a99dd8344e
Many tests were running extra passes after loop-vectorize, but they made no difference to the outcome. If tests don't require these extra passes, then we shouldn't run them because it increases the testing time.
61 lines
2.0 KiB
LLVM
61 lines
2.0 KiB
LLVM
; RUN: opt < %s -passes=loop-vectorize -mtriple=thumbv7-apple-ios3.0.0 -mcpu=swift -S | FileCheck %s
|
|
|
|
target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
|
|
target triple = "thumbv7-apple-ios3.0.0"
|
|
|
|
@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
|
|
|
|
; Select VF = 8;
|
|
;CHECK-LABEL: @example1(
|
|
;CHECK: load <4 x i32>
|
|
;CHECK: add nsw <4 x i32>
|
|
;CHECK: store <4 x i32>
|
|
;CHECK: ret void
|
|
define void @example1() {
|
|
br label %1
|
|
|
|
; <label>:
|
|
%indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
|
|
%2 = getelementptr inbounds [2048 x i32], ptr @b, i64 0, i64 %indvars.iv
|
|
%3 = load i32, ptr %2, align 4
|
|
%4 = getelementptr inbounds [2048 x i32], ptr @c, i64 0, i64 %indvars.iv
|
|
%5 = load i32, ptr %4, align 4
|
|
%6 = add nsw i32 %5, %3
|
|
%7 = getelementptr inbounds [2048 x i32], ptr @a, i64 0, i64 %indvars.iv
|
|
store i32 %6, ptr %7, 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, 256
|
|
br i1 %exitcond, label %8, label %1
|
|
|
|
; <label>:
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: @example10b(
|
|
;CHECK: load <4 x i16>
|
|
;CHECK: sext <4 x i16>
|
|
;CHECK: store <4 x i32>
|
|
;CHECK: ret void
|
|
define void @example10b(ptr noalias nocapture %sa, ptr noalias nocapture %sb, ptr noalias nocapture %sc, ptr noalias nocapture %ia, ptr noalias nocapture %ib, ptr noalias nocapture %ic) {
|
|
br label %1
|
|
|
|
; <label>:
|
|
%indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
|
|
%2 = getelementptr inbounds i16, ptr %sb, i64 %indvars.iv
|
|
%3 = load i16, ptr %2, align 2
|
|
%4 = sext i16 %3 to i32
|
|
%5 = getelementptr inbounds i32, ptr %ia, i64 %indvars.iv
|
|
store i32 %4, ptr %5, 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, 1024
|
|
br i1 %exitcond, label %6, label %1
|
|
|
|
; <label>:
|
|
ret void
|
|
}
|
|
|