Update LLVM for 3.5 rebase (r209712).

Change-Id: I149556c940fb7dc92d075273c87ff584f400941f

9 files changed, 257 insertions, 5 deletions

diff --git a/test/Analysis/CostModel/ARM64/lit.local.cfg b/test/Analysis/CostModel/AArch64/lit.local.cfg
index 84ac981..c420349 100644
--- a/test/Analysis/CostModel/ARM64/lit.local.cfg
+++ b/test/Analysis/CostModel/AArch64/lit.local.cfg
@@ -1,3 +1,3 @@
 targets = set(config.root.targets_to_build.split())
-if not 'ARM64' in targets:
+if not 'AArch64' in targets:
     config.unsupported = True
diff --git a/test/Analysis/CostModel/ARM64/select.ll b/test/Analysis/CostModel/AArch64/select.ll
index 216dc5d..216dc5d 100644
--- a/test/Analysis/CostModel/ARM64/select.ll
+++ b/test/Analysis/CostModel/AArch64/select.ll
diff --git a/test/Analysis/CostModel/ARM64/store.ll b/test/Analysis/CostModel/AArch64/store.ll
index 0c9883c..0c9883c 100644
--- a/test/Analysis/CostModel/ARM64/store.ll
+++ b/test/Analysis/CostModel/AArch64/store.ll
diff --git a/test/Analysis/CostModel/PowerPC/ext.ll b/test/Analysis/CostModel/PowerPC/ext.ll
index daaa8f5..7d6a14e 100644
--- a/test/Analysis/CostModel/PowerPC/ext.ll
+++ b/test/Analysis/CostModel/PowerPC/ext.ll
@@ -13,7 +13,7 @@ define void @exts() {
   ; CHECK: cost of 1 {{.*}} sext
   %v3 = sext <4 x i16> undef to <4 x i32>
 
-  ; CHECK: cost of 216 {{.*}} sext
+  ; CHECK: cost of 112 {{.*}} sext
   %v4 = sext <8 x i16> undef to <8 x i32>
 
   ret void
diff --git a/test/Analysis/CostModel/PowerPC/insert_extract.ll b/test/Analysis/CostModel/PowerPC/insert_extract.ll
index f51963d..8dc0031 100644
--- a/test/Analysis/CostModel/PowerPC/insert_extract.ll
+++ b/test/Analysis/CostModel/PowerPC/insert_extract.ll
@@ -3,13 +3,13 @@ target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3
 target triple = "powerpc64-unknown-linux-gnu"
 
 define i32 @insert(i32 %arg) {
-  ; CHECK: cost of 13 {{.*}} insertelement
+  ; CHECK: cost of 10 {{.*}} insertelement
   %x = insertelement <4 x i32> undef, i32 %arg, i32 0
   ret i32 undef
 }
 
 define i32 @extract(<4 x i32> %arg) {
-  ; CHECK: cost of 13 {{.*}} extractelement
+  ; CHECK: cost of 3 {{.*}} extractelement
   %x = extractelement <4 x i32> %arg, i32 0
   ret i32 %x
 }
diff --git a/test/Analysis/CostModel/PowerPC/load_store.ll b/test/Analysis/CostModel/PowerPC/load_store.ll
index 8145a1d..368f0a7 100644
--- a/test/Analysis/CostModel/PowerPC/load_store.ll
+++ b/test/Analysis/CostModel/PowerPC/load_store.ll
@@ -31,9 +31,15 @@ define i32 @loads(i32 %arg) {
 
   ; FIXME: There actually are sub-vector Altivec loads, and so we could handle
   ; this with a small expense, but we don't currently.
-  ; CHECK: cost of 60 {{.*}} load
+  ; CHECK: cost of 48 {{.*}} load
   load <4 x i16>* undef, align 2
 
