Hello,

I am working on a larger project processing audio signals in double format. As I needed to estimate the max. Amplitude of a buffer, it returned a faulty value.

I debugged the assembler code and realized, that the optimizer created a faulty computation of the maximum. By only changing one instruction, the computation is correct.

I've reduced the code to a minimum of code supplementing function calls that fill the buffer with a simple memcpy function.

The code is standalone. I'll include the factor.ii which is also a command line program demonstrating the error. I've compiled it with the command line found below. I also tried out leaving the compiler flag -march=i686 away. It just changed my assembler code but didn't get rid of the error. Further down I'll include my analysis of the assembler code.


g++ -o factor -Wall -v -O2 -march=i686 factor.cpp:
Using built-in specs.
Target: i486-linux-gnu
Configured with: ../src/configure -v --enable-languages=c,c++,fortran,objc,obj-c++ --prefix=/usr --enable-shared --with-system-zlib --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --enable-nls --with-gxx-include-dir=/usr/include/c++/4.2 --program-suffix=-4.2 --enable-clocale=gnu --enable-libstdcxx-debug --enable-objc-gc --enable-mpfr --disable-libmudflap --enable-targets=all --enable-checking=release --build=i486-linux-gnu --host=i486-linux-gnu --target=i486-linux-gnu
Thread model: posix
gcc version 4.2.3 (Debian 4.2.3-3)
 /usr/lib/gcc/i486-linux-gnu/4.2.3/cc1plus -E -quiet -v -D_GNU_SOURCE factor.cpp -march=i686 -Wall -O2 -fpch-preprocess -o factor.ii
ignoring nonexistent directory "/usr/local/include/i486-linux-gnu"
ignoring nonexistent directory "/usr/lib/gcc/i486-linux-gnu/4.2.3/../../../../i486-linux-gnu/include"
ignoring nonexistent directory "/usr/include/i486-linux-gnu"
#include "..." search starts here:
#include <...> search starts here:
 /usr/include/c++/4.2
 /usr/include/c++/4.2/i486-linux-gnu
 /usr/include/c++/4.2/backward
 /usr/local/include
 /usr/lib/gcc/i486-linux-gnu/4.2.3/include
 /usr/include
End of search list.
 /usr/lib/gcc/i486-linux-gnu/4.2.3/cc1plus -fpreprocessed factor.ii -quiet -dumpbase factor.cpp -march=i686 -auxbase factor -O2 -Wall -version -o factor.s
GNU C++ version 4.2.3 (Debian 4.2.3-3) (i486-linux-gnu)
        compiled by GNU C version 4.2.3 (Debian 4.2.3-3).
GGC heuristics: --param ggc-min-expand=45 --param ggc-min-heapsize=29241
Compiler executable checksum: f63294e1c8ecc1bf2473a5bae1642fbe
 as -V -Qy -o factor.o factor.s
GNU assembler version 2.18.0 (i486-linux-gnu) using BFD version (GNU Binutils for Debian) 2.18.0.20080103
 /usr/lib/gcc/i486-linux-gnu/4.2.3/collect2 --eh-frame-hdr -m elf_i386 --hash-style=both -dynamic-linker /lib/ld-linux.so.2 -o factor /usr/lib/gcc/i486-linux-gnu/4.2.3/../../../../lib/crt1.o /usr/lib/gcc/i486-linux-gnu/4.2.3/../../../../lib/crti.o /usr/lib/gcc/i486-linux-gnu/4.2.3/crtbegin.o -L/usr/lib/gcc/i486-linux-gnu/4.2.3 -L/usr/lib/gcc/i486-linux-gnu/4.2.3 -L/usr/lib/gcc/i486-linux-gnu/4.2.3/../../../../lib -L/lib/../lib -L/usr/lib/../lib -L/usr/lib/gcc/i486-linux-gnu/4.2.3/../../.. factor.o -lstdc++ -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc /usr/lib/gcc/i486-linux-gnu/4.2.3/crtend.o /usr/lib/gcc/i486-linux-gnu/4.2.3/../../../../lib/crtn.o


The optimizer generates the error with the following line of code:

for (unsigned long i = 0; i < insize; ++i) _factor = std::max(_factor, std::max(-data[i], data[i]));

with
double * data; (Audio Data)
unsigned long insize; (number of doubles in the buffer)
double _factor; (currently estimated, global factor)


Generated Assembler code from factor.s:

// Load data Buffer pointer to eax
	movl	-36(%ebp), %eax
// Clear edx (that's our i)
	xorl	%edx, %edx
// Load _factor on FP-Stack
	fldl	(%esi)
// Have _factor twice on the FP-Stack (Stack: (original)_factor, (current)_factor)
	fld	%st(0)
// Start the for-loop
	jmp	.L45
	.p2align 4,,7


.L64:
// This at the beginning of every iteration i >= 1
// This is the actual consistency error
// At this pointer we have the following on the FP-Stack: st(0): _factor(current), st(1): _factor(original)
// After executing this, we'll have st(0): _factor(original), st(1): _factor(current), which creates a problem further down
// To show what is actually going wrong, I'll label _factor
 
	fxch	%st(1)
.L45:
	fldl	(%eax)
	fchs
	fstl	-16(%ebp)
	fldl	(%eax)
	fucomi	%st(1), %st
	fcmovbe	%st(1), %st
	fstp	%st(1)
	fucomi	%st(2), %st
	fstp	%st(2)
	fxch	%st(1)
	fcmovbe	%st(1), %st
	addl	$1, %edx
	addl	$8, %eax
	cmpl	%ebx, %edx
	jne	.L64
	fstp	%st(1)
	fstpl	(%esi)
.L43:
	cmpb	$0, 8(%esi)
	je	.L53