From c2cc67a7728f890c563c9695883427f32c088d9b Mon Sep 17 00:00:00 2001
From: Sanjay Patel <spatel@rotateright.com>
Date: Tue, 25 Apr 2017 20:56:14 +0000
Subject: [PATCH] [x86] add more tests for potential change in bool math
 folding; NFC

Also, use AVX2 to show a potential difference for 256-bit vectors.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@301362 91177308-0d34-0410-b5e6-96231b3b80d8
---
 test/CodeGen/X86/bool-ext-inc.ll | 74 +++++++++++++++++++++++++++-----
 1 file changed, 64 insertions(+), 10 deletions(-)

diff --git a/test/CodeGen/X86/bool-ext-inc.ll b/test/CodeGen/X86/bool-ext-inc.ll
index 6f3a55f2610..6e82499ec71 100644
--- a/test/CodeGen/X86/bool-ext-inc.ll
+++ b/test/CodeGen/X86/bool-ext-inc.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 | FileCheck %s
 
 ; FIXME: add (sext i1 X), 1 -> zext (not i1 X)
 
@@ -20,9 +20,10 @@ define i32 @sext_inc(i1 zeroext %x) nounwind {
 define <4 x i32> @sext_inc_vec(<4 x i1> %x) nounwind {
 ; CHECK-LABEL: sext_inc_vec:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    pslld $31, %xmm0
-; CHECK-NEXT:    psrad $31, %xmm0
-; CHECK-NEXT:    paddd {{.*}}(%rip), %xmm0
+; CHECK-NEXT:    vpslld $31, %xmm0, %xmm0
+; CHECK-NEXT:    vpsrad $31, %xmm0, %xmm0
+; CHECK-NEXT:    vpbroadcastd {{.*}}(%rip), %xmm1
+; CHECK-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
 ; CHECK-NEXT:    retq
   %ext = sext <4 x i1> %x to <4 x i32>
   %add = add <4 x i32> %ext, <i32 1, i32 1, i32 1, i32 1>
@@ -32,8 +33,9 @@ define <4 x i32> @sext_inc_vec(<4 x i1> %x) nounwind {
 define <4 x i32> @cmpgt_sext_inc_vec(<4 x i32> %x, <4 x i32> %y) nounwind {
 ; CHECK-LABEL: cmpgt_sext_inc_vec:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    pcmpgtd %xmm1, %xmm0
-; CHECK-NEXT:    paddd {{.*}}(%rip), %xmm0
+; CHECK-NEXT:    vpcmpgtd %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    vpbroadcastd {{.*}}(%rip), %xmm1
+; CHECK-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
 ; CHECK-NEXT:    retq
   %cmp = icmp sgt <4 x i32> %x, %y
   %ext = sext <4 x i1> %cmp to <4 x i32>
@@ -44,10 +46,11 @@ define <4 x i32> @cmpgt_sext_inc_vec(<4 x i32> %x, <4 x i32> %y) nounwind {
 define <4 x i32> @cmpne_sext_inc_vec(<4 x i32> %x, <4 x i32> %y) nounwind {
 ; CHECK-LABEL: cmpne_sext_inc_vec:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    pcmpeqd %xmm1, %xmm0
-; CHECK-NEXT:    pcmpeqd %xmm1, %xmm1
-; CHECK-NEXT:    pxor %xmm1, %xmm0
-; CHECK-NEXT:    paddd {{.*}}(%rip), %xmm0
+; CHECK-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
+; CHECK-NEXT:    vpxor %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    vpbroadcastd {{.*}}(%rip), %xmm1
+; CHECK-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
 ; CHECK-NEXT:    retq
   %cmp = icmp ne <4 x i32> %x, %y
   %ext = sext <4 x i1> %cmp to <4 x i32>
@@ -55,3 +58,54 @@ define <4 x i32> @cmpne_sext_inc_vec(<4 x i32> %x, <4 x i32> %y) nounwind {
   ret <4 x i32> %add
 }
 
+define <4 x i64> @cmpgt_sext_inc_vec256(<4 x i64> %x, <4 x i64> %y) nounwind {
+; CHECK-LABEL: cmpgt_sext_inc_vec256:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vpcmpgtq %ymm1, %ymm0, %ymm0
+; CHECK-NEXT:    vpbroadcastq {{.*}}(%rip), %ymm1
+; CHECK-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
+; CHECK-NEXT:    retq
+  %cmp = icmp sgt <4 x i64> %x, %y
+  %ext = sext <4 x i1> %cmp to <4 x i64>
+  %add = add <4 x i64> %ext, <i64 1, i64 1, i64 1, i64 1>
+  ret <4 x i64> %add
+}
+
+define i32 @bool_logic_and_math(i32 %a, i32 %b, i32 %c, i32 %d) nounwind {
+; CHECK-LABEL: bool_logic_and_math:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    cmpl %esi, %edi
+; CHECK-NEXT:    setne %al
+; CHECK-NEXT:    cmpl %ecx, %edx
+; CHECK-NEXT:    setne %cl
+; CHECK-NEXT:    andb %al, %cl
+; CHECK-NEXT:    movzbl %cl, %eax
+; CHECK-NEXT:    incl %eax
+; CHECK-NEXT:    retq
+  %cmp1 = icmp ne i32 %a, %b
+  %cmp2 = icmp ne i32 %c, %d
+  %and = and i1 %cmp1, %cmp2
+  %zext = zext i1 %and to i32
+  %add = add i32 %zext, 1
+  ret i32 %add
+}
+
+define <4 x i32> @bool_logic_and_math_vec(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d) nounwind {
+; CHECK-LABEL: bool_logic_and_math_vec:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
+; CHECK-NEXT:    vpcmpeqd %xmm3, %xmm2, %xmm2
+; CHECK-NEXT:    vpxor %xmm1, %xmm2, %xmm1
+; CHECK-NEXT:    vpandn %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    vpbroadcastd {{.*}}(%rip), %xmm1
+; CHECK-NEXT:    vpsubd %xmm0, %xmm1, %xmm0
+; CHECK-NEXT:    retq
+  %cmp1 = icmp ne <4 x i32> %a, %b
+  %cmp2 = icmp ne <4 x i32> %c, %d
+  %and = and <4 x i1> %cmp1, %cmp2
+  %zext = zext <4 x i1> %and to <4 x i32>
+  %add = add <4 x i32> %zext, <i32 1, i32 1, i32 1, i32 1>
+  ret <4 x i32> %add
+}
+
-- 
2.40.0