blob: 4cf0e7def8faadf63e63837b9abf8e544b99c81c (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
|
<think>
Okay, let me try to figure out how to classify this bug report.
The user mentions that the problem is with the Sparc instructions fdtox and fqtox incorrectly selecting the destination register when it's higher than f31. They provided a test program that's supposed to output 60 but prints 0 instead. The issue was introduced in a specific commit related to changes in how destination registers are selected, moving DFPREG/QFPREG to decodetree.
Looking at the categories: instruction, syscall, or runtime.
The problem seems to be with the instruction decoding or execution. The instructions themselves (fdtox and fmovd) are not working correctly when using registers beyond f31. The test case uses inline assembly, so it's directly testing the instruction behavior. The bug is in how the destination register is selected, which is part of the instruction's handling in QEMU's code. Since it's about the instruction's implementation in QEMU, this would fall under the "instruction" category.
Syscall would involve system calls, which isn't the case here. Runtime errors are more about issues during execution that aren't specific to instructions or syscalls, like memory management maybe. But here, the problem is directly with the instruction's operation. So the correct category is "instruction".
</think>
instruction
|