https://bugs.kde.org/show_bug.cgi?id=442168
--- Comment #10 from Paul Floyd ---
As I sort of expected, my PC is too old:
CPU: Intel(R) Xeon(R) CPU W3520 @ 2.67GHz (2666.73-MHz K8-class CPU)
Origin="GenuineIntel" Id=0x106a5 Family=0x6 Model=0x1a Stepping=5
Features=0xbfebfbff
https://bugs.kde.org/show_bug.cgi?id=442168
--- Comment #9 from Paul Floyd ---
I'll have a try with this tonight to see what I can reproduce.
--
You are receiving this mail because:
You are watching all bug changes.
https://bugs.kde.org/show_bug.cgi?id=442168
--- Comment #8 from Julian Seward ---
(In reply to Xavier Roche from comment #7)
I checked V's {V,}MOVSD implementation more, and still find no problem
I think this is unrelated to those insns.
If I had to guess, I'd say it *might* be related to the
https://bugs.kde.org/show_bug.cgi?id=442168
--- Comment #7 from Xavier Roche ---
(In reply to Julian Seward from comment #4)
> (In reply to Xavier Roche from comment #2)
>
> > The difference between the correctly executed code under valgrind and the
> > faulty one:
>
> > - movsd %xmm0,
https://bugs.kde.org/show_bug.cgi?id=442168
--- Comment #6 from Xavier Roche ---
Created attachment 141820
--> https://bugs.kde.org/attachment.cgi?id=141820=edit
ASM diff between working program with valgrind (clang-11) and the faulty one
(clang12)
clang-12 -S -std=c++20 -stdlib=libc++ -O2
https://bugs.kde.org/show_bug.cgi?id=442168
--- Comment #5 from Julian Seward ---
Looking at the Intel docs for MOVSD and VMOVSD, and comparing against
what guest_amd64_toIR.c implements, I don't see any error in the
implementation. Plus, both of those must be at least moderately commonly
https://bugs.kde.org/show_bug.cgi?id=442168
--- Comment #4 from Julian Seward ---
(In reply to Xavier Roche from comment #2)
> The difference between the correctly executed code under valgrind and the
> faulty one:
> - movsd %xmm0, (%rsp) # 8-byte Spill
> +
https://bugs.kde.org/show_bug.cgi?id=442168
--- Comment #3 from Paul Floyd ---
Do you know if it is possible to reproduce this issue either with GCC or an
older C++ standard, or even both? The reason that I ask is that integrating
this testcase, at least on Linux, will be rather difficult.
I
https://bugs.kde.org/show_bug.cgi?id=442168
Paul Floyd changed:
What|Removed |Added
Summary|Floating-point erroneous|Floating-point erroneous
