Date: Fri, 22 May 2020 18:29:33 +0000 From: bugzilla-noreply@freebsd.org To: bugs@FreeBSD.org Subject: [Bug 246630] stable/11 regression: base.txz reproducibility depends on number of cpu cores Message-ID: <bug-246630-227-s9nyCV0b9k@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-246630-227@https.bugs.freebsd.org/bugzilla/> References: <bug-246630-227@https.bugs.freebsd.org/bugzilla/>
next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D246630 --- Comment #10 from Ed Maste <emaste@freebsd.org> --- Here is where the interesting parts start - I've rearranged the diff -/+ to make it easier to see where differences exist: =E2=94=82 - 43c803: 4c 63 c2 movslq %edx,%r8 =E2=94=82 + 43c803: 4c 63 da movslq %edx,%r11 =E2=94=82 - 43c806: 49 c1 e0 03 shl $0x3,%r8 =E2=94=82 + 43c806: 49 c1 e3 03 shl $0x3,%r11 =E2=94=82 - 43c80a: 4c 03 05 e7 7a bc 00 add 0xbc7ae7(%rip),%r8 = # 0x10042f8 =E2=94=82 + 43c80a: 4c 03 1d e7 7a bc 00 add 0xbc7ae7(%rip),%r11 = # 0x10042f8 =E2=94=82 - 43c811: 4c 89 05 d0 7a bc 00 mov %r8,0xbc7ad0(%rip) = # 0x10042e8 =E2=94=82 + 43c811: 4c 89 1d d0 7a bc 00 mov %r11,0xbc7ad0(%rip) = # 0x10042e8 =E2=94=82 - 43c818: 4c 3b 05 d1 7a bc 00 cmp 0xbc7ad1(%rip),%r8 = # 0x10042f0 =E2=94=82 + 43c818: 4c 3b 1d d1 7a bc 00 cmp 0xbc7ad1(%rip),%r11 = # 0x10042f0 =E2=94=82 43c81f: 76 07 jbe 0x43c828 =E2=94=82 - 43c821: 4c 89 05 c8 7a bc 00 mov %r8,0xbc7ac8(%rip) = # 0x10042f0 =E2=94=82 + 43c821: 4c 89 1d c8 7a bc 00 mov %r11,0xbc7ac8(%rip) = # 0x10042f0 =E2=94=82 43c828: 48 b8 00 00 00 00 01 mov $0x100000000,%rax =E2=94=82 43c82f: 00 00 00 =E2=94=82 43c832: 49 01 c6 add %rax,%r14 =E2=94=82 43c835: 49 c1 fe 20 sar $0x20,%r14 =E2=94=82 43c839: 4c 01 f3 add %r14,%rbx =E2=94=82 43c83c: eb 03 jmp 0x43c841 =E2=94=82 - 43c83e: 45 31 c0 xor %r8d,%r8d =E2=94=82 + 43c83e: 45 31 db xor %r11d,%r11d =E2=94=82 - 43c841: 44 8a 3b mov (%rbx),%r15b =E2=94=82 + 43c841: 8a 0b mov (%rbx),%cl =E2=94=82 - 43c844: 45 31 c9 xor %r9d,%r9d =E2=94=82 + 43c843: 45 31 c9 xor %r9d,%r9d =E2=94=82 - 43c847: 45 84 ff test %r15b,%r15b =E2=94=82 + 43c846: 84 c9 test %cl,%cl =E2=94=82 + 43c848: 4c 89 ad 00 ff ff ff mov %r13,-0x100(%rbp) =E2=94=82 - 43c84a: 74 60 je 0x43c8ac =E2=94=82 + 43c84f: 74 4f je 0x43c8a0 =E2=94=82 - 43c84c: 45 31 f6 xor %r14d,%r14d =E2=94=82 + 43c851: 45 31 e4 xor %r12d,%r12d =E2=94=82 - 43c84f: 48 b8 01 00 00 00 89 mov $0x1288900000001,%rax =E2=94=82 - 43c856: 28 01 00 =E2=94=82 + 43c854: 48 b8 01 00 00 00 89 mov $0x1288900000001,%rax =E2=94=82 + 43c85b: 28 01 00 =E2=94=82 - 43c859: 0f 1f 80 00 00 00 00 nopl 0x0(%rax) =E2=94=82 + 43c85e: 66 90 xchg %ax,%ax =E2=94=82 43c860: ba 01 00 00 00 mov $0x1,%edx =E2=94=82 - 43c865: 44 89 f9 mov %r15d,%ecx =E2=94=82 - 43c868: 48 d3 e2 shl %cl,%rdx =E2=94=82 + 43c865: 48 d3 e2 shl %cl,%rdx =E2=94=82 - 43c86b: 41 80 ff 3f cmp $0x3f,%r15b =E2=94=82 + 43c868: 80 f9 3f cmp $0x3f,%cl =E2=94=82 - 43c86f: 0f 87 73 01 00 00 ja 0x43c9e8 =E2=94=82 + 43c86b: 0f 87 60 01 00 00 ja 0x43c9d1 =E2=94=82 - 43c875: 48 21 c2 and %rax,%rdx =E2=94=82 + 43c871: 48 21 c2 and %rax,%rdx =E2=94=82 - 43c878: 0f 84 6a 01 00 00 je 0x43c9e8 =E2=94=82 + 43c874: 0f 84 57 01 00 00 je 0x43c9d1 =E2=94=82 - 43c87e: 47 88 7c 35 01 mov %r15b,0x1(%r13,%r14,= 1) =E2=94=82 + 43c87a: 43 88 4c 27 01 mov %cl,0x1(%r15,%r12,1) =E2=94=82 - 43c883: 43 c6 44 35 02 00 movb $0x0,0x2(%r13,%r14,1) =E2=94=82 + 43c87f: 43 c6 44 27 02 00 movb $0x0,0x2(%r15,%r12,1) =E2=94=82 - 43c889: 46 0f b6 7c 33 01 movzbl 0x1(%rbx,%r14,1),%r1= 5d =E2=94=82 + 43c885: 42 0f b6 4c 23 01 movzbl 0x1(%rbx,%r12,1),%ecx =E2=94=82 - 43c88f: 49 83 c6 01 add $0x1,%r14 =E2=94=82 + 43c88b: 49 83 c4 01 add $0x1,%r12 =E2=94=82 + 43c88f: 84 c9 test %cl,%cl =E2=94=82 - 43c803: 4c 63 c2 movslq %edx,%r8 =E2=94=82 + 43c803: 4c 63 da movslq %edx,%r11 =E2=94=82 - 43c806: 49 c1 e0 03 shl $0x3,%r8 =E2=94=82 + 43c806: 49 c1 e3 03 shl $0x3,%r11 =E2=94=82 - 43c80a: 4c 03 05 e7 7a bc 00 add 0xbc7ae7(%rip),%r8 = # 0x10042f8 =E2=94=82 + 43c80a: 4c 03 1d e7 7a bc 00 add 0xbc7ae7(%rip),%r11 = # 0x10042f8 =E2=94=82 - 43c811: 4c 89 05 d0 7a bc 00 mov %r8,0xbc7ad0(%rip) = # 0x10042e8 =E2=94=82 + 43c811: 4c 89 1d d0 7a bc 00 mov %r11,0xbc7ad0(%rip) = # 0x10042e8 =E2=94=82 - 43c818: 4c 3b 05 d1 7a bc 00 cmp 0xbc7ad1(%rip),%r8 = # 0x10042f0 =E2=94=82 + 43c818: 4c 3b 1d d1 7a bc 00 cmp 0xbc7ad1(%rip),%r11 = # 0x10042f0 =E2=94=82 43c81f: 76 07 jbe 0x43c828 =E2=94=82 - 43c821: 4c 89 05 c8 7a bc 00 mov %r8,0xbc7ac8(%rip) = # 0x10042f0 =E2=94=82 + 43c821: 4c 89 1d c8 7a bc 00 mov %r11,0xbc7ac8(%rip) = # 0x10042f0 =E2=94=82 - 43c865: 44 89 f9 mov %r15d,%ecx =E2=94=82 - 43c868: 48 d3 e2 shl %cl,%rdx =E2=94=82 + 43c865: 48 d3 e2 shl %cl,%rdx =E2=94=82 - 43c86b: 41 80 ff 3f cmp $0x3f,%r15b =E2=94=82 + 43c868: 80 f9 3f cmp $0x3f,%cl =E2=94=82 - 43c86f: 0f 87 73 01 00 00 ja 0x43c9e8 =E2=94=82 + 43c86b: 0f 87 60 01 00 00 ja 0x43c9d1 =E2=94=82 - 43c875: 48 21 c2 and %rax,%rdx =E2=94=82 + 43c871: 48 21 c2 and %rax,%rdx =E2=94=82 - 43c878: 0f 84 6a 01 00 00 je 0x43c9e8 =E2=94=82 + 43c874: 0f 84 57 01 00 00 je 0x43c9d1 =E2=94=82 - 43c87e: 47 88 7c 35 01 mov %r15b,0x1(%r13,%r14,= 1) =E2=94=82 + 43c87a: 43 88 4c 27 01 mov %cl,0x1(%r15,%r12,1) I have trouble figuring out how core counts would affect the compiler in th= is way, though. --=20 You are receiving this mail because: You are the assignee for the bug.=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-246630-227-s9nyCV0b9k>