123 lines
6.0 KiB
LLVM
123 lines
6.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -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"
|
|
target triple = "x86_64-apple-macosx10.8.0"
|
|
|
|
@c = common global [2048 x i32] zeroinitializer, align 16
|
|
@b = common global [2048 x i32] zeroinitializer, align 16
|
|
@d = common global [2048 x i32] zeroinitializer, align 16
|
|
@a = common global [2048 x i32] zeroinitializer, align 16
|
|
|
|
; The program below gathers and scatters data. We better not vectorize it.
|
|
define void @cost_model_1() nounwind uwtable noinline ssp {
|
|
; CHECK-LABEL: @cost_model_1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = shl nsw i64 [[INDVARS_IV]], 1
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 [[TMP0]]
|
|
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX]], align 8
|
|
; CHECK-NEXT: [[IDXPROM1:%.*]] = sext i32 [[TMP1]] to i64
|
|
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 [[IDXPROM1]]
|
|
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4
|
|
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @d, i64 0, i64 [[INDVARS_IV]]
|
|
; CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* [[ARRAYIDX4]], align 4
|
|
; CHECK-NEXT: [[IDXPROM5:%.*]] = sext i32 [[TMP3]] to i64
|
|
; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 [[IDXPROM5]]
|
|
; CHECK-NEXT: store i32 [[TMP2]], i32* [[ARRAYIDX6]], align 4
|
|
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1
|
|
; CHECK-NEXT: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
|
|
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], 256
|
|
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
|
|
; CHECK: for.end:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%0 = shl nsw i64 %indvars.iv, 1
|
|
%arrayidx = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 %0
|
|
%1 = load i32, i32* %arrayidx, align 8
|
|
%idxprom1 = sext i32 %1 to i64
|
|
%arrayidx2 = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 %idxprom1
|
|
%2 = load i32, i32* %arrayidx2, align 4
|
|
%arrayidx4 = getelementptr inbounds [2048 x i32], [2048 x i32]* @d, i64 0, i64 %indvars.iv
|
|
%3 = load i32, i32* %arrayidx4, align 4
|
|
%idxprom5 = sext i32 %3 to i64
|
|
%arrayidx6 = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 %idxprom5
|
|
store i32 %2, i32* %arrayidx6, 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 %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
; This function uses a stride that is generally too big to benefit from vectorization without
|
|
; really good support for a gather load. We were not computing an accurate cost for the
|
|
; vectorization and subsequent scalarization of the pointer induction variables.
|
|
|
|
define float @PR27826(float* nocapture readonly %a, float* nocapture readonly %b, i32 %n) {
|
|
; CHECK-LABEL: @PR27826(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i32 [[N:%.*]], 0
|
|
; CHECK-NEXT: br i1 [[CMP]], label [[PREHEADER:%.*]], label [[FOR_END:%.*]]
|
|
; CHECK: preheader:
|
|
; CHECK-NEXT: [[T0:%.*]] = sext i32 [[N]] to i64
|
|
; CHECK-NEXT: br label [[FOR:%.*]]
|
|
; CHECK: for:
|
|
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[PREHEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR]] ]
|
|
; CHECK-NEXT: [[S_02:%.*]] = phi float [ 0.000000e+00, [[PREHEADER]] ], [ [[ADD4:%.*]], [[FOR]] ]
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[INDVARS_IV]]
|
|
; CHECK-NEXT: [[T1:%.*]] = load float, float* [[ARRAYIDX]], align 4
|
|
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 [[INDVARS_IV]]
|
|
; CHECK-NEXT: [[T2:%.*]] = load float, float* [[ARRAYIDX3]], align 4
|
|
; CHECK-NEXT: [[ADD:%.*]] = fadd fast float [[T1]], [[S_02]]
|
|
; CHECK-NEXT: [[ADD4]] = fadd fast float [[ADD]], [[T2]]
|
|
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 32
|
|
; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i64 [[INDVARS_IV_NEXT]], [[T0]]
|
|
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR]], label [[LOOPEXIT:%.*]]
|
|
; CHECK: loopexit:
|
|
; CHECK-NEXT: [[ADD4_LCSSA:%.*]] = phi float [ [[ADD4]], [[FOR]] ]
|
|
; CHECK-NEXT: br label [[FOR_END]]
|
|
; CHECK: for.end:
|
|
; CHECK-NEXT: [[S_0_LCSSA:%.*]] = phi float [ 0.000000e+00, [[ENTRY:%.*]] ], [ [[ADD4_LCSSA]], [[LOOPEXIT]] ]
|
|
; CHECK-NEXT: ret float [[S_0_LCSSA]]
|
|
;
|
|
entry:
|
|
%cmp = icmp sgt i32 %n, 0
|
|
br i1 %cmp, label %preheader, label %for.end
|
|
|
|
preheader:
|
|
%t0 = sext i32 %n to i64
|
|
br label %for
|
|
|
|
for:
|
|
%indvars.iv = phi i64 [ 0, %preheader ], [ %indvars.iv.next, %for ]
|
|
%s.02 = phi float [ 0.0, %preheader ], [ %add4, %for ]
|
|
%arrayidx = getelementptr inbounds float, float* %a, i64 %indvars.iv
|
|
%t1 = load float, float* %arrayidx, align 4
|
|
%arrayidx3 = getelementptr inbounds float, float* %b, i64 %indvars.iv
|
|
%t2 = load float, float* %arrayidx3, align 4
|
|
%add = fadd fast float %t1, %s.02
|
|
%add4 = fadd fast float %add, %t2
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 32
|
|
%cmp1 = icmp slt i64 %indvars.iv.next, %t0
|
|
br i1 %cmp1, label %for, label %loopexit
|
|
|
|
loopexit:
|
|
%add4.lcssa = phi float [ %add4, %for ]
|
|
br label %for.end
|
|
|
|
for.end:
|
|
%s.0.lcssa = phi float [ 0.0, %entry ], [ %add4.lcssa, %loopexit ]
|
|
ret float %s.0.lcssa
|
|
}
|
|
|