Dear Denis,
On Wed, Mar 03, 2010 at 11:41:50AM +0100, Denis Barbier wrote:
> Hi,
>
> For the record, thanks to the GCC compile farm, I determined that this
> bug has been fixed in gcc trunk by
> http://gcc.gnu.org/viewcvs?view=revision&revision=145494
> Unfortunately this is a merge from a branch (alias-improvements) which
> is not mirrored by git, so I had not been able to run git-bisect on it
> to find the atomic commit. And since this portion of code has been
> heavily modified, I doubt that it could be backported to gcc 4.4. I
> do not know what can be done now.
I think we can still file a bug report. Could you please test the
attach test case, and let me know if it is reproducible? For me,
here's what I do:
[~/Kumar/Programming/Blas_test] gcc -v
Using built-in specs.
Target: x86_64-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Debian 4.4.3-2'
--with-bugurl=file:///usr/share/doc/gcc-4.4/README.Bugs
--enable-languages=c,c++,fortran,objc,obj-c++ --prefix=/usr --enable-shared
--enable-multiarch --enable-linker-build-id --with-system-zlib
--libexecdir=/usr/lib --without-included-gettext --enable-threads=posix
--with-gxx-include-dir=/usr/include/c++/4.4 --program-suffix=-4.4 --enable-nls
--enable-clocale=gnu --enable-libstdcxx-debug --enable-objc-gc
--with-arch-32=i486 --with-tune=generic --enable-checking=release
--build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu
Thread model: posix
gcc version 4.4.3 (Debian 4.4.3-2)
$ make clean
rm -f zdrot_test.o zdrot.o zdrot_test
$ make
cc -c -O2 zdrot_test.c -o zdrot_test.o
gfortran -c -O2 -ftree-vectorize zdrot.f -o zdrot.o
cc zdrot_test.o zdrot.o -o zdrot_test
$ ./zdrot_test |tee 1
x: {(-0.8568, -0.0000), (-0.3505, -0.2082), (0.1505, 0.6113)}
y: {(0.4017, -0.0000), (-0.2403, -0.2102), (0.6074, 0.6064)}
$ make clean
rm -f zdrot_test.o zdrot.o zdrot_test
$ make FFLAGS=-O2
cc -c -O2 zdrot_test.c -o zdrot_test.o
gfortran -c -O2 zdrot.f -o zdrot.o
cc zdrot_test.o zdrot.o -o zdrot_test
$ ./zdrot_test |tee 2
x: {(-0.8568, -0.0000), (-0.3505, 0.1285), (0.1505, 0.3224)}
y: {(0.4017, -0.0000), (-0.2403, -0.2102), (0.6074, 0.6064)}
$ diff 1 2
1c1
< x: {(-0.8568, -0.0000), (-0.3505, -0.2082), (0.1505, 0.6113)}
---
> x: {(-0.8568, -0.0000), (-0.3505, 0.1285), (0.1505, 0.3224)}
$
I have attached the relevant files.
Thank you.
Kumar
--
To the guests that must go, bid God's speed and brush away all traces
of their steps.
