[SLP] Refactoring of the operand reordering code.

This is a refactoring patch which should have all the functionality of the current code. Its goal is twofold:
i. Cleanup and simplify the reordering code, and
ii. Generalize reordering so that it will work for an arbitrary number of operands, not just 2.

This is the second patch in a series of patches that will enable operand reordering across chains of operations. An example of this was presented in EuroLLVM'18 https://www.youtube.com/watch?v=gIEn34LvyNo .

Committed on behalf of @vporpo (Vasileios Porpodas)

Differential Revision: https://reviews.llvm.org/D59973

llvm-svn: 358519

3 files changed, 44 insertions, 55 deletions

diff --git a/llvm/test/Transforms/SLPVectorizer/X86/alternate-int.ll b/llvm/test/Transforms/SLPVectorizer/X86/alternate-int.ll
index 008d34ef8e2..44729b4a8d5 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/alternate-int.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/alternate-int.ll
@@ -536,13 +536,11 @@ define <8 x i32> @sdiv_v8i32_undefs(<8 x i32> %a) {
 
 define <8 x i32> @add_sub_v8i32_splat(<8 x i32> %a, i32 %b) {
 ; CHECK-LABEL: @add_sub_v8i32_splat(
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[A:%.*]], <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x i32> undef, i32 [[B:%.*]], i32 0
-; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP4:%.*]] = add <4 x i32> [[TMP1]], [[TMP3]]
-; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    [[TMP6:%.*]] = sub <4 x i32> [[TMP3]], [[TMP5]]
-; CHECK-NEXT:    [[R7:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <8 x i32> undef, i32 [[B:%.*]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> undef, <8 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = add <8 x i32> [[TMP2]], [[A:%.*]]
+; CHECK-NEXT:    [[TMP4:%.*]] = sub <8 x i32> [[TMP2]], [[A]]
+; CHECK-NEXT:    [[R7:%.*]] = shufflevector <8 x i32> [[TMP3]], <8 x i32> [[TMP4]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-NEXT:    ret <8 x i32> [[R7]]
 ;
   %a0 = extractelement <8 x i32> %a, i32 0
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/crash_lencod.ll b/llvm/test/Transforms/SLPVectorizer/X86/crash_lencod.ll
index eb1cb32a638..53f61fe68ea 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/crash_lencod.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/crash_lencod.ll
@@ -126,14 +126,15 @@ entry:
 define fastcc void @dct36(double* %inbuf) {
 ; CHECK-LABEL: @dct36(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[ARRAYIDX41:%.*]] = getelementptr inbounds double, double* [[INBUF:%.*]], i64 2
-; CHECK-NEXT:    [[ARRAYIDX44:%.*]] = getelementptr inbounds double, double* [[INBUF]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load double, double* [[ARRAYIDX44]], align 8
-; CHECK-NEXT:    [[ADD46:%.*]] = fadd double [[TMP0]], undef
-; CHECK-NEXT:    store double [[ADD46]], double* [[ARRAYIDX41]], align 8
-; CHECK-NEXT:    [[TMP1:%.*]] = load double, double* [[INBUF]], align 8
-; CHECK-NEXT:    [[ADD49:%.*]] = fadd double [[TMP1]], [[TMP0]]
-; CHECK-NEXT:    store double [[ADD49]], double* [[ARRAYIDX44]], align 8
+; CHECK-NEXT:    [[ARRAYIDX44:%.*]] = getelementptr inbounds double, double* [[INBUF:%.*]], i64 1
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast double* [[INBUF]] to <2 x double>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[TMP1]], i32 1
+; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x double> undef, double [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <2 x double> [[TMP3]], double undef, i32 1
+; CHECK-NEXT:    [[TMP5:%.*]] = fadd <2 x double> [[TMP1]], [[TMP4]]
+; CHECK-NEXT:    [[TMP6:%.*]] = bitcast double* [[ARRAYIDX44]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> [[TMP5]], <2 x double>* [[TMP6]], align 8
 ; CHECK-NEXT:    ret void
 ;
 entry:
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/operandorder.ll b/llvm/test/Transforms/SLPVectorizer/X86/operandorder.ll
index ba5cf496fa2..726f04aafb1 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/operandorder.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/operandorder.ll
@@ -28,19 +28,16 @@ define void @shuffle_operands1(double * noalias %from, double * noalias %to, dou
   ret void
 }
 
