From 9b21cf336d5dfbbb2b50c40ccad6bca968fef6fb Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Wed, 4 May 2016 15:45:48 +0000
Subject: [PATCH] [X86][SSE] Regenerate vector bswap tests

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@268514 91177308-0d34-0410-b5e6-96231b3b80d8
---
 test/CodeGen/X86/bswap-vector.ll | 151 +++++++++++++++++++------------
 1 file changed, 91 insertions(+), 60 deletions(-)

diff --git a/test/CodeGen/X86/bswap-vector.ll b/test/CodeGen/X86/bswap-vector.ll
index 5376601a95e..6697183ab67 100644
--- a/test/CodeGen/X86/bswap-vector.ll
+++ b/test/CodeGen/X86/bswap-vector.ll
@@ -1,7 +1,8 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mcpu=x86-64 | FileCheck %s --check-prefix=CHECK-ALL --check-prefix=CHECK-SSE --check-prefix=CHECK-NOSSSE3
 ; RUN: llc < %s -mcpu=core2 | FileCheck %s --check-prefix=CHECK-ALL --check-prefix=CHECK-SSE --check-prefix=CHECK-SSSE3
-; RUN: llc < %s -mcpu=core-avx2 | FileCheck %s --check-prefix=CHECK-AVX --check-prefix=CHECK-AVX2
-; RUN: llc < %s -mcpu=core-avx2 -x86-experimental-vector-widening-legalization | FileCheck %s --check-prefix=CHECK-WIDE-AVX2
+; RUN: llc < %s -mcpu=core-avx2 | FileCheck %s --check-prefix=CHECK-ALL --check-prefix=CHECK-AVX --check-prefix=CHECK-AVX2
+; RUN: llc < %s -mcpu=core-avx2 -x86-experimental-vector-widening-legalization | FileCheck %s --check-prefix=CHECK-ALL --check-prefix=CHECK-WIDE-AVX --check-prefix=CHECK-WIDE-AVX2
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
@@ -29,15 +30,15 @@ define <8 x i16> @test1(<8 x i16> %v) {
 ; CHECK-SSSE3-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[1,0,3,2,5,4,7,6,9,8,11,10,13,12,15,14]
 ; CHECK-SSSE3-NEXT:    retq
 ;
-; CHECK-AVX2-LABEL: test1:
-; CHECK-AVX2:       # BB#0: # %entry
-; CHECK-AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[1,0,3,2,5,4,7,6,9,8,11,10,13,12,15,14]
-; CHECK-AVX2-NEXT:    retq
+; CHECK-AVX-LABEL: test1:
+; CHECK-AVX:       # BB#0: # %entry
+; CHECK-AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[1,0,3,2,5,4,7,6,9,8,11,10,13,12,15,14]
+; CHECK-AVX-NEXT:    retq
 ;
-; CHECK-WIDE-AVX2-LABEL: test1:
-; CHECK-WIDE-AVX2:       # BB#0: # %entry
-; CHECK-WIDE-AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[1,0,3,2,5,4,7,6,9,8,11,10,13,12,15,14]
-; CHECK-WIDE-AVX2-NEXT:    retq
+; CHECK-WIDE-AVX-LABEL: test1:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[1,0,3,2,5,4,7,6,9,8,11,10,13,12,15,14]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> %v)
   ret <8 x i16> %r
@@ -62,15 +63,15 @@ define <4 x i32> @test2(<4 x i32> %v) {
 ; CHECK-SSSE3-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
 ; CHECK-SSSE3-NEXT:    retq
 ;
-; CHECK-AVX2-LABEL: test2:
-; CHECK-AVX2:       # BB#0: # %entry
-; CHECK-AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
-; CHECK-AVX2-NEXT:    retq
+; CHECK-AVX-LABEL: test2:
+; CHECK-AVX:       # BB#0: # %entry
+; CHECK-AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
+; CHECK-AVX-NEXT:    retq
 ;
-; CHECK-WIDE-AVX2-LABEL: test2:
-; CHECK-WIDE-AVX2:       # BB#0: # %entry
