[Cost]Add tests for boolean and/or reductions, NFC.

Tests with the default costs for boolean and/or reductions.

Differential Revision: https://reviews.llvm.org/D97793

diff --git a/llvm/test/Analysis/CostModel/AArch64/reduce-and.ll b/llvm/test/Analysis/CostModel/AArch64/reduce-and.ll
new file mode 100644 (file)
index 0000000..2df09c5
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AArch64/reduce-and.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 129 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 364 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 455 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 637 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1001 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.and.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.and.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.and.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.and.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.and.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.and.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.and.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.and.v128i1(<128 x i1>)

diff --git a/llvm/test/Analysis/CostModel/AArch64/reduce-or.ll b/llvm/test/Analysis/CostModel/AArch64/reduce-or.ll
new file mode 100644 (file)
index 0000000..3888495
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AArch64/reduce-or.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 129 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 364 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 455 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 637 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1001 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.or.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.or.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.or.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.or.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.or.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.or.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.or.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.or.v128i1(<128 x i1>)

diff --git a/llvm/test/Analysis/CostModel/AMDGPU/reduce-and.ll b/llvm/test/Analysis/CostModel/AMDGPU/reduce-and.ll
new file mode 100644 (file)
index 0000000..7609deb
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/reduce-and.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=amdgcn-unknown-amdhsa -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.and.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.and.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.and.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.and.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.and.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.and.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.and.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.and.v128i1(<128 x i1>)

diff --git a/llvm/test/Analysis/CostModel/AMDGPU/reduce-or.ll b/llvm/test/Analysis/CostModel/AMDGPU/reduce-or.ll
new file mode 100644 (file)
index 0000000..362efbb
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/reduce-or.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=amdgcn-unknown-amdhsa -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.or.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.or.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.or.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.or.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.or.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.or.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.or.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.or.v128i1(<128 x i1>)

diff --git a/llvm/test/Analysis/CostModel/ARM/reduce-and.ll b/llvm/test/Analysis/CostModel/ARM/reduce-and.ll
new file mode 100644 (file)
index 0000000..26120b8
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/ARM/reduce-and.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=armv8a-linux-gnueabihf -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 150 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 391 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 488 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 682 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1070 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.and.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.and.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.and.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.and.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.and.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.and.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.and.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.and.v128i1(<128 x i1>)

diff --git a/llvm/test/Analysis/CostModel/ARM/reduce-or.ll b/llvm/test/Analysis/CostModel/ARM/reduce-or.ll
new file mode 100644 (file)
index 0000000..2027e6f
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/ARM/reduce-or.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=armv8a-linux-gnueabihf -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 150 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 391 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 488 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 682 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1070 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.or.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.or.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.or.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.or.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.or.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.or.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.or.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.or.v128i1(<128 x i1>)

diff --git a/llvm/test/Analysis/CostModel/PowerPC/reduce-and.ll b/llvm/test/Analysis/CostModel/PowerPC/reduce-and.ll
new file mode 100644 (file)
index 0000000..15f697f
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/PowerPC/reduce-and.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.and.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.and.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.and.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.and.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.and.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.and.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.and.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.and.v128i1(<128 x i1>)

diff --git a/llvm/test/Analysis/CostModel/PowerPC/reduce-or.ll b/llvm/test/Analysis/CostModel/PowerPC/reduce-or.ll
new file mode 100644 (file)
index 0000000..b37396f
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/PowerPC/reduce-or.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.or.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.or.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.or.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.or.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.or.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.or.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.or.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.or.v128i1(<128 x i1>)

diff --git a/llvm/test/Analysis/CostModel/RISCV/reduce-and.ll b/llvm/test/Analysis/CostModel/RISCV/reduce-and.ll
new file mode 100644 (file)
index 0000000..d5aae41
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/RISCV/reduce-and.ll
@@ -0,0 +1,35 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=riscv32 -cost-model -cost-kind=throughput -analyze | FileCheck %s
+; RUN: opt < %s -mtriple=riscv64 -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.and.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.and.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.and.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.and.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.and.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.and.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.and.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.and.v128i1(<128 x i1>)

diff --git a/llvm/test/Analysis/CostModel/RISCV/reduce-or.ll b/llvm/test/Analysis/CostModel/RISCV/reduce-or.ll
new file mode 100644 (file)
index 0000000..3f14f26
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/RISCV/reduce-or.ll
@@ -0,0 +1,35 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=riscv32 -cost-model -cost-kind=throughput -analyze | FileCheck %s
+; RUN: opt < %s -mtriple=riscv64 -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.or.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.or.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.or.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.or.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.or.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.or.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.or.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.or.v128i1(<128 x i1>)

diff --git a/llvm/test/Analysis/CostModel/SystemZ/reduce-and.ll b/llvm/test/Analysis/CostModel/SystemZ/reduce-and.ll
new file mode 100644 (file)
index 0000000..fccd496
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/SystemZ/reduce-and.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=systemz-unknown -mcpu=z13 -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.and.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.and.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.and.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.and.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.and.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.and.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.and.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.and.v128i1(<128 x i1>)

diff --git a/llvm/test/Analysis/CostModel/SystemZ/reduce-or.ll b/llvm/test/Analysis/CostModel/SystemZ/reduce-or.ll
new file mode 100644 (file)
index 0000000..18d0f2b
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/SystemZ/reduce-or.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=systemz-unknown -mcpu=z13 -cost-model -cost-kind=throughput -analyze | FileCheck %s
+
+define i32 @reduce_i1(i32 %arg) {
+; CHECK-LABEL: 'reduce_i1'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+  %V1   = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
+  %V2   = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
+  %V4   = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
+  %V8   = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
+  %V16  = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
+  %V32  = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+  %V64  = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+  %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+  ret i32 undef
+}
+
+declare i1 @llvm.vector.reduce.or.v1i1(<1 x i1>)
+declare i1 @llvm.vector.reduce.or.v2i1(<2 x i1>)
+declare i1 @llvm.vector.reduce.or.v4i1(<4 x i1>)
+declare i1 @llvm.vector.reduce.or.v8i1(<8 x i1>)
+declare i1 @llvm.vector.reduce.or.v16i1(<16 x i1>)
+declare i1 @llvm.vector.reduce.or.v32i1(<32 x i1>)
+declare i1 @llvm.vector.reduce.or.v64i1(<64 x i1>)
+declare i1 @llvm.vector.reduce.or.v128i1(<128 x i1>)