[Kryo] Enable loop prefetcher.

Differential Revision: http://reviews.llvm.org/D21535

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@273329 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AArch64/AArch64Subtarget.cpp b/lib/Target/AArch64/AArch64Subtarget.cpp
index 5904221e1531bc9cd9464eb176d75af2169bf52f..20faf8e6d2e15d1a84b5776dd181c2f3633f7bd8 100644 (file)
--- a/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -70,6 +70,10 @@ void AArch64Subtarget::initializeProperties() {
   case Kryo:
     MaxInterleaveFactor = 4;
     VectorInsertExtractBaseCost = 2;
+    CacheLineSize = 128;
+    PrefetchDistance = 740;
+    MinPrefetchStride = 1024;
+    MaxPrefetchIterationsAhead = 11;
     break;
   case Vulcan: break;
   case CortexA35: break;

diff --git a/test/Transforms/LoopDataPrefetch/AArch64/kryo-large-stride.ll b/test/Transforms/LoopDataPrefetch/AArch64/kryo-large-stride.ll
new file mode 100644 (file)
index 0000000..6433a82
--- /dev/null
+++ b/test/Transforms/LoopDataPrefetch/AArch64/kryo-large-stride.ll
@@ -0,0 +1,51 @@
+; RUN: opt -mcpu=kryo -mtriple=aarch64-gnu-linux -loop-data-prefetch -max-prefetch-iters-ahead=1000 -S < %s | FileCheck %s --check-prefix=LARGE_PREFETCH --check-prefix=ALL
+; RUN: opt -mcpu=kryo -mtriple=aarch64-gnu-linux -loop-data-prefetch -S < %s | FileCheck %s --check-prefix=NO_LARGE_PREFETCH --check-prefix=ALL
+
+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-n32:64-S128"
+
+; ALL-LABEL: @small_stride(
+define void @small_stride(double* nocapture %a, double* nocapture readonly %b) {
+entry:
+  br label %for.body
+
+; ALL: for.body:
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds double, double* %b, i64 %indvars.iv
+; ALL-NOT: call void @llvm.prefetch
+  %0 = load double, double* %arrayidx, align 8
+  %add = fadd double %0, 1.000000e+00
+  %arrayidx2 = getelementptr inbounds double, double* %a, i64 %indvars.iv
+  store double %add, double* %arrayidx2, align 8
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1600
+  br i1 %exitcond, label %for.end, label %for.body
+
+; ALL: for.end:
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+; ALL-LABEL: @large_stride(
+define void @large_stride(double* nocapture %a, double* nocapture readonly %b) {
+entry:
+  br label %for.body
+
+; ALL: for.body:
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds double, double* %b, i64 %indvars.iv
+; LARGE_PREFETCH: call void @llvm.prefetch
+; NO_LARGE_PREFETCH-NOT: call void @llvm.prefetch
+  %0 = load double, double* %arrayidx, align 8
+  %add = fadd double %0, 1.000000e+00
+  %arrayidx2 = getelementptr inbounds double, double* %a, i64 %indvars.iv
+  store double %add, double* %arrayidx2, align 8
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 150 
+  %exitcond = icmp eq i64 %indvars.iv.next, 160000
+  br i1 %exitcond, label %for.end, label %for.body
+
+; ALL: for.end:
+for.end:                                          ; preds = %for.body
+  ret void
+}