055bfc0271
GEPs are often in the form `gep [N x %T], ptr %p, i64 0, i64 %idx`. Canonicalize these to `gep %T, ptr %p, i64 %idx`. This enables transforms that only support one GEP index to work and improves CSE. Various transforms were recently hardened to make sure they still work without the leading index.
63 lines
2.9 KiB
LLVM
63 lines
2.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 3
|
|
; RUN: opt < %s -passes=loop-vectorize,dce,instcombine -force-vector-interleave=1 -force-vector-width=4 -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"
|
|
|
|
@b = common global [2048 x i32] zeroinitializer, align 16
|
|
@c = common global [2048 x i32] zeroinitializer, align 16
|
|
@a = common global [2048 x i32] zeroinitializer, align 16
|
|
|
|
define void @example1(i32 %n) nounwind uwtable ssp {
|
|
; CHECK-LABEL: define void @example1(
|
|
; CHECK-SAME: i32 [[N:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[N4:%.*]] = shl i32 [[N]], 2
|
|
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[N4]], -4
|
|
; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
|
|
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr @b, i64 [[INDEX]]
|
|
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP2]], align 4
|
|
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, ptr @c, i64 [[INDEX]]
|
|
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <4 x i32>, ptr [[TMP3]], align 4
|
|
; CHECK-NEXT: [[TMP4:%.*]] = add nsw <4 x i32> [[WIDE_LOAD1]], [[WIDE_LOAD]]
|
|
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, ptr @a, i64 [[INDEX]]
|
|
; CHECK-NEXT: store <4 x i32> [[TMP4]], ptr [[TMP5]], align 4
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
|
|
; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX]], [[TMP1]]
|
|
; CHECK-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
|
|
; CHECK: scalar.ph:
|
|
; CHECK-NEXT: br label [[LOOP:%.*]]
|
|
; CHECK: loop:
|
|
; CHECK-NEXT: br i1 poison, label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
|
|
; CHECK: exit:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%n4 = shl i32 %n, 2
|
|
br label %loop
|
|
|
|
loop:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %loop ]
|
|
%gep1 = getelementptr inbounds [2048 x i32], ptr @b, i64 0, i64 %indvars.iv
|
|
%load1 = load i32, ptr %gep1, align 4
|
|
%gep2 = getelementptr inbounds [2048 x i32], ptr @c, i64 0, i64 %indvars.iv
|
|
%load2 = load i32, ptr %gep2, align 4
|
|
%add = add nsw i32 %load2, %load1
|
|
%gep3 = getelementptr inbounds [2048 x i32], ptr @a, i64 0, i64 %indvars.iv
|
|
store i32 %add, ptr %gep3, 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, %n4
|
|
br i1 %exitcond, label %exit, label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|