blob: f92c8bc05d0022d3f8a3f6e215d64c27ae96e70f (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
|
<think>
Alright, let me try to figure out how to classify this bug report. The user provided a detailed issue about SSE/SSE2/SSE3 instructions handling NaNs incorrectly in QEMU compared to real CPUs. They included code that uses assembly instructions and observed different results between CPU execution and QEMU.
First, the problem is related to instruction handling because it mentions specific SSE instructions like addsubps not behaving as expected with NaN values. The issue arises during the execution of these instructions, leading to incorrect results in QEMU versus a real CPU.
The user also provided steps to reproduce, which involves compiling code that uses inline assembly, pushing certain values onto the stack, and then performing an addsubps operation on XMM registers. This suggests it's not a syscall issue because it doesn't involve system calls; instead, it's about how instructions are executed in the CPU emulator.
Looking at the possible categories: instruction, syscall, runtime. Since the bug is directly related to the handling of specific CPU instructions and their semantics with NaNs, the appropriate category would be 'instruction'. It's not a runtime error in general because it specifically points out incorrect behavior of certain instructions.
</think>
The issue pertains to how QEMU handles specific SSE/SSE2/SSE3 instructions when dealing with NaN values. The problem is directly related to the implementation of these instructions and their expected behavior as per Intel's manual, indicating a faulty instruction handling.
**Answer:**
instruction
|