I tried to track down the bug mentioned previously in testing my software SSE2 when compiled with -m64 and ended up removing all of the CHECK and my own includes without eliminating the bug. The test program works fine with -m32, or with -m64 -msse2, but it fails with -m64 -mno-sse2. Here is the greatly reduced gccprob2.c:
8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8< #include <stdio.h> /* for printf */ typedef double __m128d __attribute__ ((__vector_size__ (16), __may_alias__)); typedef union { __m128d x; double a[2]; } union128d; #define EMM_FLT8(a) ((double *)&(a)) void test ( __m128d s1, __m128d s2) { printf("test s1 %lf %lf\n",EMM_FLT8(s1)[0],EMM_FLT8(s1)[1]); printf("test s2 %lf %lf\n",EMM_FLT8(s2)[0],EMM_FLT8(s2)[1]); } int main (void) { __attribute__ ((aligned (16))) union128d s1; s1.a[0] = 1.0; s1.a[1] = 2.0; printf("s1 %lf %lf\n",s1.a[0],s1.a[1]); test (s1.x, s1.x); } 8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8<8< Test runs: % gcc -msse -mno-sse2 -m64 -o foo gccprob2.c % ./foo #first value in s2 is wrong s1 1.000000 2.000000 test s1 1.000000 2.000000 test s2 2.000000 2.000000 % gcc -msse -msse2 -m64 -o foo gccprob2.c % ./foo s1 1.000000 2.000000 test s1 1.000000 2.000000 test s2 1.000000 2.000000 % gcc -msse -mno-sse2 -lm -m32 -o foo gccprob2.c % ./foo s1 1.000000 2.000000 test s1 1.000000 2.000000 test s2 1.000000 2.000000 % gcc --version gcc (GCC) 4.4.1 % cat /etc/release Mandriva Linux release 2010.0 (Official) for x86_64 % cat /proc/cpuinfo | head -10 processor : 0 vendor_id : AuthenticAMD cpu family : 15 model : 33 model name : Dual Core AMD Opteron(tm) Processor 280 stepping : 2 cpu MHz : 1000.000 cache size : 1024 KB physical id : 0 siblings : 2 Is there something wrong with this program or is this a compiler bug? Thanks, David Mathog mat...@caltech.edu Manager, Sequence Analysis Facility, Biology Division, Caltech