blob: 968c19c735e02bc2416ac833142ae1a6448e1260 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
|
<think>
Okay, I need to figure out whether this QEMU bug is related to user-mode or system-mode. The problem involves SSE/SSE2/SSE3 instructions handling NaNs incorrectly compared to a CPU. From the description, it's about how these specific instructions behave with NaN values, leading to different results in QEMU versus actual hardware.
The steps involve compiling code that uses inline assembly with XMM registers and certain memory accesses. This seems like user-mode code because it's executing within an application context without needing special privileges beyond what a typical program would have. The bug report mentions that the behavior is incorrect as per Intel's manual, so it's about how QEMU emulates these instructions in user space.
I don't see any mention of system-level components like device drivers, interrupt handling, or kernel operations here. It's purely about instruction execution and register state within a program, which points to user-mode emulation issues.
So, this bug is likely related to the user-mode part of QEMU.
</think>
user
|