[ARM][ParallelDSP] Disable for big-endian

Bail early when we don't have a preheader and also if the target is
big endian because it's written with only little endian in mind!

Differential Revision: https://reviews.llvm.org/D59368

llvm-svn: 356243

Author: sparker-arm

llvm/lib/Target/ARM/ARMParallelDSP.cpp

@@ -201,6 +201,12 @@ namespace {
         return false;
       }
 
+      // We need a preheader as getIncomingValueForBlock assumes there is one.
+      if (!TheLoop->getLoopPreheader()) {
+        LLVM_DEBUG(dbgs() << "No preheader found, bailing out\n");
+        return false;
+      }
+
       Function &F = *Header->getParent();
       M = F.getParent();
       DL = &M->getDataLayout();
@@ -220,6 +226,12 @@ namespace {
         return false;
       }
 
+      if (!ST->isLittle()) {
+        LLVM_DEBUG(dbgs() << "Only supporting little endian: not running pass "
+                             "ARMParallelDSP\n");
+        return false;
+      }
+
       LoopAccessInfo LAI(L, SE, TLI, AA, DT, LI);
 
       LLVM_DEBUG(dbgs() << "\n== Parallel DSP pass ==\n");
@@ -454,12 +466,6 @@ static void MatchReductions(Function &F, Loop *TheLoop, BasicBlock *Header,
     F.getFnAttribute("no-nans-fp-math").getValueAsString() == "true";
   const BasicBlock *Latch = TheLoop->getLoopLatch();
 
-  // We need a preheader as getIncomingValueForBlock assumes there is one.
-  if (!TheLoop->getLoopPreheader()) {
-    LLVM_DEBUG(dbgs() << "No preheader found, bailing out\n");
-    return;
-  }
-
   for (PHINode &Phi : Header->phis()) {
     const auto *Ty = Phi.getType();
     if (!Ty->isIntegerTy(32) && !Ty->isIntegerTy(64))

llvm/test/CodeGen/ARM/ParallelDSP/multi-use-loads.ll

@@ -1,4 +1,7 @@
 ; RUN: llc -O3 -mtriple=arm-arm-eabi -mcpu=cortex-m33 < %s | FileCheck %s
+; RUN: llc -O3 -mtriple=armeb-arm-eabi -mcpu=cortex-m33 < %s | FileCheck %s --check-prefix=CHECK-UNSUPPORTED
+
+; CHECK-UNSUPPORTED-NOT: smlad
 
 ; CHECK-LABEL: add_user
 ; CHECK: %for.body

llvm/test/CodeGen/ARM/ParallelDSP/smlad0.ll

@@ -1,4 +1,5 @@
 ; RUN: opt -mtriple=arm-arm-eabi -mcpu=cortex-m33 < %s -arm-parallel-dsp -S | FileCheck %s
+; RUN: opt -mtriple=armeb-arm-eabi -mcpu=cortex-m0 < %s -arm-parallel-dsp -S | FileCheck %s --check-prefix=CHECK-UNSUPPORTED
 ;
 ; The Cortex-M0 does not support unaligned accesses:
 ; RUN: opt -mtriple=arm-arm-eabi -mcpu=cortex-m0 < %s -arm-parallel-dsp -S | FileCheck %s --check-prefix=CHECK-UNSUPPORTED

llvm/test/CodeGen/ARM/ParallelDSP/smladx-1.ll

@@ -1,6 +1,7 @@
 ; RUN: opt -mtriple=thumbv8m.main -mcpu=cortex-m33 -arm-parallel-dsp %s -S -o - | FileCheck %s
 ; RUN: opt -mtriple=arm-arm-eabi -mcpu=cortex-m0 < %s -arm-parallel-dsp -S | FileCheck %s --check-prefix=CHECK-UNSUPPORTED
 ; RUN: opt -mtriple=arm-arm-eabi -mcpu=cortex-m33 -mattr=-dsp < %s -arm-parallel-dsp -S | FileCheck %s --check-prefix=CHECK-UNSUPPORTED
+; RUN: opt -mtriple=armeb-arm-eabi -mcpu=cortex-m33 < %s -arm-parallel-dsp -S | FileCheck %s --check-prefix=CHECK-UNSUPPORTED
 
 define i32 @smladx(i16* nocapture readonly %pIn1, i16* nocapture readonly %pIn2, i32 %j, i32 %limit) {
 

llvm/test/CodeGen/ARM/ParallelDSP/smlald0.ll

@@ -1,4 +1,5 @@
 ; RUN: opt -mtriple=arm-arm-eabi -mcpu=cortex-m33 < %s -arm-parallel-dsp -S | FileCheck %s
+; RUN: opt -mtriple=armeb-arm-eabi -mcpu=cortex-m33 < %s -arm-parallel-dsp -S | FileCheck %s --check-prefix=CHECK-UNSUPPORTED
 ;
 ; The Cortex-M0 does not support unaligned accesses:
 ; RUN: opt -mtriple=arm-arm-eabi -mcpu=cortex-m0 < %s -arm-parallel-dsp -S | FileCheck %s --check-prefix=CHECK-UNSUPPORTED

llvm/test/CodeGen/ARM/ParallelDSP/unroll-n-jam-smlad.ll

@@ -1,9 +1,14 @@
 ; RUN: llc -O3 -mtriple=thumbv7em %s -o - | FileCheck %s
+; RUN: llc -O3 -mtriple=thumbv7eb %s -o - | FileCheck %s --check-prefix=CHECK-UNSUPPORTED
 ; RUN: llc -O3 -mtriple=thumbv8m.main -mattr=+dsp %s -o - | FileCheck %s
 
+; CHECK-UNSUPPORTED-LABEL: unroll_n_jam_smlad
+; CHECK-UNSUPPORTED-NOT: smlad r{{.}}
+
 ; Test that the duplicate loads are removed, which allows parallel dsp to find
 ; the parallel operations.
 
+; CHECK-LABEL: unroll_n_jam_smlad
 define void @unroll_n_jam_smlad(i32* %res, i16* %A, i16* %B, i32 %N, i32 %idx) {
 entry:
   %xtraiter306.i = and i32 %N, 3