-define void @shuffle_preserve_broadcast(double * noalias %from, double * noalias %to, double %v1, double %v2) {
-; CHECK-LABEL: @shuffle_preserve_broadcast(
+define void @vecload_vs_broadcast(double * noalias %from, double * noalias %to, double %v1, double %v2) {
+; CHECK-LABEL: @vecload_vs_broadcast(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br label [[LP:%.*]]
 ; CHECK:       lp:
 ; CHECK-NEXT:    [[P:%.*]] = phi double [ 1.000000e+00, [[LP]] ], [ 0.000000e+00, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[FROM_1:%.*]] = getelementptr double, double* [[FROM:%.*]], i32 1
-; CHECK-NEXT:    [[V0_1:%.*]] = load double, double* [[FROM]], align 4
-; CHECK-NEXT:    [[V0_2:%.*]] = load double, double* [[FROM_1]], align 4
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> undef, double [[V0_1]], i32 0
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <2 x double> [[TMP0]], <2 x double> undef, <2 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast double* [[FROM:%.*]] to <2 x double>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x double> undef, double [[P]], i32 0
-; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[V0_2]], i32 1
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <2 x double> [[TMP2]], <2 x double> [[TMP1]], <2 x i32> <i32 0, i32 2>
 ; CHECK-NEXT:    [[TMP4:%.*]] = fadd <2 x double> [[TMP1]], [[TMP3]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = bitcast double* [[TO:%.*]] to <2 x double>*
 ; CHECK-NEXT:    store <2 x double> [[TMP4]], <2 x double>* [[TMP5]], align 4
@@ -67,20 +64,17 @@ ext:
   ret void
 }
 
-define void @shuffle_preserve_broadcast2(double * noalias %from, double * noalias %to, double %v1, double %v2) {
-; CHECK-LABEL: @shuffle_preserve_broadcast2(
+define void @vecload_vs_broadcast2(double * noalias %from, double * noalias %to, double %v1, double %v2) {
+; CHECK-LABEL: @vecload_vs_broadcast2(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br label [[LP:%.*]]
 ; CHECK:       lp:
 ; CHECK-NEXT:    [[P:%.*]] = phi double [ 1.000000e+00, [[LP]] ], [ 0.000000e+00, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[FROM_1:%.*]] = getelementptr double, double* [[FROM:%.*]], i32 1
-; CHECK-NEXT:    [[V0_1:%.*]] = load double, double* [[FROM]], align 4
-; CHECK-NEXT:    [[V0_2:%.*]] = load double, double* [[FROM_1]], align 4
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> undef, double [[P]], i32 0
-; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[V0_2]], i32 1
-; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x double> undef, double [[V0_1]], i32 0
-; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <2 x double> [[TMP2]], <2 x double> undef, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP4:%.*]] = fadd <2 x double> [[TMP1]], [[TMP3]]
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast double* [[FROM:%.*]] to <2 x double>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x double> undef, double [[P]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <2 x double> [[TMP2]], <2 x double> [[TMP1]], <2 x i32> <i32 0, i32 2>
+; CHECK-NEXT:    [[TMP4:%.*]] = fadd <2 x double> [[TMP3]], [[TMP1]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = bitcast double* [[TO:%.*]] to <2 x double>*
 ; CHECK-NEXT:    store <2 x double> [[TMP4]], <2 x double>* [[TMP5]], align 4
 ; CHECK-NEXT:    br i1 undef, label [[LP]], label [[EXT:%.*]]
@@ -106,20 +100,17 @@ ext:
   ret void
 }
 
