mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-29 10:32:47 +00:00
6bbb01bbf8
The generic (concatenation) loop unroller is currently placed early in the standard optimization pipeline. This is a good place to perform full unrolling, but not the right place to perform partial/runtime unrolling. However, most targets don't enable partial/runtime unrolling, so this never mattered. However, even some x86 cores benefit from partial/runtime unrolling of very small loops, and follow-up commits will enable this. First, we need to move partial/runtime unrolling late in the optimization pipeline (importantly, this is after SLP and loop vectorization, as vectorization can drastically change the size of a loop), while keeping the full unrolling where it is now. This change does just that. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205264 91177308-0d34-0410-b5e6-96231b3b80d8
47 lines
2.0 KiB
LLVM
47 lines
2.0 KiB
LLVM
; RUN: opt < %s -disable-loop-unrolling -debug-only=loop-vectorize -O3 -S 2>&1 | FileCheck %s
|
|
; REQUIRES: asserts
|
|
; We want to make sure that we don't even try to vectorize loops again
|
|
; The vectorizer used to mark the un-vectorized loop only as already vectorized
|
|
; thus, trying to vectorize the vectorized loop again
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
@a = external global [255 x i32]
|
|
|
|
; Function Attrs: nounwind readonly uwtable
|
|
define i32 @vect() {
|
|
; CHECK: LV: Checking a loop in "vect"
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
; We need to make sure we did vectorize the loop
|
|
; CHECK: LV: Found a loop: for.body
|
|
; CHECK: LV: We can vectorize this loop!
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%red.05 = phi i32 [ 0, %entry ], [ %add, %for.body ]
|
|
%arrayidx = getelementptr inbounds [255 x i32]* @a, i64 0, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%add = add nsw i32 %0, %red.05
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 255
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
; If it did, we have two loops:
|
|
; CHECK: vector.body:
|
|
; CHECK: br {{.*}} label %vector.body, !llvm.loop [[vect:![0-9]+]]
|
|
; CHECK: for.body:
|
|
; CHECK: br {{.*}} label %for.body, !llvm.loop [[scalar:![0-9]+]]
|
|
|
|
for.end: ; preds = %for.body
|
|
ret i32 %add
|
|
}
|
|
|
|
; Now, we check for the Hint metadata
|
|
; CHECK: [[vect]] = metadata !{metadata [[vect]], metadata [[width:![0-9]+]], metadata [[unroll:![0-9]+]]}
|
|
; CHECK: [[width]] = metadata !{metadata !"llvm.vectorizer.width", i32 1}
|
|
; CHECK: [[unroll]] = metadata !{metadata !"llvm.vectorizer.unroll", i32 1}
|
|
; CHECK: [[scalar]] = metadata !{metadata [[scalar]], metadata [[width]], metadata [[unroll]]}
|
|
|