+  ; CHECK: cost of 1 {{.*}} load
+  load <4 x i32>* undef, align 4
+
+  ; CHECK: cost of 46 {{.*}} load
+  load <3 x float>* undef, align 1
+
   ret i32 undef
 }
 
diff --git a/test/Analysis/CostModel/X86/intrinsic-cost.ll b/test/Analysis/CostModel/X86/intrinsic-cost.ll
index 8eeee81..3b27b52 100644
--- a/test/Analysis/CostModel/X86/intrinsic-cost.ll
+++ b/test/Analysis/CostModel/X86/intrinsic-cost.ll
@@ -58,3 +58,31 @@ for.end:                                          ; preds = %vector.body
 }
 
 declare <4 x float> @llvm.nearbyint.v4f32(<4 x float>)  nounwind readnone
+
+define void @test3(float* nocapture %f, <4 x float> %b, <4 x float> %c) nounwind {
+vector.ph:
+  br label %vector.body
+
+vector.body:                                      ; preds = %vector.body, %vector.ph
+  %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+  %0 = getelementptr inbounds float* %f, i64 %index
+  %1 = bitcast float* %0 to <4 x float>*
+  %wide.load = load <4 x float>* %1, align 4
+  %2 = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> %wide.load, <4 x float> %b, <4 x float> %c)
+  store <4 x float> %2, <4 x float>* %1, align 4
+  %index.next = add i64 %index, 4
+  %3 = icmp eq i64 %index.next, 1024
+  br i1 %3, label %for.end, label %vector.body
+
+for.end:                                          ; preds = %vector.body
+  ret void
+
+; CORE2: Printing analysis 'Cost Model Analysis' for function 'test3':
+; CORE2: Cost Model: Found an estimated cost of 4 for instruction: %2 = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> %wide.load, <4 x float> %b, <4 x float> %c)
+
+; COREI7: Printing analysis 'Cost Model Analysis' for function 'test3':
+; COREI7: Cost Model: Found an estimated cost of 4 for instruction: %2 = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> %wide.load, <4 x float> %b, <4 x float> %c)
+
+}
+
+declare <4 x float> @llvm.fmuladd.v4f32(<4 x float>, <4 x float>, <4 x float>) nounwind readnone
diff --git a/test/Analysis/CostModel/X86/vdiv-cost.ll b/test/Analysis/CostModel/X86/vdiv-cost.ll
new file mode 100644
index 0000000..c8e4557
--- /dev/null
+++ b/test/Analysis/CostModel/X86/vdiv-cost.ll
@@ -0,0 +1,92 @@
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -mattr=+sse2,-sse4.1 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=SSE2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=core-avx2 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=AVX2
+
+define <4 x i32> @test1(<4 x i32> %a) {
+  %div = udiv <4 x i32> %a, <i32 7, i32 7, i32 7, i32 7>
+  ret <4 x i32> %div
+
+; CHECK: 'Cost Model Analysis' for function 'test1':
+; SSE2: Found an estimated cost of 15 for instruction:   %div
+; AVX2: Found an estimated cost of 15 for instruction:   %div
+}
+
+define <8 x i32> @test2(<8 x i32> %a) {
+  %div = udiv <8 x i32> %a, <i32 7, i32 7, i32 7, i32 7,i32 7, i32 7, i32 7, i32 7>
+  ret <8 x i32> %div
+
+; CHECK: 'Cost Model Analysis' for function 'test2':
+; SSE2: Found an estimated cost of 30 for instruction:   %div
+; AVX2: Found an estimated cost of 15 for instruction:   %div
+}
+
+define <8 x i16> @test3(<8 x i16> %a) {
+  %div = udiv <8 x i16> %a, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+  ret <8 x i16> %div
+
+; CHECK: 'Cost Model Analysis' for function 'test3':
+; SSE2: Found an estimated cost of 6 for instruction:   %div
+; AVX2: Found an estimated cost of 6 for instruction:   %div
+}
+
+define <16 x i16> @test4(<16 x i16> %a) {
+  %div = udiv <16 x i16> %a, <i16 7, i16 7, i16 7, i16 7,i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7,i16 7, i16 7, i16 7, i16 7>
+  ret <16 x i16> %div
+
+; CHECK: 'Cost Model Analysis' for function 'test4':
+; SSE2: Found an estimated cost of 12 for instruction:   %div
+; AVX2: Found an estimated cost of 6 for instruction:   %div
+}
+
+define <8 x i16> @test5(<8 x i16> %a) {
+  %div = sdiv <8 x i16> %a, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+  ret <8 x i16> %div
+
+; CHECK: 'Cost Model Analysis' for function 'test5':
+; SSE2: Found an estimated cost of 6 for instruction:   %div
+; AVX2: Found an estimated cost of 6 for instruction:   %div
+}
+
+define <16 x i16> @test6(<16 x i16> %a) {
+  %div = sdiv <16 x i16> %a, <i16 7, i16 7, i16 7, i16 7,i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7,i16 7, i16 7, i16 7, i16 7>
+  ret <16 x i16> %div
+
+; CHECK: 'Cost Model Analysis' for function 'test6':
+; SSE2: Found an estimated cost of 12 for instruction:   %div
+; AVX2: Found an estimated cost of 6 for instruction:   %div
+}
+
+define <16 x i8> @test7(<16 x i8> %a) {
+  %div = sdiv <16 x i8> %a, <i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7>
+  ret <16 x i8> %div
+
+; CHECK: 'Cost Model Analysis' for function 'test7':
+; SSE2: Found an estimated cost of 320 for instruction:   %div
+; AVX2: Found an estimated cost of 320 for instruction:   %div
+}
+
+define <4 x i32> @test8(<4 x i32> %a) {
+  %div = sdiv <4 x i32> %a, <i32 7, i32 7, i32 7, i32 7>
+  ret <4 x i32> %div
+
+; CHECK: 'Cost Model Analysis' for function 'test8':
+; SSE2: Found an estimated cost of 19 for instruction:   %div
+; AVX2: Found an estimated cost of 15 for instruction:   %div
+}
+
+define <8 x i32> @test9(<8 x i32> %a) {
+  %div = sdiv <8 x i32> %a, <i32 7, i32 7, i32 7, i32 7,i32 7, i32 7, i32 7, i32 7>
+  ret <8 x i32> %div
+
+; CHECK: 'Cost Model Analysis' for function 'test9':
+; SSE2: Found an estimated cost of 38 for instruction:   %div
+; AVX2: Found an estimated cost of 15 for instruction:   %div
+}
+
+define <8 x i32> @test10(<8 x i32> %a) {
+  %div = sdiv <8 x i32> %a, <i32 8, i32 7, i32 7, i32 7,i32 7, i32 7, i32 7, i32 7>
+  ret <8 x i32> %div
+
+; CHECK: 'Cost Model Analysis' for function 'test10':
+; SSE2: Found an estimated cost of 160 for instruction:   %div
+; AVX2: Found an estimated cost of 160 for instruction:   %div
+}
diff --git a/test/Analysis/CostModel/X86/vselect-cost.ll b/test/Analysis/CostModel/X86/vselect-cost.ll
new file mode 100644
index 0000000..2416777
--- /dev/null
+++ b/test/Analysis/CostModel/X86/vselect-cost.ll
@@ -0,0 +1,126 @@
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -mattr=+sse2,-sse4.1 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=SSE2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=SSE41
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7-avx -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=AVX
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=core-avx2 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=AVX2
+
+
+; Verify the cost of vector select instructions.
+