- Rabindranath Tagore (The Gardener, 1915)
CFLAGS ?= -O2
FFLAGS ?= -O2 -ftree-vectorize
LFLAGS ?= -O3
FC = gfortran
all: zdrot_test
zdrot_test: zdrot.o zdrot_test.o
zdrot.o: zdrot.f
$(FC) -c $(FFLAGS) $< -o $@
zdrot_test.o: zdrot_test.c
$(CC) -c $(CFLAGS) $< -o $@
.PHONY: clean
clean:
$(RM) zdrot_test.o zdrot.o zdrot_test
#include <stdio.h>
#include <math.h>
typedef struct _dcomplex {
double real;
double imag;
} dcomplex;
int
zdrot_(int *N, dcomplex *CX, int *INCX, dcomplex *CY,int *INCY, double *C, double *S);
void
dump_array(int n, int incx, const dcomplex *cx, const char *label)
{
int i;
printf("%s: {", label);
for (i = 0; i < n - 1; ++i) {
printf("(%.4f, %.4f), ", cx[incx * i].real, cx[incx * i].imag);
}
printf("(%.4f, %.4f)}\n", cx[incx * (n - 1)].real, cx[incx * (n - 1)].imag);
}
int
main(void)
{
int i, n, incx, incy;
double c, s;
/* int n = 5; */
/* dcomplex cx[] = {{1.0, 1.0}, {2.0, 2.0}, {3.0, 3.0}, {4.0, 4.0}, {5.0, 5.0}, {1.0, 1.0}, {2.0, 2.0}, {3.0, 3.0}, {4.0, 4.0}}; */
/* int incx = 2; */
/* dcomplex cy[] = {{-5.0, 5.0}, {0.0, 0.0}, {-4.0, 4.0}, {0.0, 0.0}, {-3.0, 3.0}, {0.0, 0.0}, {-2.0, 2.0}, {0.0, 0.0}, {-1.0, 1.0}}; */
/* int incy = 2; */
dcomplex cx[] = {{-0.85979604472439053,-2.7649680642690493e-18},
{-0.34870067583684999,0.13008763797653625},
{0.1458460044809155,0.31774950758397147}
};
dcomplex cy[] = {{0.39513973218816306,-1.6608257098635789e-17},
{-0.24300238986826755,-0.20921321526463676},
{0.60854527713236894,0.60886526161631016}
};
n = 3;
incx = incy = 1;
c = 0.99997081162455026;
s = 0.007640412223039174;
zdrot_(&n, cx, &incx, cy, &incy, &c, &s);
dump_array(n, incx, cx, "x");
dump_array(n, incy, cy, "y");
return 0;
}
SUBROUTINE ZDROT( N, CX, INCX, CY, INCY, C, S )
*
* .. Scalar Arguments ..
INTEGER INCX, INCY, N
DOUBLE PRECISION C, S
* ..
* .. Array Arguments ..
COMPLEX*16 CX( * ), CY( * )
* ..
*
* Purpose
* =======
*
* Applies a plane rotation, where the cos and sin (c and s) are real
* and the vectors cx and cy are complex.
* jack dongarra, linpack, 3/11/78.
*
* Arguments
* ==========
*
* N (input) INTEGER
* On entry, N specifies the order of the vectors cx and cy.
* N must be at least zero.
* Unchanged on exit.
*
* CX (input) COMPLEX*16 array, dimension at least
* ( 1 + ( N - 1 )*abs( INCX ) ).
* Before entry, the incremented array CX must contain the n
* element vector cx. On exit, CX is overwritten by the updated
* vector cx.
*
* INCX (input) INTEGER
* On entry, INCX specifies the increment for the elements of
* CX. INCX must not be zero.
* Unchanged on exit.
*
* CY (input) COMPLEX*16 array, dimension at least
* ( 1 + ( N - 1 )*abs( INCY ) ).
* Before entry, the incremented array CY must contain the n
* element vector cy. On exit, CY is overwritten by the updated
* vector cy.
*
* INCY (input) INTEGER
* On entry, INCY specifies the increment for the elements of
* CY. INCY must not be zero.
* Unchanged on exit.
*
* C (input) DOUBLE PRECISION
* On entry, C specifies the cosine, cos.
* Unchanged on exit.
*
* S (input) DOUBLE PRECISION
* On entry, S specifies the sine, sin.
* Unchanged on exit.
*
* =====================================================================
*
* .. Local Scalars ..
INTEGER I, IX, IY
COMPLEX*16 CTEMP
* ..
* .. Executable Statements ..
*
IF( N.LE.0 )
$ RETURN
IF( INCX.EQ.1 .AND. INCY.EQ.1 )
$ GO TO 20
*
* code for unequal increments or equal increments not equal
* to 1
*
IX = 1
IY = 1
IF( INCX.LT.0 )
$ IX = ( -N+1 )*INCX + 1
IF( INCY.LT.0 )
$ IY = ( -N+1 )*INCY + 1
DO 10 I = 1, N
CTEMP = C*CX( IX ) + S*CY( IY )
CY( IY ) = C*CY( IY ) - S*CX( IX )
CX( IX ) = CTEMP
IX = IX + INCX
IY = IY + INCY
10 CONTINUE
RETURN
*
* code for both increments equal to 1
*
20 CONTINUE
DO 30 I = 1, N
CTEMP = C*CX( I ) + S*CY( I )
CY( I ) = C*CY( I ) - S*CX( I )
CX( I ) = CTEMP
30 CONTINUE
RETURN
END
