Update aosp/master LLVM for rebase to r230699.

Change-Id: I2b5be30509658cb8266be782de0ab24f9099f9b9

3 files changed, 106 insertions, 18 deletions

diff --git a/test/Analysis/CostModel/X86/masked-intrinsic-cost.ll b/test/Analysis/CostModel/X86/masked-intrinsic-cost.ll
new file mode 100644
index 0000000..4683c43
--- /dev/null
+++ b/test/Analysis/CostModel/X86/masked-intrinsic-cost.ll
@@ -0,0 +1,89 @@
+; RUN: opt -S -mtriple=x86_64-apple-darwin -mcpu=core-avx2 -cost-model -analyze < %s | FileCheck %s -check-prefix=AVX2
+
+
+; AVX2-LABEL: test1
+; AVX2: Found an estimated cost of 4 {{.*}}.masked
+define <2 x double> @test1(<2 x i64> %trigger, <2 x double>* %addr, <2 x double> %dst) {
+  %mask = icmp eq <2 x i64> %trigger, zeroinitializer
+  %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %addr, i32 4, <2 x i1>%mask, <2 x double>%dst)
+  ret <2 x double> %res
+}
+
+; AVX2-LABEL: test2
+; AVX2: Found an estimated cost of 4 {{.*}}.masked
+define <4 x i32> @test2(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %dst) {
+  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+  %res = call <4 x i32> @llvm.masked.load.v4i32(<4 x i32>* %addr, i32 4, <4 x i1>%mask, <4 x i32>%dst)
+  ret <4 x i32> %res
+}
+
+; AVX2-LABEL: test3
+; AVX2: Found an estimated cost of 4 {{.*}}.masked
+define void @test3(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
+  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+  call void @llvm.masked.store.v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1>%mask)
+  ret void
+}
+
+; AVX2-LABEL: test4
+; AVX2: Found an estimated cost of 4 {{.*}}.masked
+define <8 x float> @test4(<8 x i32> %trigger, <8 x float>* %addr, <8 x float> %dst) {
+  %mask = icmp eq <8 x i32> %trigger, zeroinitializer
+  %res = call <8 x float> @llvm.masked.load.v8f32(<8 x float>* %addr, i32 4, <8 x i1>%mask, <8 x float>%dst)
+  ret <8 x float> %res
+}
+
+; AVX2-LABEL: test5
+; AVX2: Found an estimated cost of 5 {{.*}}.masked
+define void @test5(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %val) {
+  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+  call void @llvm.masked.store.v2f32(<2 x float>%val, <2 x float>* %addr, i32 4, <2 x i1>%mask)
+  ret void
+}
+
+; AVX2-LABEL: test6
+; AVX2: Found an estimated cost of 6 {{.*}}.masked
+define void @test6(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %val) {
+  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+  call void @llvm.masked.store.v2i32(<2 x i32>%val, <2 x i32>* %addr, i32 4, <2 x i1>%mask)
+  ret void
+}
+
+; AVX2-LABEL: test7
+; AVX2: Found an estimated cost of 5 {{.*}}.masked
+define <2 x float> @test7(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %dst) {
+  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+  %res = call <2 x float> @llvm.masked.load.v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>%dst)
+  ret <2 x float> %res
+}
+
+; AVX2-LABEL: test8
+; AVX2: Found an estimated cost of 6 {{.*}}.masked
+define <2 x i32> @test8(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %dst) {
+  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+  %res = call <2 x i32> @llvm.masked.load.v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
+  ret <2 x i32> %res
+}
+
+
+declare <16 x i32> @llvm.masked.load.v16i32(<16 x i32>*, i32, <16 x i1>, <16 x i32>)
+declare <4 x i32> @llvm.masked.load.v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
+declare <2 x i32> @llvm.masked.load.v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
+declare void @llvm.masked.store.v16i32(<16 x i32>, <16 x i32>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
+declare void @llvm.masked.store.v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v2i32(<2 x i32>, <2 x i32>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v16f32(<16 x float>, <16 x float>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v16f32p(<16 x float>*, <16 x float>**, i32, <16 x i1>)
+declare <16 x float> @llvm.masked.load.v16f32(<16 x float>*, i32, <16 x i1>, <16 x float>)
+declare <8 x float> @llvm.masked.load.v8f32(<8 x float>*, i32, <8 x i1>, <8 x float>)
+declare <4 x float> @llvm.masked.load.v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>)
+declare <2 x float> @llvm.masked.load.v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>)
+declare <8 x double> @llvm.masked.load.v8f64(<8 x double>*, i32, <8 x i1>, <8 x double>)
+declare <4 x double> @llvm.masked.load.v4f64(<4 x double>*, i32, <4 x i1>, <4 x double>)
+declare <2 x double> @llvm.masked.load.v2f64(<2 x double>*, i32, <2 x i1>, <2 x double>)
+declare void @llvm.masked.store.v8f64(<8 x double>, <8 x double>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v2f64(<2 x double>, <2 x double>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v2i64(<2 x i64>, <2 x i64>*, i32, <2 x i1>)
+
diff --git a/test/Analysis/CostModel/X86/vselect-cost.ll b/test/Analysis/CostModel/X86/vselect-cost.ll
index 2416777..b7e56ef 100644
--- a/test/Analysis/CostModel/X86/vselect-cost.ll
+++ b/test/Analysis/CostModel/X86/vselect-cost.ll
@@ -11,7 +11,7 @@
 