-define void @shuffle_preserve_broadcast3(double * noalias %from, double * noalias %to, double %v1, double %v2) {
-; CHECK-LABEL: @shuffle_preserve_broadcast3(
+define void @vecload_vs_broadcast3(double * noalias %from, double * noalias %to, double %v1, double %v2) {
+; CHECK-LABEL: @vecload_vs_broadcast3(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br label [[LP:%.*]]
 ; CHECK:       lp:
 ; CHECK-NEXT:    [[P:%.*]] = phi double [ 1.000000e+00, [[LP]] ], [ 0.000000e+00, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[FROM_1:%.*]] = getelementptr double, double* [[FROM:%.*]], i32 1
-; CHECK-NEXT:    [[V0_1:%.*]] = load double, double* [[FROM]], align 4
-; CHECK-NEXT:    [[V0_2:%.*]] = load double, double* [[FROM_1]], align 4
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> undef, double [[P]], i32 0
-; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[V0_2]], i32 1
-; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x double> undef, double [[V0_1]], i32 0
-; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <2 x double> [[TMP2]], <2 x double> undef, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP4:%.*]] = fadd <2 x double> [[TMP1]], [[TMP3]]
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast double* [[FROM:%.*]] to <2 x double>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x double> undef, double [[P]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <2 x double> [[TMP2]], <2 x double> [[TMP1]], <2 x i32> <i32 0, i32 2>
+; CHECK-NEXT:    [[TMP4:%.*]] = fadd <2 x double> [[TMP3]], [[TMP1]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = bitcast double* [[TO:%.*]] to <2 x double>*
 ; CHECK-NEXT:    store <2 x double> [[TMP4]], <2 x double>* [[TMP5]], align 4
 ; CHECK-NEXT:    br i1 undef, label [[LP]], label [[EXT:%.*]]
@@ -184,22 +175,21 @@ ext:
   ret void
 }
 
-define void @shuffle_preserve_broadcast5(double * noalias %from, double * noalias %to, double %v1, double %v2) {
-; CHECK-LABEL: @shuffle_preserve_broadcast5(
+define void @vecload_vs_broadcast5(double * noalias %from, double * noalias %to, double %v1, double %v2) {
+; CHECK-LABEL: @vecload_vs_broadcast5(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br label [[LP:%.*]]
 ; CHECK:       lp:
 ; CHECK-NEXT:    [[P:%.*]] = phi double [ 1.000000e+00, [[LP]] ], [ 0.000000e+00, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[FROM_1:%.*]] = getelementptr double, double* [[FROM:%.*]], i32 1
-; CHECK-NEXT:    [[V0_1:%.*]] = load double, double* [[FROM]], align 4
-; CHECK-NEXT:    [[V0_2:%.*]] = load double, double* [[FROM_1]], align 4
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> undef, double [[V0_1]], i32 0
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <2 x double> [[TMP0]], <2 x double> undef, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x double> undef, double [[V0_2]], i32 0
-; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[P]], i32 1
-; CHECK-NEXT:    [[TMP4:%.*]] = fadd <2 x double> [[TMP1]], [[TMP3]]
-; CHECK-NEXT:    [[TMP5:%.*]] = bitcast double* [[TO:%.*]] to <2 x double>*
-; CHECK-NEXT:    store <2 x double> [[TMP4]], <2 x double>* [[TMP5]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast double* [[FROM:%.*]] to <2 x double>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x double> undef, double [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <2 x double> [[TMP3]], double [[P]], i32 1
+; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <2 x double> [[TMP1]], <2 x double> undef, <2 x i32> <i32 1, i32 0>
+; CHECK-NEXT:    [[TMP6:%.*]] = fadd <2 x double> [[TMP4]], [[TMP5]]
+; CHECK-NEXT:    [[TMP7:%.*]] = bitcast double* [[TO:%.*]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> [[TMP6]], <2 x double>* [[TMP7]], align 4
 ; CHECK-NEXT:    br i1 undef, label [[LP]], label [[EXT:%.*]]
 ; CHECK:       ext:
 ; CHECK-NEXT:    ret void