[PATCH] [X86] New pass that moves immediate operands to registers.

[Quentin Colombet]

Hi Serge,

The constant hoisting pass does this kind of things. Should we try to teach it to handle this kind of cases?

Moreover, this may be beneficial for code size, but I guess it is generally not beneficial for performances. Therefore, I believe this should be done for functions with the Os or Oz attributes only.

CC’ed Juergen to have his thoughts on the constant hoisting stuff.

Thanks,
-Quentin 
On Sep 30, 2014, at 10:24 AM, Serge Pavlov <sepavloff at gmail.com> wrote:

> The pass scans machine instructions looking for uses of immediate
> values. If the same value is used in neighbouring instructions, it
> is moved to a register, if this is possible and reduces code size.
> For instance, instructions
> 
>    mov $0, 0x4(%esi)
>    mov $0, 0x8(%esi)
> 
> can be replaced by
> 
>    mov $0, %eax
>    mov %eax, 0x4(%esi)
>    mov %eax, 0x8(%esi)
> 
> which is shorter in code size.
> 
> This patch fixes PR5124, it uses feedback on the previous patch discussed in the thread
> http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20130916/188079.html .
> 
> http://reviews.llvm.org/D5544
> 
> Files:
>  lib/Target/X86/CMakeLists.txt
>  lib/Target/X86/X86.h
>  lib/Target/X86/X86MaterializeImmediates.cpp
>  lib/Target/X86/X86TargetMachine.cpp
>  test/CodeGen/X86/coalescer-commute3.ll
>  test/CodeGen/X86/fast-isel-x86.ll
>  test/CodeGen/X86/materialize-imm.ll
>  test/CodeGen/X86/memcpy-2.ll
>  test/CodeGen/X86/memset.ll
>  test/CodeGen/X86/memset64-on-x86-32.ll
>  test/CodeGen/X86/nancvt.ll
>  test/CodeGen/X86/pr14562.ll
>  test/CodeGen/X86/pr18023.ll
>  test/CodeGen/X86/tlv-1.ll
>  test/CodeGen/X86/xmulo.ll
>  test/DebugInfo/X86/debug-loc-offset.ll
> <D5544.14236.patch>_______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits