ARM cost model: Address computation in vector mem ops not free

Adds a function to target transform info to query for the cost of address
computation. The cost model analysis pass now also queries this interface.
The code in LoopVectorize adds the cost of address computation as part of the
memory instruction cost calculation. Only there, we know whether the instruction
will be scalarized or not.
Increase the penality for inserting in to D registers on swift. This becomes
necessary because we now always assume that address computation has a cost and
three is a closer value to the architecture.

radar://13097204

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174713 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 86 insertions, 3 deletions

diff --git a/test/Analysis/CostModel/ARM/gep.ll b/test/Analysis/CostModel/ARM/gep.ll
new file mode 100644
index 0000000000..a63b87d2ad
--- /dev/null
+++ b/test/Analysis/CostModel/ARM/gep.ll
@@ -0,0 +1,43 @@
+; RUN: opt -cost-model -analyze -mtriple=thumbv7-apple-ios6.0.0 -mcpu=swift < %s | FileCheck %s
+
+target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
+target triple = "thumbv7-apple-ios6.0.0"
+
+define void @test_geps() {
+  ; Cost of scalar integer geps should be one. We can't always expect it to be
+  ; folded into the instruction addressing mode.
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds i8*
+  %a0 = getelementptr inbounds i8* undef, i32 0
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds i16*
+  %a1 = getelementptr inbounds i16* undef, i32 0
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds i32*
+  %a2 = getelementptr inbounds i32* undef, i32 0
+
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds i64*
+  %a3 = getelementptr inbounds i64* undef, i32 0
+
+  ; Cost of scalar floating point geps should be one. We cannot fold the address
+  ; computation.
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds float*
+  %a4 = getelementptr inbounds float* undef, i32 0
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds double*
+  %a5 = getelementptr inbounds double* undef, i32 0
+
+
+  ; Cost of vector geps should be one. We cannot fold the address computation.
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds <4 x i8>*
+  %a7 = getelementptr inbounds <4 x i8>* undef, i32 0
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds <4 x i16>*
+  %a8 = getelementptr inbounds <4 x i16>* undef, i32 0
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds <4 x i32>*
+  %a9 = getelementptr inbounds <4 x i32>* undef, i32 0
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds <4 x i64>*
+  %a10 = getelementptr inbounds <4 x i64>* undef, i32 0
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds <4 x float>*
+  %a11 = getelementptr inbounds <4 x float>* undef, i32 0
+;CHECK: cost of 1 for instruction: {{.*}} getelementptr inbounds <4 x double>*
+  %a12 = getelementptr inbounds <4 x double>* undef, i32 0
+
+
+  ret void
+}
diff --git a/test/Analysis/CostModel/ARM/insertelement.ll b/test/Analysis/CostModel/ARM/insertelement.ll
index 2d43e4ddd9..f951b08f9b 100644
--- a/test/Analysis/CostModel/ARM/insertelement.ll
+++ b/test/Analysis/CostModel/ARM/insertelement.ll
@@ -12,7 +12,7 @@ define void @insertelement_i8(%T_i8* %saddr,
                            %T_i8v* %vaddr) {
   %v0 = load %T_i8v* %vaddr
   %v1 = load %T_i8* %saddr
-;CHECK: estimated cost of 2 for {{.*}} insertelement <8 x i8>
+;CHECK: estimated cost of 3 for {{.*}} insertelement <8 x i8>
   %v2 = insertelement %T_i8v %v0, %T_i8 %v1, i32 1
   store %T_i8v %v2, %T_i8v* %vaddr
   ret void
@@ -26,7 +26,7 @@ define void @insertelement_i16(%T_i16* %saddr,
                            %T_i16v* %vaddr) {
   %v0 = load %T_i16v* %vaddr
   %v1 = load %T_i16* %saddr
-;CHECK: estimated cost of 2 for {{.*}} insertelement <4 x i16>
+;CHECK: estimated cost of 3 for {{.*}} insertelement <4 x i16>
   %v2 = insertelement %T_i16v %v0, %T_i16 %v1, i32 1
   store %T_i16v %v2, %T_i16v* %vaddr
   ret void
@@ -39,7 +39,7 @@ define void @insertelement_i32(%T_i32* %saddr,
                            %T_i32v* %vaddr) {
   %v0 = load %T_i32v* %vaddr
   %v1 = load %T_i32* %saddr
-;CHECK: estimated cost of 2 for {{.*}} insertelement <2 x i32>
+;CHECK: estimated cost of 3 for {{.*}} insertelement <2 x i32>
   %v2 = insertelement %T_i32v %v0, %T_i32 %v1, i32 1
   store %T_i32v %v2, %T_i32v* %vaddr
   ret void
diff --git a/test/Analysis/CostModel/X86/gep.ll b/test/Analysis/CostModel/X86/gep.ll
new file mode 100644
index 0000000000..877184a3ea
--- /dev/null
+++ b/test/Analysis/CostModel/X86/gep.ll
@@ -0,0 +1,40 @@
+; RUN: opt < %s  -cost-model -analyze -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"
+
+
+define void @test_geps() {
+  ; Cost of should be zero. We expect it to be folded into
+  ; the instruction addressing mode.
+;CHECK:  cost of 0 for instruction: {{.*}} getelementptr inbounds i8*
+  %a0 = getelementptr inbounds i8* undef, i32 0
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds i16*
+  %a1 = getelementptr inbounds i16* undef, i32 0
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds i32*
+  %a2 = getelementptr inbounds i32* undef, i32 0
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds i64*
+  %a3 = getelementptr inbounds i64* undef, i32 0
+
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds float*
+  %a4 = getelementptr inbounds float* undef, i32 0
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds double*
+  %a5 = getelementptr inbounds double* undef, i32 0
+
+ ; Vector geps should also have zero cost.
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds <4 x i8>*
+  %a7 = getelementptr inbounds <4 x i8>* undef, i32 0
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds <4 x i16>*
+  %a8 = getelementptr inbounds <4 x i16>* undef, i32 0
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds <4 x i32>*
+  %a9 = getelementptr inbounds <4 x i32>* undef, i32 0
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds <4 x i64>*
+  %a10 = getelementptr inbounds <4 x i64>* undef, i32 0
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds <4 x float>*
+  %a11 = getelementptr inbounds <4 x float>* undef, i32 0
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds <4 x double>*
+  %a12 = getelementptr inbounds <4 x double>* undef, i32 0
+
+
+  ret void
+}