mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-21 12:02:58 +02:00
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
38 lines
1.2 KiB
LLVM
38 lines
1.2 KiB
LLVM
; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
|
|
|
|
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"
|
|
|
|
;CHECK-LABEL: @add_ints(
|
|
;CHECK: br
|
|
;CHECK: getelementptr
|
|
;CHECK-DAG: getelementptr
|
|
;CHECK-DAG: icmp ugt
|
|
;CHECK-DAG: icmp ugt
|
|
;CHECK-DAG: icmp ugt
|
|
;CHECK-DAG: icmp ugt
|
|
;CHECK-DAG: and
|
|
;CHECK-DAG: and
|
|
;CHECK: br
|
|
;CHECK: ret
|
|
define void @add_ints(i32* nocapture %A, i32* nocapture %B, i32* nocapture %C) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
|
|
%0 = load i32, i32* %arrayidx, align 4
|
|
%arrayidx2 = getelementptr inbounds i32, i32* %C, i64 %indvars.iv
|
|
%1 = load i32, i32* %arrayidx2, align 4
|
|
%add = add nsw i32 %1, %0
|
|
%arrayidx4 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
|
|
store i32 %add, i32* %arrayidx4, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 200
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end:
|
|
ret void
|
|
}
|