 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>
+; SSE2: Cost Model: {{.*}} 1 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>
@@ -21,7 +21,7 @@ define <2 x i64> @test_2i64(<2 x i64> %a, <2 x i64> %b) {
 
 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>
+; SSE2: Cost Model: {{.*}} 1 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>
@@ -31,7 +31,7 @@ define <2 x double> @test_2double(<2 x double> %a, <2 x double> %b) {
 
 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>
+; SSE2: Cost Model: {{.*}} 1 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>
@@ -41,7 +41,7 @@ define <4 x i32> @test_4i32(<4 x i32> %a, <4 x i32> %b) {
 
 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>
+; SSE2: Cost Model: {{.*}} 1 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>
@@ -51,7 +51,7 @@ define <4 x float> @test_4float(<4 x float> %a, <4 x float> %b) {
 
 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>
+; SSE2: Cost Model: {{.*}} 1 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>
@@ -63,7 +63,7 @@ define <16 x i8> @test_16i8(<16 x i8> %a, <16 x i8> %b) {
 ; <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>
+; SSE2: Cost Model: {{.*}} 2 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>
@@ -73,7 +73,7 @@ define <4 x i64> @test_4i64(<4 x i64> %a, <4 x i64> %b) {
 
 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>
+; SSE2: Cost Model: {{.*}} 2 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>
@@ -83,7 +83,7 @@ define <4 x double> @test_4double(<4 x double> %a, <4 x double> %b) {
 
 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>
+; SSE2: Cost Model: {{.*}} 2 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>
@@ -93,7 +93,7 @@ define <8 x i32> @test_8i32(<8 x i32> %a, <8 x i32> %b) {
 
 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>
+; SSE2: Cost Model: {{.*}} 2 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>
@@ -104,10 +104,9 @@ define <8 x float> @test_8float(<8 x float> %a, <8 x float> %b) {
 ; 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>
+; SSE2: Cost Model: {{.*}} 2 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>
+; 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 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
@@ -115,10 +114,9 @@ define <16 x i16> @test_16i16(<16 x i16> %a, <16 x i16> %b) {
 
 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>
+; SSE2: Cost Model: {{.*}} 2 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>
+; AVX: Cost Model: {{.*}} 1 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
diff --git a/test/Analysis/CostModel/no_info.ll b/test/Analysis/CostModel/no_info.ll
index f3f165b..5f3b56a 100644
--- a/test/Analysis/CostModel/no_info.ll
+++ b/test/Analysis/CostModel/no_info.ll
@@ -1,11 +1,12 @@
 ; RUN: opt < %s -cost-model -analyze | FileCheck %s
 
-; The cost model does not have any target information so it can't make a decision.
+; The cost model does not have any target information so it just makes boring
+; assumptions.
 
 ; -- No triple in this module --
 
-;CHECK: Unknown cost {{.*}} add
-;CHECK: Unknown cost {{.*}} ret
+;CHECK: cost of 1 {{.*}} add
+;CHECK: cost of 1 {{.*}} ret
 define i32 @no_info(i32 %arg) {
   %e = add i32 %arg, %arg
   ret i32 %e