63 lines
2.6 KiB
LLVM
63 lines
2.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=slp-vectorizer -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | 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"
|
|
|
|
; Simple 3-pair chain with loads and stores
|
|
define void @test1(ptr %a, ptr %b, ptr %c) {
|
|
; CHECK-LABEL: @test1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[AGG_TMP_I_I_SROA_0:%.*]] = alloca [3 x double], align 16
|
|
; CHECK-NEXT: [[STORE1:%.*]] = getelementptr inbounds [3 x double], ptr [[AGG_TMP_I_I_SROA_0]], i64 0, i64 1
|
|
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, ptr [[A:%.*]], align 8
|
|
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x double>, ptr [[B:%.*]], align 8
|
|
; CHECK-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]
|
|
; CHECK-NEXT: store <2 x double> [[TMP4]], ptr [[STORE1]], align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%agg.tmp.i.i.sroa.0 = alloca [3 x double], align 16
|
|
%i0 = load double, ptr %a
|
|
%i1 = load double, ptr %b
|
|
%mul = fmul double %i0, %i1
|
|
%store1 = getelementptr inbounds [3 x double], ptr %agg.tmp.i.i.sroa.0, i64 0, i64 1
|
|
%store2 = getelementptr inbounds [3 x double], ptr %agg.tmp.i.i.sroa.0, i64 0, i64 2
|
|
%arrayidx3 = getelementptr inbounds double, ptr %a, i64 1
|
|
%i3 = load double, ptr %arrayidx3, align 8
|
|
%arrayidx4 = getelementptr inbounds double, ptr %b, i64 1
|
|
%i4 = load double, ptr %arrayidx4, align 8
|
|
%mul5 = fmul double %i3, %i4
|
|
store double %mul, ptr %store1
|
|
store double %mul5, ptr %store2, align 16
|
|
ret void
|
|
}
|
|
|
|
; Float has 4 byte abi alignment on x86_64. We must use the alignment of the
|
|
; value being loaded/stored not the alignment of the pointer type.
|
|
|
|
define void @test2(ptr %a, ptr %b) {
|
|
; CHECK-LABEL: @test2(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr [[A:%.*]], align 4
|
|
; CHECK-NEXT: store <4 x float> [[TMP1]], ptr [[B:%.*]], align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%l0 = load float, ptr %a
|
|
%a1 = getelementptr inbounds float, ptr %a, i64 1
|
|
%l1 = load float, ptr %a1
|
|
%a2 = getelementptr inbounds float, ptr %a, i64 2
|
|
%l2 = load float, ptr %a2
|
|
%a3 = getelementptr inbounds float, ptr %a, i64 3
|
|
%l3 = load float, ptr %a3
|
|
store float %l0, ptr %b
|
|
%b1 = getelementptr inbounds float, ptr %b, i64 1
|
|
store float %l1, ptr %b1
|
|
%b2 = getelementptr inbounds float, ptr %b, i64 2
|
|
store float %l2, ptr %b2
|
|
%b3 = getelementptr inbounds float, ptr %b, i64 3
|
|
store float %l3, ptr %b3
|
|
ret void
|
|
}
|