Excellent question! One use-case for such a blunt-acting instruction as invd is in specialized or very-early-bootstrap code, such as when the presence or absence of RAM has not yet been verified. Since we might not know whether RAM is present, its size, or even if particular parts of it function properly, or we might not … Read more
I think it’s just R for “register”, since there are additional registers R8 – R15 on x86-64, and R is a common prefix on many CPU architectures where registers are numbered.
The instruction is loading a new EIP value from memory at ds:[40207A]. i.e. there’s a function pointer at address 40207A. (And it pushes a return address because this is a call not just a jmp.) The ds: means the instruction is referencing memory in the Data Segment – and can pretty much be ignored on … Read more
No, a 64-bit process can only load 64-bit DLLs and a 32-bit process can only load 32-bit DLLs. What you’re probably thinking of is that a 64-bit operating system can run 32-bit processes. The main issue with .NET is that – prior to VS2010 – executable projects defaulted to “AnyCPU” which means it would load … Read more
In the Intel® 64 and IA-32 Architectures Developer’s Manual: Vol. 3A, which nowadays contains the specifications of the memory ordering white paper you mention, it is said in section 8.1.1 that: The Intel486 processor (and newer processors since) guarantees that the following basic memory operations will always be carried out atomically: Reading or writing a … Read more
When the function is called, the stack looks like: +————-+ | Parameter 2 | +————-+ | Parameter 1 | +————-+ | Return Addr | <– esp +————-+ then after the “stack frame” is set up: +————-+ | Parameter 2 | <– [ebp + 12] +————-+ | Parameter 1 | <– [ebp + 8] +————-+ | … Read more
Here’s a great article on the subject: http://arstechnica.com/gadgets/reviews/2002/07/caching.ars/1 To answer your question – yes, a cache hit has approximately the same cost as a register access. And of course a cache miss is quite costly 😉 PS: The specifics will vary, but this link has some good ballpark figures: Approximate cost to access various caches … Read more
These instruction prefixes have no effect on modern processors (anything newer than Pentium 4). They just cost one byte of code space, and thus, not generating them is the right thing. For details, see Agner Fog’s optimization manuals, in particular 3. Microarchitecture: http://www.agner.org/optimize/ The “Intel® 64 and IA-32 Architectures Optimization Reference Manual” no longer mentions … Read more
For my final year project in collage I developed a small x86 OS with a virtual memory manager, a virtual file system and fully preemptive multitasking. I made it open source and the code is heavily commented, check out its source forge page at: https://github.com/stephenfewer/NoNameOS From my experience I can recommend the following: You will … Read more
unwind’s explanation is the literal truth (one minor directional error notwithstanding), but doesn’t explain why. %ebp is the “base pointer” for your stack frame. It’s the pointer used by the C runtime to access local variables and parameters on the stack. Here’s some typical function prologue code generated by GCC (g++ to be precise) First … Read more