------- Comment #4 from ubizjak at gmail dot com 2009-07-04 12:43 -------
(In reply to comment #1)
> Can you check numbers with vectorization disabled? I see the regression as
> well on a AMD Fam 10 machine which supposedly has unaligned moves as fast
> as aligned moves (if the data turns out to be aligned). Which means the
> data really is unaligned.
Without the vectorisation (adding -fno-tree-vectorize), there is no difference:
time ./a.out
Benchmark running, hopefully as only ACTIVE task
Test1 - Gauss 2000 (101x101) inverts 2.2 sec Err= 0.000000000000006
Test2 - Crout 2000 (101x101) inverts 2.5 sec Err= 0.000000000000023
Test3 - Crout 2 (1001x1001) inverts 2.6 sec Err= 0.000000000000031
Test4 - Lapack 2 (1001x1001) inverts 2.2 sec Err= 0.000000000000250
total = 9.5 sec
real 0m9.760s
user 0m9.674s
sys 0m0.082s
> What is the difference in code generation? Can you create a testcase from
> the hot loop(s)?
The first thing to catch my eye is missing CSE on memory references in the
_MAIN loop (added -march=barcelona to generate movupd insns:
.L14:
movupd equiv.0.1551(%rdx,%rax), %xmm8 #, tmp720
movupd a3.1557(%rdx,%rax), %xmm7 #, tmp722
leaq 16(%rdx), %r10 #, tmp789
movupd equiv.0.1551(%r10,%rax), %xmm6 #, tmp867
movupd a3.1557(%r10,%rax), %xmm5 #, tmp869
leaq 32(%rdx), %rcx #, ivtmp.845
subpd %xmm8, %xmm7 # tmp720, tmp722
movupd equiv.0.1551(%rcx,%rax), %xmm3 #, tmp873
movupd a3.1557(%rcx,%rax), %xmm4 #, tmp875
subpd %xmm6, %xmm5 # tmp867, tmp869
leaq 48(%rdx), %r9 #, ivtmp.845
leaq 64(%rdx), %r8 #, ivtmp.845
subpd %xmm3, %xmm4 # tmp873, tmp875
movupd a3.1557(%r9,%rax), %xmm15 #, tmp881
movupd equiv.0.1551(%r9,%rax), %xmm2 #, tmp879
movupd a3.1557(%r8,%rax), %xmm13 #, tmp887
movupd equiv.0.1551(%r8,%rax), %xmm14 #, tmp885
and in regressed case:
.L13:
movupd (%rdx,%rax), %xmm15 #* ivtmp.792, tmp962
movupd (%r12,%rax), %xmm14 #* ivtmp.792, tmp964
leaq 16(%rax), %rsi #, tmp1050
movupd (%rdx,%rsi), %xmm13 #, tmp1114
movupd (%r12,%rsi), %xmm12 #, tmp1116
leaq 32(%rax), %r15 #, ivtmp.792
subpd %xmm15, %xmm14 # tmp962, tmp964
movupd (%rdx,%r15), %xmm11 #* ivtmp.792, tmp1120
movupd (%r12,%r15), %xmm10 #* ivtmp.792, tmp1122
subpd %xmm13, %xmm12 # tmp1114, tmp1116
leaq 48(%rax), %rcx #, ivtmp.792
leaq 64(%rax), %r13 #, ivtmp.792
subpd %xmm11, %xmm10 # tmp1120, tmp1122
movupd (%r12,%rcx), %xmm8 #* ivtmp.792, tmp1128
movupd (%rdx,%rcx), %xmm9 #* ivtmp.792, tmp1126
movupd (%r12,%r13), %xmm6 #* ivtmp.792, tmp1134
movupd (%rdx,%r13), %xmm7 #* ivtmp.792, tmp1132
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=40648
