[llvm] 43017ce - [PhaseOrdering] add vector reduction tests; NFC

[Sanjay Patel via llvm-commits]

Author: Sanjay Patel
Date: 2020-05-16T12:51:10-04:00
New Revision: 43017ceb7841c7a0700e5401e79c2f1a28caec5e

URL: https://github.com/llvm/llvm-project/commit/43017ceb7841c7a0700e5401e79c2f1a28caec5e
DIFF: https://github.com/llvm/llvm-project/commit/43017ceb7841c7a0700e5401e79c2f1a28caec5e.diff

LOG: [PhaseOrdering] add vector reduction tests; NFC

These are based on tests originally included in:
D79078

Added: 
    llvm/test/Transforms/PhaseOrdering/X86/vector-reductions.ll

Modified: 
    

Removed: 
    


################################################################################
diff  --git a/llvm/test/Transforms/PhaseOrdering/X86/vector-reductions.ll b/llvm/test/Transforms/PhaseOrdering/X86/vector-reductions.ll
new file mode 100644
index 000000000000..f2e374cb087e
--- /dev/null
+++ b/llvm/test/Transforms/PhaseOrdering/X86/vector-reductions.ll
@@ -0,0 +1,67 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -O2                   -S -mattr=avx < %s | FileCheck %s
+; RUN: opt -passes='default<O2>' -S -mattr=avx < %s | FileCheck %s
+
+target triple = "x86_64--"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+
+define i32 @ext_ext_or_reduction_v4i32(<4 x i32> %x, <4 x i32> %y) {
+; CHECK-LABEL: @ext_ext_or_reduction_v4i32(
+; CHECK-NEXT:    [[Z:%.*]] = and <4 x i32> [[Y:%.*]], [[X:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i32> [[Z]], <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP2:%.*]] = or <4 x i32> [[Z]], [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i32> [[TMP2]], i32 0
+; CHECK-NEXT:    [[Z2:%.*]] = extractelement <4 x i32> [[Z]], i32 2
+; CHECK-NEXT:    [[Z012:%.*]] = or i32 [[TMP3]], [[Z2]]
+; CHECK-NEXT:    [[Z3:%.*]] = extractelement <4 x i32> [[Z]], i32 3
+; CHECK-NEXT:    [[Z0123:%.*]] = or i32 [[Z012]], [[Z3]]
+; CHECK-NEXT:    ret i32 [[Z0123]]
+;
+  %z = and <4 x i32> %x, %y
+  %z0 = extractelement <4 x i32> %z, i32 0
+  %z1 = extractelement <4 x i32> %z, i32 1
+  %z01 = or i32 %z0, %z1
+  %z2 = extractelement <4 x i32> %z, i32 2
+  %z012 = or i32 %z01, %z2
+  %z3 = extractelement <4 x i32> %z, i32 3
+  %z0123 = or i32 %z3, %z012
+  ret i32 %z0123
+}
+
+define i32 @ext_ext_partial_add_reduction_v4i32(<4 x i32> %x) {
+; CHECK-LABEL: @ext_ext_partial_add_reduction_v4i32(
+; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i32> [[X:%.*]], <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP2:%.*]] = add <4 x i32> [[TMP1]], [[X]]
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i32> [[TMP2]], i64 0
+; CHECK-NEXT:    [[X2:%.*]] = extractelement <4 x i32> [[X]], i32 2
+; CHECK-NEXT:    [[X210:%.*]] = add i32 [[TMP3]], [[X2]]
+; CHECK-NEXT:    ret i32 [[X210]]
+;
+  %x0 = extractelement <4 x i32> %x, i32 0
+  %x1 = extractelement <4 x i32> %x, i32 1
+  %x10 = add i32 %x1, %x0
+  %x2 = extractelement <4 x i32> %x, i32 2
+  %x210 = add i32 %x2, %x10
+  ret i32 %x210
+}
+
+define i32 @ext_ext_partial_add_reduction_and_extra_add_v4i32(<4 x i32> %x, <4 x i32> %y) {
+; CHECK-LABEL: @ext_ext_partial_add_reduction_and_extra_add_v4i32(
+; CHECK-NEXT:    [[Y1:%.*]] = extractelement <4 x i32> [[Y:%.*]], i32 1
+; CHECK-NEXT:    [[Y2:%.*]] = extractelement <4 x i32> [[Y]], i32 2
+; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i32> [[X:%.*]], <4 x i32> undef, <4 x i32> <i32 2, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP2:%.*]] = add <4 x i32> [[TMP1]], [[Y]]
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i32> [[TMP2]], i32 0
+; CHECK-NEXT:    [[Y210:%.*]] = add i32 [[TMP3]], [[Y1]]
+; CHECK-NEXT:    [[X2Y210:%.*]] = add i32 [[Y210]], [[Y2]]
+; CHECK-NEXT:    ret i32 [[X2Y210]]
+;
+  %y0 = extractelement <4 x i32> %y, i32 0
+  %y1 = extractelement <4 x i32> %y, i32 1
+  %y10 = add i32 %y1, %y0
+  %y2 = extractelement <4 x i32> %y, i32 2
+  %y210 = add i32 %y2, %y10
+  %x2 = extractelement <4 x i32> %x, i32 2
+  %x2y210 = add i32 %x2, %y210
+  ret i32 %x2y210
+}