+; SSE41 added blend instructions with an immediate for <2 x double> and
+; <4 x float>. Integers of the same size should also use those instructions.
+
+define <2 x i64> @test_2i64(<2 x i64> %a, <2 x i64> %b) {
+; CHECK: Printing analysis 'Cost Model Analysis' for function 'test_2i64':
+; SSE2: Cost Model: {{.*}} 4 for instruction:   %sel = select <2 x i1>
+; SSE41: Cost Model: {{.*}} 1 for instruction:   %sel = select <2 x i1>
+; AVX: Cost Model: {{.*}} 1 for instruction:   %sel = select <2 x i1>
+; AVX2: Cost Model: {{.*}} 1 for instruction:   %sel = select <2 x i1>
+  %sel = select <2 x i1> <i1 true, i1 false>, <2 x i64> %a, <2 x i64> %b
+  ret <2 x i64> %sel
+}
+
+define <2 x double> @test_2double(<2 x double> %a, <2 x double> %b) {
+; CHECK: Printing analysis 'Cost Model Analysis' for function 'test_2double':
+; SSE2: Cost Model: {{.*}} 3 for instruction:   %sel = select <2 x i1>
+; SSE41: Cost Model: {{.*}} 1 for instruction:   %sel = select <2 x i1>
+; AVX: Cost Model: {{.*}} 1 for instruction:   %sel = select <2 x i1>
+; AVX2: Cost Model: {{.*}} 1 for instruction:   %sel = select <2 x i1>
+  %sel = select <2 x i1> <i1 true, i1 false>, <2 x double> %a, <2 x double> %b
+  ret <2 x double> %sel
+}
+
+define <4 x i32> @test_4i32(<4 x i32> %a, <4 x i32> %b) {
+; CHECK: Printing analysis 'Cost Model Analysis' for function 'test_4i32':
+; SSE2: Cost Model: {{.*}} 8 for instruction:   %sel = select <4 x i1>
+; SSE41: Cost Model: {{.*}} 1 for instruction:   %sel = select <4 x i1>
+; AVX: Cost Model: {{.*}} 1 for instruction:   %sel = select <4 x i1>
+; AVX2: Cost Model: {{.*}} 1 for instruction:   %sel = select <4 x i1>
+  %sel = select <4 x i1> <i1 true, i1 false, i1 true, i1 false>, <4 x i32> %a, <4 x i32> %b
+  ret <4 x i32> %sel
+}
+
+define <4 x float> @test_4float(<4 x float> %a, <4 x float> %b) {
+; CHECK: Printing analysis 'Cost Model Analysis' for function 'test_4float':
+; SSE2: Cost Model: {{.*}} 7 for instruction:   %sel = select <4 x i1>
+; SSE41: Cost Model: {{.*}} 1 for instruction:   %sel = select <4 x i1>
+; AVX: Cost Model: {{.*}} 1 for instruction:   %sel = select <4 x i1>
+; AVX2: Cost Model: {{.*}} 1 for instruction:   %sel = select <4 x i1>
+  %sel = select <4 x i1> <i1 true, i1 false, i1 true, i1 true>, <4 x float> %a, <4 x float> %b
+  ret <4 x float> %sel
+}
+
+define <16 x i8> @test_16i8(<16 x i8> %a, <16 x i8> %b) {
+; CHECK: Printing analysis 'Cost Model Analysis' for function 'test_16i8':
+; SSE2: Cost Model: {{.*}} 32 for instruction:   %sel = select <16 x i1>
+; SSE41: Cost Model: {{.*}} 1 for instruction:   %sel = select <16 x i1>
+; AVX: Cost Model: {{.*}} 1 for instruction:   %sel = select <16 x i1>
+; AVX2: Cost Model: {{.*}} 1 for instruction:   %sel = select <16 x i1>
+  %sel = select <16 x i1> <i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true>, <16 x i8> %a, <16 x i8> %b
+  ret <16 x i8> %sel
+}
+
+; AVX added blend instructions with an immediate for <4 x double> and
+; <8 x float>. Integers of the same size should also use those instructions.
+define <4 x i64> @test_4i64(<4 x i64> %a, <4 x i64> %b) {
+; CHECK: Printing analysis 'Cost Model Analysis' for function 'test_4i64':
+; SSE2: Cost Model: {{.*}} 8 for instruction:   %sel = select <4 x i1>
+; SSE41: Cost Model: {{.*}} 2 for instruction:   %sel = select <4 x i1>