-; CHECK-WIDE-AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
-; CHECK-WIDE-AVX2-NEXT:    retq
+; CHECK-WIDE-AVX-LABEL: test2:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> %v)
   ret <4 x i32> %r
@@ -97,15 +98,15 @@ define <2 x i64> @test3(<2 x i64> %v) {
 ; CHECK-SSSE3-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[7,6,5,4,3,2,1,0,15,14,13,12,11,10,9,8]
 ; CHECK-SSSE3-NEXT:    retq
 ;
-; CHECK-AVX2-LABEL: test3:
-; CHECK-AVX2:       # BB#0: # %entry
-; CHECK-AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[7,6,5,4,3,2,1,0,15,14,13,12,11,10,9,8]
-; CHECK-AVX2-NEXT:    retq
+; CHECK-AVX-LABEL: test3:
+; CHECK-AVX:       # BB#0: # %entry
+; CHECK-AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[7,6,5,4,3,2,1,0,15,14,13,12,11,10,9,8]
+; CHECK-AVX-NEXT:    retq
 ;
-; CHECK-WIDE-AVX2-LABEL: test3:
-; CHECK-WIDE-AVX2:       # BB#0: # %entry
-; CHECK-WIDE-AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[7,6,5,4,3,2,1,0,15,14,13,12,11,10,9,8]
-; CHECK-WIDE-AVX2-NEXT:    retq
+; CHECK-WIDE-AVX-LABEL: test3:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[7,6,5,4,3,2,1,0,15,14,13,12,11,10,9,8]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> %v)
   ret <2 x i64> %r
@@ -144,15 +145,15 @@ define <16 x i16> @test4(<16 x i16> %v) {
 ; CHECK-SSSE3-NEXT:    pshufb %xmm2, %xmm1
 ; CHECK-SSSE3-NEXT:    retq
 ;
-; CHECK-AVX2-LABEL: test4:
-; CHECK-AVX2:       # BB#0: # %entry
-; CHECK-AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[1,0,3,2,5,4,7,6,9,8,11,10,13,12,15,14,17,16,19,18,21,20,23,22,25,24,27,26,29,28,31,30]
-; CHECK-AVX2-NEXT:    retq
+; CHECK-AVX-LABEL: test4:
+; CHECK-AVX:       # BB#0: # %entry
+; CHECK-AVX-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[1,0,3,2,5,4,7,6,9,8,11,10,13,12,15,14,17,16,19,18,21,20,23,22,25,24,27,26,29,28,31,30]
+; CHECK-AVX-NEXT:    retq
 ;
-; CHECK-WIDE-AVX2-LABEL: test4:
-; CHECK-WIDE-AVX2:       # BB#0: # %entry
-; CHECK-WIDE-AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[1,0,3,2,5,4,7,6,9,8,11,10,13,12,15,14,17,16,19,18,21,20,23,22,25,24,27,26,29,28,31,30]
-; CHECK-WIDE-AVX2-NEXT:    retq
+; CHECK-WIDE-AVX-LABEL: test4:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[1,0,3,2,5,4,7,6,9,8,11,10,13,12,15,14,17,16,19,18,21,20,23,22,25,24,27,26,29,28,31,30]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> %v)
   ret <16 x i16> %r
@@ -187,15 +188,15 @@ define <8 x i32> @test5(<8 x i32> %v) {
 ; CHECK-SSSE3-NEXT:    pshufb %xmm2, %xmm1
 ; CHECK-SSSE3-NEXT:    retq
 ;
-; CHECK-AVX2-LABEL: test5:
-; CHECK-AVX2:       # BB#0: # %entry
-; CHECK-AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12,19,18,17,16,23,22,21,20,27,26,25,24,31,30,29,28]
-; CHECK-AVX2-NEXT:    retq
+; CHECK-AVX-LABEL: test5:
+; CHECK-AVX:       # BB#0: # %entry
+; CHECK-AVX-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12,19,18,17,16,23,22,21,20,27,26,25,24,31,30,29,28]
+; CHECK-AVX-NEXT:    retq
 ;
-; CHECK-WIDE-AVX2-LABEL: test5:
-; CHECK-WIDE-AVX2:       # BB#0: # %entry
