1
2
3
4
5
6
7
8
9
10
11
12
13
|
<think>
Okay, let's try to figure out what category this bug report falls into. The user says it's part of QEMU, and they're seeing issues with Python regression tests failing due to floating-point precision problems.
The problem seems to be related to the x87 emulation in QEMU. The user mentions that QEMU's x87 emulation for trigonometric and other complex operations is only using 64-bit precision instead of 80-bit. That's important because the x87 FPU typically uses 80-bit internal registers, and if QEMU is emulating it with 64 bits, that would lead to precision loss.
Looking at the test failures: test_cmath, test_float, and test_math. The errors are about values not being close enough, which points to floating-point calculation discrepancies. The specific example in test_float shows a difference in the represented value when converting a float to a string, which suggests that the floating-point computations during the conversion are not precise enough.
The categories given are instruction, syscall, or runtime. The instruction category is for faulty instructions. Since the issue is about the emulation of x87 instructions (like those for trigonometric functions) not using the correct precision, that would relate to how QEMU emulates specific CPU instructions. The problem isn't with a system call (syscall category) because it's about FPU operations, not OS-level calls. Runtime errors are for other runtime issues, but here the core issue is in the instruction emulation.
Therefore, the bug is likely due to QEMU's incorrect emulation of x87 instructions, specifically handling precision. So the correct category should be "instruction".
</think>
instruction
|