[Openmcl-devel] Inline assembly?
R. Matthew Emerson
rme at clozure.com
Wed Aug 26 14:34:38 EDT 2009
On Aug 26, 2009, at 6:08 AM, Jianshi Huang wrote:
> I'm reading the source code of ccl's backend. Currently the x86
> does not support emitting SSE instructions.
> I'm wondering how much effort does it take to add SSE instruction
> support? Is alignment in the GC a problem?
> If only the compiler backend needs modification I'd like to volunteer
> for the work.
We do use some mmx/sse/sse2 instructions: scalar floating point
operations and some more exotic ones (like pmuldq) in bignum
operations (see the source for %multiply-and-add-loop on a 64-bit
lisp, for example), but it's true that the assembler doesn't recognize
all of them.
These instructions are defined at around line 2987 of
Adding more instructions is not too difficult once you figure out what
the def-x86-opcode macro is expecting.
If you need 16-byte alignment (for instance, in order to use movapd or
whatever), then you generally have to ensure proper alignment yourself
All heap-allocated lisp objects are doublenode (8 bytes on x8632, 16
bytes on x8664) aligned. Double-floats are 8-byte aligned on both
platforms. The elements of vectors have natural alignment.
about how objects are represented in memory in a little more detail.
If you send a patch (or patches) to add more SSE instructions, I'll be
glad to commit it.
If I'm not answering your questions, please don't hesitate to ask for
More information about the Openmcl-devel