-; CHECK-WIDE-AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12,19,18,17,16,23,22,21,20,27,26,25,24,31,30,29,28]
-; CHECK-WIDE-AVX2-NEXT:    retq
+; CHECK-WIDE-AVX-LABEL: test5:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12,19,18,17,16,23,22,21,20,27,26,25,24,31,30,29,28]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> %v)
   ret <8 x i32> %r
@@ -234,15 +235,15 @@ define <4 x i64> @test6(<4 x i64> %v) {
 ; CHECK-SSSE3-NEXT:    pshufb %xmm2, %xmm1
 ; CHECK-SSSE3-NEXT:    retq
 ;
-; CHECK-AVX2-LABEL: test6:
-; CHECK-AVX2:       # BB#0: # %entry
-; CHECK-AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[7,6,5,4,3,2,1,0,15,14,13,12,11,10,9,8,23,22,21,20,19,18,17,16,31,30,29,28,27,26,25,24]
-; CHECK-AVX2-NEXT:    retq
+; CHECK-AVX-LABEL: test6:
+; CHECK-AVX:       # BB#0: # %entry
+; CHECK-AVX-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[7,6,5,4,3,2,1,0,15,14,13,12,11,10,9,8,23,22,21,20,19,18,17,16,31,30,29,28,27,26,25,24]
+; CHECK-AVX-NEXT:    retq
 ;
-; CHECK-WIDE-AVX2-LABEL: test6:
-; CHECK-WIDE-AVX2:       # BB#0: # %entry
-; CHECK-WIDE-AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[7,6,5,4,3,2,1,0,15,14,13,12,11,10,9,8,23,22,21,20,19,18,17,16,31,30,29,28,27,26,25,24]
-; CHECK-WIDE-AVX2-NEXT:    retq
+; CHECK-WIDE-AVX-LABEL: test6:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[7,6,5,4,3,2,1,0,15,14,13,12,11,10,9,8,23,22,21,20,19,18,17,16,31,30,29,28,27,26,25,24]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> %v)
   ret <4 x i64> %r
@@ -271,16 +272,16 @@ define <4 x i16> @test7(<4 x i16> %v) {
 ; CHECK-SSSE3-NEXT:    psrld $16, %xmm0
 ; CHECK-SSSE3-NEXT:    retq
 ;
-; CHECK-AVX2-LABEL: test7:
-; CHECK-AVX2:       # BB#0: # %entry
-; CHECK-AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
-; CHECK-AVX2-NEXT:    vpsrld $16, %xmm0, %xmm0
-; CHECK-AVX2-NEXT:    retq
+; CHECK-AVX-LABEL: test7:
+; CHECK-AVX:       # BB#0: # %entry
+; CHECK-AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
+; CHECK-AVX-NEXT:    vpsrld $16, %xmm0, %xmm0
+; CHECK-AVX-NEXT:    retq
 ;
-; CHECK-WIDE-AVX2-LABEL: test7:
-; CHECK-WIDE-AVX2:       # BB#0: # %entry
-; CHECK-WIDE-AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[1,0,3,2,5,4,7,6,9,8,11,10,13,12,15,14]
-; CHECK-WIDE-AVX2-NEXT:    retq
+; CHECK-WIDE-AVX-LABEL: test7:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[1,0,3,2,5,4,7,6,9,8,11,10,13,12,15,14]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <4 x i16> @llvm.bswap.v4i16(<4 x i16> %v)
   ret <4 x i16> %r
@@ -293,7 +294,7 @@ entry:
 define <8 x i16> @identity_v8i16(<8 x i16> %v) {
 ; CHECK-ALL-LABEL: identity_v8i16:
 ; CHECK-ALL:       # BB#0: # %entry
-; CHECK-ALL:         retq
+; CHECK-ALL-NEXT:    retq
 entry:
   %bs1 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> %v)
   %bs2 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> %bs1)
@@ -374,6 +375,11 @@ define <8 x i16> @fold_v8i16() {
 ; CHECK-AVX:       # BB#0: # %entry
 ; CHECK-AVX-NEXT:    vmovaps {{.*#+}} xmm0 = [0,256,65535,512,65023,1024,64511,1536]
 ; CHECK-AVX-NEXT:    retq
+;
