LDC, * ),
208 $ T( LDT, * )
209* ..
210*
211* =====================================================================
212*
213* ..
214* .. Local Scalars ..
215 LOGICAL LEFT, RIGHT, TRAN, NOTRAN, LQUERY
216 INTEGER I, II, KK, LW, CTR
217* ..
218* .. External Functions ..
219 LOGICAL LSAME
220 EXTERNAL lsame
221* .. External Subroutines ..
222 EXTERNAL ztpmlqt, zgemlqt, xerbla
223* ..
224* .. Executable Statements ..
225*
226* Test the input arguments
227*
228 lquery = lwork.LT.0
229 notran = lsame( trans, 'N' )
230 tran = lsame( trans, 'C' )
231 left = lsame( side, 'L' )
232 right = lsame( side, 'R' )
233 IF (left) THEN
234 lw = n * mb
235 ELSE
236 lw = m * mb
237 END IF
238*
239 info = 0
240 IF( .NOT.left .AND. .NOT.right ) THEN
241 info = -1
242 ELSE IF( .NOT.tran .AND. .NOT.notran ) THEN
243 info = -2
244 ELSE IF( k.LT.0 ) THEN
245 info = -5
246 ELSE IF( m.LT.k ) THEN
247 info = -3
248 ELSE IF( n.LT.0 ) THEN
249 info = -4
250 ELSE IF( k.LT.mb .OR. mb.LT.1) THEN
251 info = -6
252 ELSE IF( lda.LT.max( 1, k ) ) THEN
253 info = -9
254 ELSE IF( ldt.LT.max( 1, mb) ) THEN
255 info = -11
256 ELSE IF( ldc.LT.max( 1, m ) ) THEN
257 info = -13
258 ELSE IF(( lwork.LT.max(1,lw)).AND.(.NOT.lquery)) THEN
259 info = -15
260 END IF
261*
262 IF( info.NE.0 ) THEN
263 CALL xerbla( 'ZLAMSWLQ', -info )
264 work(1) = lw
265 RETURN
266 ELSE IF (lquery) THEN
267 work(1) = lw
268 RETURN
269 END IF
270*
271* Quick return if possible
272*
273 IF( min(m,n,k).EQ.0 ) THEN
274 RETURN
275 END IF
276*
277 IF((nb.LE.k).OR.(nb.GE.max(m,n,k))) THEN
278 CALL zgemlqt( side, trans, m, n, k, mb, a, lda,
279 $ t, ldt, c, ldc, work, info)
280 RETURN
281 END IF
282*
283 IF(left.AND.tran) THEN
284*
285* Multiply Q to the last block of C
286*
287 kk = mod((m-k),(nb-k))
288 ctr = (m-k)/(nb-k)
289*
290 IF (kk.GT.0) THEN
291 ii=m-kk+1
292 CALL ztpmlqt('L','C',kk , n, k, 0, mb, a(1,ii), lda,
293 $ t(1,ctr*k+1), ldt, c(1,1), ldc,
294 $ c(ii,1), ldc, work, info )
295 ELSE
296 ii=m+1
297 END IF
298*
299 DO i=ii-(nb-k),nb+1,-(nb-k)
300*
301* Multiply Q to the current block of C (1:M,I:I+NB)
302*
303 ctr = ctr - 1
304 CALL ztpmlqt('L','C',nb-k , n, k, 0,mb, a(1,i), lda,
305 $ t(1,ctr*k+1),ldt, c(1,1), ldc,
306 $ c(i,1), ldc, work, info )
307
308 END DO
309*
310* Multiply Q to the first block of C (1:M,1:NB)
311*
312 CALL zgemlqt('L','C',nb , n, k, mb, a(1,1), lda, t
313 $ ,ldt ,c(1,1), ldc, work, info )
314*
315 ELSE IF (left.AND.notran) THEN
316*
317* Multiply Q to the first block of C
318*
319 kk = mod((m-k),(nb-k))
320 ii=m-kk+1
321 ctr = 1