+; AVX: Cost Model: {{.*}} 1 for instruction:   %sel = select <4 x i1>
+; AVX2: Cost Model: {{.*}} 1 for instruction:   %sel = select <4 x i1>
+  %sel = select <4 x i1> <i1 true, i1 false, i1 false, i1 true>, <4 x i64> %a, <4 x i64> %b
+  ret <4 x i64> %sel
+}
+
+define <4 x double> @test_4double(<4 x double> %a, <4 x double> %b) {
+; CHECK: Printing analysis 'Cost Model Analysis' for function 'test_4double':
+; SSE2: Cost Model: {{.*}} 6 for instruction:   %sel = select <4 x i1>
+; SSE41: Cost Model: {{.*}} 2 for instruction:   %sel = select <4 x i1>
+; AVX: Cost Model: {{.*}} 1 for instruction:   %sel = select <4 x i1>
+; AVX2: Cost Model: {{.*}} 1 for instruction:   %sel = select <4 x i1>
+  %sel = select <4 x i1> <i1 true, i1 false, i1 true, i1 false>, <4 x double> %a, <4 x double> %b
+  ret <4 x double> %sel
+}
+
+define <8 x i32> @test_8i32(<8 x i32> %a, <8 x i32> %b) {
+; CHECK: Printing analysis 'Cost Model Analysis' for function 'test_8i32':
+; SSE2: Cost Model: {{.*}} 16 for instruction:   %sel = select <8 x i1>
+; SSE41: Cost Model: {{.*}} 2 for instruction:   %sel = select <8 x i1>
+; AVX: Cost Model: {{.*}} 1 for instruction:   %sel = select <8 x i1>
+; AVX2: Cost Model: {{.*}} 1 for instruction:   %sel = select <8 x i1>
+  %sel = select <8 x i1> <i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 true, i1 false>, <8 x i32> %a, <8 x i32> %b
+  ret <8 x i32> %sel
+}
+
+define <8 x float> @test_8float(<8 x float> %a, <8 x float> %b) {
+; CHECK: Printing analysis 'Cost Model Analysis' for function 'test_8float':
+; SSE2: Cost Model: {{.*}} 14 for instruction:   %sel = select <8 x i1>
+; SSE41: Cost Model: {{.*}} 2 for instruction:   %sel = select <8 x i1>
+; AVX: Cost Model: {{.*}} 1 for instruction:   %sel = select <8 x i1>
+; AVX2: Cost Model: {{.*}} 1 for instruction:   %sel = select <8 x i1>
+  %sel = select <8 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <8 x float> %a, <8 x float> %b
+  ret <8 x float> %sel
+}
+
+; AVX2
+define <16 x i16> @test_16i16(<16 x i16> %a, <16 x i16> %b) {
+; CHECK:Printing analysis 'Cost Model Analysis' for function 'test_16i16':
+; SSE2: Cost Model: {{.*}} 32 for instruction:   %sel = select <16 x i1>
+; SSE41: Cost Model: {{.*}} 2 for instruction:   %sel = select <16 x i1>
+;;; FIXME: This AVX cost is obviously wrong. We shouldn't be scalarizing.
+; AVX: Cost Model: {{.*}} 32 for instruction:   %sel = select <16 x i1>
+; AVX2: Cost Model: {{.*}} 1 for instruction:   %sel = select <16 x i1>
+  %sel = select <16 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <16 x i16> %a, <16 x i16> %b
+  ret <16 x i16> %sel
+}
+
+define <32 x i8> @test_32i8(<32 x i8> %a, <32 x i8> %b) {
+; CHECK: Printing analysis 'Cost Model Analysis' for function 'test_32i8':
+; SSE2: Cost Model: {{.*}} 64 for instruction:   %sel = select <32 x i1>
+; SSE41: Cost Model: {{.*}} 2 for instruction:   %sel = select <32 x i1>
+;;; FIXME: This AVX cost is obviously wrong. We shouldn't be scalarizing.
+; AVX: Cost Model: {{.*}} 64 for instruction:   %sel = select <32 x i1>
+; AVX2: Cost Model: {{.*}} 1 for instruction:   %sel = select <32 x i1>
+  %sel = select <32 x i1> <i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true>, <32 x i8> %a, <32 x i8> %b
+  ret <32 x i8> %sel
+}
+