+; CHECK-WIDE-AVX-LABEL: fold_v8i16:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vmovaps {{.*#+}} xmm0 = [0,256,65535,512,65023,1024,64511,1536]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> <i16 0, i16 1, i16 -1, i16 2, i16 -3, i16 4, i16 -5, i16 6>)
   ret <8 x i16> %r
@@ -389,6 +395,11 @@ define <4 x i32> @fold_v4i32() {
 ; CHECK-AVX:       # BB#0: # %entry
 ; CHECK-AVX-NEXT:    vmovaps {{.*#+}} xmm0 = [0,4294967295,33554432,4261412863]
 ; CHECK-AVX-NEXT:    retq
+;
+; CHECK-WIDE-AVX-LABEL: fold_v4i32:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vmovaps {{.*#+}} xmm0 = [0,4294967295,33554432,4261412863]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> <i32 0, i32 -1, i32 2, i32 -3>)
   ret <4 x i32> %r
@@ -404,6 +415,11 @@ define <2 x i64> @fold_v2i64() {
 ; CHECK-AVX:       # BB#0: # %entry
 ; CHECK-AVX-NEXT:    vmovaps {{.*#+}} xmm0 = [18374686479671623680,18446744073709551615]
 ; CHECK-AVX-NEXT:    retq
+;
+; CHECK-WIDE-AVX-LABEL: fold_v2i64:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vmovaps {{.*#+}} xmm0 = [18374686479671623680,18446744073709551615]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> <i64 255, i64 -1>)
   ret <2 x i64> %r
@@ -420,6 +436,11 @@ define <16 x i16> @fold_v16i16() {
 ; CHECK-AVX:       # BB#0: # %entry
 ; CHECK-AVX-NEXT:    vmovaps {{.*#+}} ymm0 = [0,256,65535,512,65023,1024,64511,1536,63999,2048,63487,2560,62975,3072,62463,3584]
 ; CHECK-AVX-NEXT:    retq
+;
+; CHECK-WIDE-AVX-LABEL: fold_v16i16:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vmovaps {{.*#+}} ymm0 = [0,256,65535,512,65023,1024,64511,1536,63999,2048,63487,2560,62975,3072,62463,3584]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> <i16 0, i16 1, i16 -1, i16 2, i16 -3, i16 4, i16 -5, i16 6, i16 -7, i16 8, i16 -9, i16 10, i16 -11, i16 12, i16 -13, i16 14>)
   ret <16 x i16> %r
@@ -436,6 +457,11 @@ define <8 x i32> @fold_v8i32() {
 ; CHECK-AVX:       # BB#0: # %entry
 ; CHECK-AVX-NEXT:    vmovaps {{.*#+}} ymm0 = [0,16777216,4294967295,33554432,4261412863,67108864,4227858431,100663296]
 ; CHECK-AVX-NEXT:    retq
+;
+; CHECK-WIDE-AVX-LABEL: fold_v8i32:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vmovaps {{.*#+}} ymm0 = [0,16777216,4294967295,33554432,4261412863,67108864,4227858431,100663296]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> <i32 0, i32 1, i32 -1, i32 2, i32 -3, i32 4, i32 -5, i32 6>)
   ret <8 x i32> %r
@@ -452,6 +478,11 @@ define <4 x i64> @fold_v4i64() {
 ; CHECK-AVX:       # BB#0: # %entry
 ; CHECK-AVX-NEXT:    vmovaps {{.*#+}} ymm0 = [18374686479671623680,18446744073709551615,18446462598732840960,72056494526300160]
 ; CHECK-AVX-NEXT:    retq
+;
+; CHECK-WIDE-AVX-LABEL: fold_v4i64:
+; CHECK-WIDE-AVX:       # BB#0: # %entry
+; CHECK-WIDE-AVX-NEXT:    vmovaps {{.*#+}} ymm0 = [18374686479671623680,18446744073709551615,18446462598732840960,72056494526300160]
+; CHECK-WIDE-AVX-NEXT:    retq
 entry:
   %r = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> <i64 255, i64 -1, i64 65535, i64 16776960>)
   ret <4 x i64> %r
-- 
2.50.1