mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-11 14:57:05 +00:00
This new version is much more aggressive about doing "full" reduction in cases where it reduces register pressure, and also more aggressive about rewriting induction variables to count down (or up) to zero when doing so reduces register pressure. It currently uses fairly simplistic algorithms for finding reuse opportunities, but it introduces a new framework allows it to combine multiple strategies at once to form hybrid solutions, instead of doing all full-reduction or all base+index. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@94061 91177308-0d34-0410-b5e6-96231b3b80d8
40 lines
1.5 KiB
LLVM
40 lines
1.5 KiB
LLVM
; RUN: llc < %s -march=x86 >%t
|
|
|
|
; TODO: Enhance full lsr mode to get this:
|
|
; RUNX: grep {addl \\\$4,} %t | count 3
|
|
; RUNX: not grep {,%} %t
|
|
|
|
; For now, it should find this, which is still pretty good:
|
|
; RUN: not grep {addl \\\$4,} %t
|
|
; RUN: grep {,%} %t | count 6
|
|
|
|
define void @foo(float* nocapture %A, float* nocapture %B, float* nocapture %C, i32 %N) nounwind {
|
|
entry:
|
|
%0 = icmp sgt i32 %N, 0 ; <i1> [#uses=1]
|
|
br i1 %0, label %bb, label %return
|
|
|
|
bb: ; preds = %bb, %entry
|
|
%i.03 = phi i32 [ 0, %entry ], [ %indvar.next, %bb ] ; <i32> [#uses=5]
|
|
%1 = getelementptr float* %A, i32 %i.03 ; <float*> [#uses=1]
|
|
%2 = load float* %1, align 4 ; <float> [#uses=1]
|
|
%3 = getelementptr float* %B, i32 %i.03 ; <float*> [#uses=1]
|
|
%4 = load float* %3, align 4 ; <float> [#uses=1]
|
|
%5 = fadd float %2, %4 ; <float> [#uses=1]
|
|
%6 = getelementptr float* %C, i32 %i.03 ; <float*> [#uses=1]
|
|
store float %5, float* %6, align 4
|
|
%7 = add i32 %i.03, 10 ; <i32> [#uses=3]
|
|
%8 = getelementptr float* %A, i32 %7 ; <float*> [#uses=1]
|
|
%9 = load float* %8, align 4 ; <float> [#uses=1]
|
|
%10 = getelementptr float* %B, i32 %7 ; <float*> [#uses=1]
|
|
%11 = load float* %10, align 4 ; <float> [#uses=1]
|
|
%12 = fadd float %9, %11 ; <float> [#uses=1]
|
|
%13 = getelementptr float* %C, i32 %7 ; <float*> [#uses=1]
|
|
store float %12, float* %13, align 4
|
|
%indvar.next = add i32 %i.03, 1 ; <i32> [#uses=2]
|
|
%exitcond = icmp eq i32 %indvar.next, %N ; <i1> [#uses=1]
|
|
br i1 %exitcond, label %return, label %bb
|
|
|
|
return: ; preds = %bb, %entry
|
|
ret void
|
|
}
|