[llvm] 1167414 - [LoongArch] Enable LoopDataPrefetch pass

[Xiaodong Liu via llvm-commits]

Author: Xiaodong Liu
Date: 2023-03-24T11:09:18+08:00
New Revision: 11674147e40699202132440313032528dfbf624f

URL: https://github.com/llvm/llvm-project/commit/11674147e40699202132440313032528dfbf624f
DIFF: https://github.com/llvm/llvm-project/commit/11674147e40699202132440313032528dfbf624f.diff

LOG: [LoongArch] Enable LoopDataPrefetch pass

Keep `EnableLoopDataPrefetch` option off for now because
we need a few more TTIs and ISels.

This patch is inspired by http://reviews.llvm.org/D17943.

Reviewed By: SixWeining

Differential Revision: https://reviews.llvm.org/D146600

Added: 
    llvm/test/Transforms/LoopDataPrefetch/LoongArch/basic.ll
    llvm/test/Transforms/LoopDataPrefetch/LoongArch/lit.local.cfg

Modified: 
    llvm/lib/Target/LoongArch/LoongArchTargetMachine.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/LoongArch/LoongArchTargetMachine.cpp b/llvm/lib/Target/LoongArch/LoongArchTargetMachine.cpp
index 933ba3b40ce40..504019c2a09e8 100644
--- a/llvm/lib/Target/LoongArch/LoongArchTargetMachine.cpp
+++ b/llvm/lib/Target/LoongArch/LoongArchTargetMachine.cpp
@@ -19,6 +19,7 @@
 #include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/MC/TargetRegistry.h"
+#include "llvm/Transforms/Scalar.h"
 #include <optional>
 
 using namespace llvm;
@@ -34,6 +35,11 @@ extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeLoongArchTarget() {
   initializeLoongArchDAGToDAGISelPass(*PR);
 }
 
+static cl::opt<bool>
+    EnableLoopDataPrefetch("loongarch-enable-loop-data-prefetch", cl::Hidden,
+                           cl::desc("Enable the loop data prefetch pass"),
+                           cl::init(false));
+
 static std::string computeDataLayout(const Triple &TT) {
   if (TT.isArch64Bit())
     return "e-m:e-p:64:64-i64:64-i128:128-n64-S128";
@@ -126,6 +132,12 @@ LoongArchTargetMachine::createPassConfig(PassManagerBase &PM) {
 }
 
 void LoongArchPassConfig::addIRPasses() {
+  // Run LoopDataPrefetch
+  //
+  // Run this before LSR to remove the multiplies involved in computing the
+  // pointer values N iterations ahead.
+  if (TM->getOptLevel() != CodeGenOpt::None && EnableLoopDataPrefetch)
+    addPass(createLoopDataPrefetchPass());
   addPass(createAtomicExpandPass());
 
   TargetPassConfig::addIRPasses();

diff  --git a/llvm/test/Transforms/LoopDataPrefetch/LoongArch/basic.ll b/llvm/test/Transforms/LoopDataPrefetch/LoongArch/basic.ll
new file mode 100644
index 0000000000000..55a2a2970d2d7
--- /dev/null
+++ b/llvm/test/Transforms/LoopDataPrefetch/LoongArch/basic.ll
@@ -0,0 +1,25 @@
+;; Tag this 'XFAIL' because we need a few more TTIs and ISels.
+; XFAIL: *
+; RUN: opt --mtriple=loongarch64 --passes=loop-data-prefetch -loongarch-enable-loop-data-prefetch -S < %s | FileCheck %s
+
+define void @foo(ptr %a, ptr %b) {
+entry:
+  br label %for.body
+
+; CHECK: for.body:
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds double, ptr %b, i64 %indvars.iv
+; CHECK: call void @llvm.prefetch
+  %0 = load double, ptr %arrayidx, align 8
+  %add = fadd double %0, 1.000000e+00
+  %arrayidx2 = getelementptr inbounds double, ptr %a, i64 %indvars.iv
+  store double %add, ptr %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
+
+; CHECK: for.end:
+for.end:                                          ; preds = %for.body
+  ret void
+}

diff  --git a/llvm/test/Transforms/LoopDataPrefetch/LoongArch/lit.local.cfg b/llvm/test/Transforms/LoopDataPrefetch/LoongArch/lit.local.cfg
new file mode 100644
index 0000000000000..2b5a4893e686f
--- /dev/null
+++ b/llvm/test/Transforms/LoopDataPrefetch/LoongArch/lit.local.cfg
@@ -0,0 +1,2 @@
+if not 'LoongArch' in config.root.targets:
+    config.unsupported = True