[PPC] Give unaligned memory access lower cost on processor that supports it

[Carrot]

Summary

Newer ppc supports unaligned memory access, it reduces the cost of unaligned memory access significantly. This patch handles this case in PPCTTIImpl::getMemoryOpCost.

This patch fixes pr31492.

[Carrot]

ping

[echristo]

LGTM.

Thanks!

-eric

llvm/trunk/lib/Target/PowerPC/PPCTargetTransformInfo.cpp

int PPCTTIImpl::getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
 
   // For VSX, we can do unaligned loads and stores on Altivec/VSX types. On the
   // P7, unaligned vector loads are more expensive than the permutation-based
   // load sequence, so that might be used instead, but regardless, the net cost
   // is about the same (not counting loop-invariant instructions).
   if (IsVSXType || (ST->hasVSX() && IsAltivecType))
     return Cost;
 
+  // Newer PPC supports unaligned memory access.
+  if (TLI->allowsMisalignedMemoryAccesses(LT.second, 0))
+    return Cost;
+
   // PPC in general does not support unaligned loads and stores. They'll need
   // to be decomposed based on the alignment factor.
 
   // Add the cost of each scalar load or store.
   Cost += LT.first*(SrcBytes/Alignment-1);
 
   // For a vector type, there is also scalarization overhead (only for
   // stores, loads are expanded using the vector-load + permutation sequence,

llvm/trunk/test/Analysis/CostModel/PowerPC/load_store.ll

-; RUN: opt < %s  -cost-model -analyze -mtriple=powerpc64-unknown-linux-gnu -mcpu=g5 | FileCheck %s
+; RUN: opt < %s  -cost-model -analyze -mtriple=powerpc64-unknown-linux-gnu -mcpu=g5 -disable-ppc-unaligned | 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-f128:128:128-v128:128:128-n32:64"
 target triple = "powerpc64-unknown-linux-gnu"
 
 define i32 @stores(i32 %arg) {
 
   ; CHECK: cost of 1 {{.*}} store
   store i8 undef, i8* undef, align 4
   ; CHECK: cost of 1 {{.*}} store

llvm/trunk/test/Analysis/CostModel/PowerPC/unaligned_ld_st.ll

+; RUN: opt < %s -cost-model -analyze -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 -mattr=+vsx | 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-f128:128:128-v128:128:128-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+define i32 @test(i32 %arg) {
+
+  ; CHECK: cost of 1 {{.*}} load
+  load i8, i8* undef, align 1
+  ; CHECK: cost of 1 {{.*}} load
+  load i16, i16* undef, align 1
+  ; CHECK: cost of 1 {{.*}} load
+  load i32, i32* undef, align 1
+  ; CHECK: cost of 1 {{.*}} load
+  load i64, i64* undef, align 1
+
+  ; CHECK: cost of 1 {{.*}} store
+  store i8 undef, i8* undef, align 1
+  ; CHECK: cost of 1 {{.*}} store
+  store i16 undef, i16* undef, align 1
+  ; CHECK: cost of 1 {{.*}} store
+  store i32 undef, i32* undef, align 1
+  ; CHECK: cost of 1 {{.*}} store
+  store i64 undef, i64* undef, align 1
+
+  ret i32 undef
+}