322 CALL zgemlqt('L','N',nb , n, k, mb, a(1,1), lda, t
323 $ ,ldt ,c(1,1), ldc, work, info )
324*
325 DO i=nb+1,ii-nb+k,(nb-k)
326*
327* Multiply Q to the current block of C (I:I+NB,1:N)
328*
329 CALL ztpmlqt('L','N',nb-k , n, k, 0,mb, a(1,i), lda,
330 $ t(1, ctr * k + 1), ldt, c(1,1), ldc,
331 $ c(i,1), ldc, work, info )
332 ctr = ctr + 1
333*
334 END DO
335 IF(ii.LE.m) THEN
336*
337* Multiply Q to the last block of C
338*
339 CALL ztpmlqt('L','N',kk , n, k, 0, mb, a(1,ii), lda,
340 $ t(1, ctr * k + 1), ldt, c(1,1), ldc,
341 $ c(ii,1), ldc, work, info )
342*
343 END IF
344*
345 ELSE IF(right.AND.notran) THEN
346*
347* Multiply Q to the last block of C
348*
349 kk = mod((n-k),(nb-k))
350 ctr = (n-k)/(nb-k)
351 IF (kk.GT.0) THEN
352 ii=n-kk+1
353 CALL ztpmlqt('R','N',m , kk, k, 0, mb, a(1, ii), lda,
354 $ t(1, ctr * k + 1), ldt, c(1,1), ldc,
355 $ c(1,ii), ldc, work, info )
356 ELSE
357 ii=n+1
358 END IF
359*
360 DO i=ii-(nb-k),nb+1,-(nb-k)
361*
362* Multiply Q to the current block of C (1:M,I:I+MB)
363*
364 ctr = ctr - 1
365 CALL ztpmlqt('R','N', m, nb-k, k, 0, mb, a(1, i), lda,
366 $ t(1, ctr * k + 1), ldt, c(1,1), ldc,
367 $ c(1,i), ldc, work, info )
368
369 END DO
370*
371* Multiply Q to the first block of C (1:M,1:MB)
372*
373 CALL zgemlqt('R','N',m , nb, k, mb, a(1,1), lda, t
374 $ ,ldt ,c(1,1), ldc, work, info )
375*
376 ELSE IF (right.AND.tran) THEN
377*
378* Multiply Q to the first block of C
379*
380 kk = mod((n-k),(nb-k))
381 ii=n-kk+1
382 CALL zgemlqt('R','C',m , nb, k, mb, a(1,1), lda, t
383 $ ,ldt ,c(1,1), ldc, work, info )
384 ctr = 1
385*
386 DO i=nb+1,ii-nb+k,(nb-k)
387*
388* Multiply Q to the current block of C (1:M,I:I+MB)
389*
390 CALL ztpmlqt('R','C',m , nb-k, k, 0,mb, a(1,i), lda,
391 $ t(1,ctr *k+1), ldt, c(1,1), ldc,
392 $ c(1,i), ldc, work, info )
393 ctr = ctr + 1
394*
395 END DO
396 IF(ii.LE.n) THEN
397*
398* Multiply Q to the last block of C
399*
400 CALL ztpmlqt('R','C',m , kk, k, 0,mb, a(1,ii), lda,
401 $ t(1, ctr * k + 1),ldt, c(1,1), ldc,
402 $ c(1,ii), ldc, work, info )
403*
404 END IF
405*
406 END IF
407*
408 work(1) = lw
409 RETURN
410*
411* End of ZLAMSWLQ
412*
subroutine xerbla(srname, info)
Definition cblat2.f:3285
subroutine zgemlqt(side, trans, m, n, k, mb, v, ldv, t, ldt, c, ldc, work, info)
ZGEMLQT
Definition zgemlqt.f:168
logical function lsame(ca, cb)
LSAME
Definition lsame.f:48
subroutine ztpmlqt(side, trans, m, n, k, l, mb, v, ldv, t, ldt, a, lda, b, ldb, work, info)
ZTPMLQT
Definition ztpmlqt.f:214
Here is the call graph for this function:
Here is the caller graph for this function: