mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-26 04:40:38 +00:00
fd3659df66
Generate a single test to decide if there are enough iterations to jump to the vectorized loop, or else go to the scalar remainder loop. This test compares the Scalar Trip Count: if STC < VF * UF go to the scalar loop. If requiresScalarEpilogue() holds, at-least one iteration must remain scalar; the rest can be used to form vector iterations. So in this case the test checks instead if (STC - 1) < VF * UF by comparing STC <= VF * UF, and going to the scalar loop if so. Otherwise the vector loop is entered for at-least one vector iteration. This test covers the case where incrementing the backedge-taken count will overflow leading to an incorrect trip count of zero. In this (rare) case we will also avoid the vector loop and jump to the scalar loop. This patch simplifies the existing tests and effectively removes the basic-block originally named "min.iters.checked", leaving the single test in block "vector.ph". Original observation and initial patch by Evgeny Stupachenko. Differential Revision: https://reviews.llvm.org/D34150 llvm-svn: 308421
45 lines
1.9 KiB
LLVM
45 lines
1.9 KiB
LLVM
; RUN: opt %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -S | FileCheck %s
|
|
; RUN: opt %s -loop-vectorize -force-vector-interleave=2 -force-vector-width=4 -S | FileCheck %s -check-prefix=UNROLL
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
|
|
@b = common global [1000 x i32] zeroinitializer, align 16
|
|
@c = common global [1000 x i32] zeroinitializer, align 16
|
|
@a = common global [1000 x i32] zeroinitializer, align 16
|
|
|
|
; Generate min.iters.check to skip the vector loop and jump to scalar.ph directly when loop iteration number is less than VF * UF.
|
|
; CHECK-LABEL: foo(
|
|
; CHECK: %min.iters.check = icmp ult i64 %N, 4
|
|
; CHECK: br i1 %min.iters.check, label %scalar.ph, label %vector.ph
|
|
; UNROLL-LABEL: foo(
|
|
; UNROLL: %min.iters.check = icmp ult i64 %N, 8
|
|
; UNROLL: br i1 %min.iters.check, label %scalar.ph, label %vector.ph
|
|
|
|
define void @foo(i64 %N) {
|
|
entry:
|
|
%cmp.8 = icmp sgt i64 %N, 0
|
|
br i1 %cmp.8, label %for.body.preheader, label %for.end
|
|
|
|
for.body.preheader: ; preds = %entry
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %for.body.preheader
|
|
%i.09 = phi i64 [ %inc, %for.body ], [ 0, %for.body.preheader ]
|
|
%arrayidx = getelementptr inbounds [1000 x i32], [1000 x i32]* @b, i64 0, i64 %i.09
|
|
%tmp = load i32, i32* %arrayidx, align 4
|
|
%arrayidx1 = getelementptr inbounds [1000 x i32], [1000 x i32]* @c, i64 0, i64 %i.09
|
|
%tmp1 = load i32, i32* %arrayidx1, align 4
|
|
%add = add nsw i32 %tmp1, %tmp
|
|
%arrayidx2 = getelementptr inbounds [1000 x i32], [1000 x i32]* @a, i64 0, i64 %i.09
|
|
store i32 %add, i32* %arrayidx2, align 4
|
|
%inc = add nuw nsw i64 %i.09, 1
|
|
%exitcond = icmp eq i64 %inc, %N
|
|
br i1 %exitcond, label %for.end.loopexit, label %for.body
|
|
|
|
for.end.loopexit: ; preds = %for.body
|
|
br label %for.end
|
|
|
|
for.end: ; preds = %for.end.loopexit, %entry
|
|
ret void
|
|
}
|