looks like there is an unaligned XMM store:

(gdb) info reg
rax            0x0	0
rbx            0x0	0
rcx            0x7fffffffc660	140737488340576
rdx            0x55555574eff0	93824994308080
rsi            0x555555748d90	93824994282896
rdi            0x7fffffffc810	140737488341008
rbp            0x7fffffffc080	0x7fffffffc080
rsp            0x7fffffffc008	0x7fffffffc008
r8             0x55555574fad0	93824994310864
r9             0x7fffffffbdcc	140737488338380
r10            0x1	1
r11            0x2	2
r12            0x7ffff45637b8	140737292679096
r13            0x555555752580	93824994321792
r14            0x7fffffffc320	140737488339744
r15            0x555555748d90	93824994282896
rip            0x7ffff4371e06	0x7ffff4371e06 <r600_sb::alu_group_tracker::alu_group_tracker(r600_sb::shader&)+38>
eflags         0x10246	[ PF ZF IF RF ]
cs             0x33	51
ss             0x2b	43
ds             0x0	0
es             0x0	0
fs             0x0	0
gs             0x0	0
(gdb) disas
Dump of assembler code for function r600_sb::alu_group_tracker::alu_group_tracker(r600_sb::shader&):
   0x00007ffff4371de0 <+0>:	pxor   %xmm1,%xmm1
   0x00007ffff4371de4 <+4>:	pxor   %xmm0,%xmm0
   0x00007ffff4371de8 <+8>:	xor    %eax,%eax
   0x00007ffff4371dea <+10>:	movups %xmm1,0xb0(%rdi)
   0x00007ffff4371df1 <+17>:	movups %xmm1,0xc0(%rdi)
   0x00007ffff4371df8 <+24>:	movq   $0x0,0xd0(%rdi)
   0x00007ffff4371e03 <+35>:	mov    (%rsi),%rdx
=> 0x00007ffff4371e06 <+38>:	movaps %xmm0,0x8(%rdi)
   0x00007ffff4371e0a <+42>:	movaps %xmm0,0x18(%rdi)
   0x00007ffff4371e0e <+46>:	movups %xmm0,0x2c(%rdi)
   0x00007ffff4371e12 <+50>:	movups %xmm0,0x3c(%rdi)
   0x00007ffff4371e16 <+54>:	movups %xmm0,0x4c(%rdi)
   0x00007ffff4371e1a <+58>:	movups %xmm0,0x5c(%rdi)
   0x00007ffff4371e1e <+62>:	movups %xmm0,0x6c(%rdi)
   0x00007ffff4371e22 <+66>:	movups %xmm0,0x7c(%rdi)
   0x00007ffff4371e26 <+70>:	movups %xmm0,0x9c(%rdi)
   0x00007ffff4371e2d <+77>:	movl   $0x2,0x28(%rdi)
   0x00007ffff4371e34 <+84>:	movl   $0x0,0x8c(%rdi)
   0x00007ffff4371e3e <+94>:	movl   $0x0,0x90(%rdi)
   0x00007ffff4371e48 <+104>:	movl   $0x0,0x94(%rdi)
   0x00007ffff4371e52 <+114>:	movl   $0x0,0x98(%rdi)
   0x00007ffff4371e5c <+124>:	cmpl   $0x4,0x5c(%rdx)
   0x00007ffff4371e60 <+128>:	mov    %rsi,(%rdi)
   0x00007ffff4371e63 <+131>:	movups %xmm0,0x118(%rdi)
   0x00007ffff4371e6a <+138>:	pxor   %xmm0,%xmm0
   0x00007ffff4371e6e <+142>:	movl   $0x0,0xe8(%rdi)
   0x00007ffff4371e78 <+152>:	setne  %al
   0x00007ffff4371e7b <+155>:	movq   $0x0,0xf0(%rdi)
   0x00007ffff4371e86 <+166>:	add    $0x4,%eax
   0x00007ffff4371e89 <+169>:	movb   $0x0,0x116(%rdi)
   0x00007ffff4371e90 <+176>:	mov    %eax,0xdc(%rdi)
   0x00007ffff4371e96 <+182>:	lea    0xe8(%rdi),%rax
   0x00007ffff4371e9d <+189>:	mov    %rax,0xf8(%rdi)
   0x00007ffff4371ea4 <+196>:	mov    %rax,0x100(%rdi)
   0x00007ffff4371eab <+203>:	xor    %eax,%eax
   0x00007ffff4371ead <+205>:	mov    %ax,0x114(%rdi)
   0x00007ffff4371eb4 <+212>:	movq   $0x0,0x108(%rdi)
   0x00007ffff4371ebf <+223>:	movl   $0x0,0x110(%rdi)
   0x00007ffff4371ec9 <+233>:	movq   $0x0,0x128(%rdi)
   0x00007ffff4371ed4 <+244>:	movups %xmm0,0x130(%rdi)
   0x00007ffff4371edb <+251>:	movq   $0x0,0x140(%rdi)
   0x00007ffff4371ee6 <+262>:	cmpb   $0x1,0x68(%rdx)
   0x00007ffff4371eea <+266>:	sbb    %eax,%eax
   0x00007ffff4371eec <+268>:	and    $0xfffffff0,%eax
   0x00007ffff4371eef <+271>:	add    $0x1f,%eax
   0x00007ffff4371ef2 <+274>:	mov    %eax,0xd8(%rdi)
   0x00007ffff4371ef8 <+280>:	retq