From 173d4b84f61469c627e251753a034e7300faaabe Mon Sep 17 00:00:00 2001
From: Simon Moll <moll@cs.uni-saarland.de>
Date: Thu, 14 Jul 2022 12:36:22 +0200
Subject: [PATCH] [VP] Add test to show optimization opportunities

Add vp.add test cases that can are optimized with D92086 to show the
potential of generalized pattern rewriting.

Reviewed By: frasercrmck

Differential Revision: https://reviews.llvm.org/D129746
---
 llvm/test/Transforms/InstSimplify/add_vp.ll | 91 +++++++++++++++++++++++++++++
 1 file changed, 91 insertions(+)
 create mode 100644 llvm/test/Transforms/InstSimplify/add_vp.ll

diff --git a/llvm/test/Transforms/InstSimplify/add_vp.ll b/llvm/test/Transforms/InstSimplify/add_vp.ll
new file mode 100644
index 0000000..f8e6a4c
--- /dev/null
+++ b/llvm/test/Transforms/InstSimplify/add_vp.ll
@@ -0,0 +1,91 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -instsimplify -S | FileCheck %s
+
+declare <2 x i32> @llvm.vp.add.v2i32(<2 x i32>, <2 x i32>, <2 x i1>, i32)
+declare <2 x i32> @llvm.vp.sub.v2i32(<2 x i32>, <2 x i32>, <2 x i1>, i32)
+
+declare <2 x i8> @llvm.vp.add.v2i8(<2 x i8>, <2 x i8>, <2 x i1>, i32)
+declare <2 x i8> @llvm.vp.sub.v2i8(<2 x i8>, <2 x i8>, <2 x i1>, i32)
+
+; Constant folding should just work.
+define <2 x i32> @constant_vp_add(<2 x i1> %mask, i32 %evl) {
+; CHECK-LABEL: @constant_vp_add(
+; CHECK-NEXT:    [[Q:%.*]] = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> <i32 3, i32 3>, <2 x i32> <i32 7, i32 7>, <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
+; CHECK-NEXT:    ret <2 x i32> [[Q]]
+;
+  %Q = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> <i32 3, i32 3>, <2 x i32> <i32 7, i32 7>, <2 x i1> %mask, i32 %evl)
+  ret <2 x i32> %Q
+}
+
+; Simplifying pure VP intrinsic patterns.
+define <2 x i32> @common_sub_operand(<2 x i32> %X, <2 x i32> %Y, <2 x i1> %mask, i32 %evl) {
+; CHECK-LABEL: @common_sub_operand(
+; CHECK-NEXT:    [[Z:%.*]] = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> [[X:%.*]], <2 x i32> [[Y:%.*]], <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
+; CHECK-NEXT:    [[Q:%.*]] = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> [[Z]], <2 x i32> [[Y]], <2 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT:    ret <2 x i32> [[Q]]
+;
+  ; %Z = sub i32 %X, %Y, vp(%mask, %evl)
+  %Z = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> %X, <2 x i32> %Y, <2 x i1> %mask, i32 %evl)
+  ; %Q = add i32 %Z, %Y, vp(%mask, %evl)
+  %Q = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> %Z, <2 x i32> %Y, <2 x i1> %mask, i32 %evl)
+  ret <2 x i32> %Q
+}
+
+; Mixing regular SIMD with vp intrinsics (vp add match root).
+define <2 x i32> @common_sub_operand_vproot(<2 x i32> %X, <2 x i32> %Y, <2 x i1> %mask, i32 %evl) {
+; CHECK-LABEL: @common_sub_operand_vproot(
+; CHECK-NEXT:    [[Z:%.*]] = sub <2 x i32> [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[Q:%.*]] = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> [[Z]], <2 x i32> [[Y]], <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
+; CHECK-NEXT:    ret <2 x i32> [[Q]]
+;
+  %Z = sub <2 x i32> %X, %Y
+  ; %Q = add i32 %Z, %Y, vp(%mask, %evl)
+  %Q = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> %Z, <2 x i32> %Y, <2 x i1> %mask, i32 %evl)
+  ret <2 x i32> %Q
+}
+
+; Mixing regular SIMD with vp intrinsics (vp inside pattern, regular instruction root).
+define <2 x i32> @common_sub_operand_vpinner(<2 x i32> %X, <2 x i32> %Y, <2 x i1> %mask, i32 %evl) {
+; CHECK-LABEL: @common_sub_operand_vpinner(
+; CHECK-NEXT:    [[Z:%.*]] = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> [[X:%.*]], <2 x i32> [[Y:%.*]], <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
+; CHECK-NEXT:    [[Q:%.*]] = add <2 x i32> [[Z]], [[Y]]
+; CHECK-NEXT:    ret <2 x i32> [[Q]]
+;
+  ; %Z = sub i32 %X, %Y, vp(%mask, %evl)
+  %Z = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> %X, <2 x i32> %Y, <2 x i1> %mask, i32 %evl)
+  %Q = add <2 x i32> %Z, %Y
+  ret <2 x i32> %Q
+}
+
+define <2 x i32> @negated_operand(<2 x i32> %x, <2 x i1> %mask, i32 %evl) {
+; CHECK-LABEL: @negated_operand(
+; CHECK-NEXT:    [[NEGX:%.*]] = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> zeroinitializer, <2 x i32> [[X:%.*]], <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
+; CHECK-NEXT:    [[R:%.*]] = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> [[NEGX]], <2 x i32> [[X]], <2 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT:    ret <2 x i32> [[R]]
+;
+  ; %negx = sub i32 0, %x
+  %negx = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> zeroinitializer, <2 x i32> %x, <2 x i1> %mask, i32 %evl)
+  ; %r = add i32 %negx, %x
+  %r = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> %negx, <2 x i32> %x, <2 x i1> %mask, i32 %evl)
+  ret <2 x i32> %r
+}
+
+; TODO Lift InstSimplify::SimplifyAdd to the trait framework to optimize this.
+define <2 x i8> @knownnegation(<2 x i8> %x, <2 x i8> %y, <2 x i1> %mask, i32 %evl) {
+; TODO-CHECK-LABEL: @knownnegation(
+; TODO-XHECK-NEXT:    ret i8 <2 x i8> zeroinitializer
+;
+  ; %xy = sub i8 %x, %y
+; CHECK-LABEL: @knownnegation(
+; CHECK-NEXT:    [[XY:%.*]] = call <2 x i8> @llvm.vp.sub.v2i8(<2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
+; CHECK-NEXT:    [[YX:%.*]] = call <2 x i8> @llvm.vp.sub.v2i8(<2 x i8> [[Y]], <2 x i8> [[X]], <2 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> [[XY]], <2 x i8> [[YX]], <2 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT:    ret <2 x i8> [[R]]
+;
+  %xy = call <2 x i8> @llvm.vp.sub.v2i8(<2 x i8> %x, <2 x i8> %y, <2 x i1> %mask, i32 %evl)
+  ; %yx = sub i8 %y, %x
+  %yx = call <2 x i8> @llvm.vp.sub.v2i8(<2 x i8> %y, <2 x i8> %x, <2 x i1> %mask, i32 %evl)
+  ; %r = add i8 %xy, %yx
+  %r = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> %xy, <2 x i8> %yx, <2 x i1> %mask, i32 %evl)
+  ret <2 x i8> %r
+}
-- 
2.7.4