[SLP]Initial support for (masked)loads + compress and (masked)interleaved

Added initial support for (masked)loads + compress and
(masked)interleaved loads.

Reviewers: RKSimon, hiraditya

Reviewed By: RKSimon

Pull Request: #132099

Author: alexey-bataev

Diff for: llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -15,19 +15,16 @@ define void @test() {
 ; CHECK-NEXT:    [[TMP2:%.*]] = fmul reassoc ninf nsz arcp contract afn float [[GEPLOAD1612]], [[TMP1]]
 ; CHECK-NEXT:    [[TMP6:%.*]] = fmul reassoc ninf nsz arcp contract afn <16 x float> [[TMP4]], [[TMP0]]
 ; CHECK-NEXT:    store <16 x float> [[TMP6]], ptr getelementptr ([16000 x i8], ptr @GLOB, i64 0, i64 2928), align 16
-; CHECK-NEXT:    [[TMP7:%.*]] = load <4 x float>, ptr getelementptr ([16000 x i8], ptr @GLOB, i64 0, i64 1272), align 16
-; CHECK-NEXT:    [[TMP8:%.*]] = load <2 x float>, ptr getelementptr ([16000 x i8], ptr @GLOB, i64 0, i64 1288), align 16
-; CHECK-NEXT:    [[TMP9:%.*]] = load <2 x float>, ptr getelementptr ([16000 x i8], ptr @GLOB, i64 0, i64 1296), align 16
-; CHECK-NEXT:    [[TMP13:%.*]] = load <8 x float>, ptr getelementptr ([16000 x i8], ptr @GLOB, i64 0, i64 1304), align 16
+; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x float>, ptr getelementptr ([16000 x i8], ptr @GLOB, i64 0, i64 1272), align 16
 ; CHECK-NEXT:    [[TMP11:%.*]] = load <2 x float>, ptr getelementptr ([16000 x i8], ptr @GLOB, i64 0, i64 1620), align 4
-; CHECK-NEXT:    [[TMP12:%.*]] = shufflevector <2 x float> [[TMP11]], <2 x float> [[TMP8]], <16 x i32> <i32 poison, i32 0, i32 2, i32 1, i32 0, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT:    [[TMP9:%.*]] = shufflevector <2 x float> [[TMP11]], <2 x float> poison, <16 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT:    [[TMP10:%.*]] = shufflevector <16 x float> [[TMP9]], <16 x float> [[TMP7]], <16 x i32> <i32 poison, i32 0, i32 20, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
 ; CHECK-NEXT:    [[TMP19:%.*]] = shufflevector <2 x float> [[TMP3]], <2 x float> poison, <16 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <16 x float> [[TMP19]], <16 x float> [[TMP12]], <16 x i32> <i32 1, i32 1, i32 17, i32 17, i32 18, i32 17, i32 17, i32 17, i32 17, i32 17, i32 17, i32 17, i32 19, i32 19, i32 19, i32 19>
-; CHECK-NEXT:    [[TMP15:%.*]] = call <16 x float> @llvm.vector.insert.v16f32.v8f32(<16 x float> [[TMP12]], <8 x float> [[TMP13]], i64 8)
-; CHECK-NEXT:    [[TMP16:%.*]] = call <16 x float> @llvm.vector.insert.v16f32.v4f32(<16 x float> [[TMP15]], <4 x float> [[TMP7]], i64 0)
-; CHECK-NEXT:    [[TMP17:%.*]] = call <16 x float> @llvm.vector.insert.v16f32.v2f32(<16 x float> [[TMP16]], <2 x float> [[TMP9]], i64 6)
+; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <16 x float> [[TMP19]], <16 x float> [[TMP10]], <16 x i32> <i32 1, i32 1, i32 17, i32 17, i32 17, i32 17, i32 17, i32 17, i32 17, i32 17, i32 17, i32 19, i32 19, i32 19, i32 19, i32 18>
+; CHECK-NEXT:    [[TMP17:%.*]] = shufflevector <16 x float> [[TMP7]], <16 x float> [[TMP14]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 18>
 ; CHECK-NEXT:    [[TMP18:%.*]] = fmul reassoc ninf nsz arcp contract afn <16 x float> [[TMP14]], [[TMP17]]
-; CHECK-NEXT:    store <16 x float> [[TMP18]], ptr getelementptr ([16000 x i8], ptr @GLOB, i64 0, i64 2992), align 16
+; CHECK-NEXT:    [[TMP15:%.*]] = shufflevector <16 x float> [[TMP18]], <16 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 15, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14>
+; CHECK-NEXT:    store <16 x float> [[TMP15]], ptr getelementptr ([16000 x i8], ptr @GLOB, i64 0, i64 2992), align 16
 ; CHECK-NEXT:    ret void
 ;
 alloca_0:

Diff for: llvm/test/Transforms/SLPVectorizer/X86/entries-shuffled-diff-sizes.ll

@@ -9,17 +9,9 @@ define void @test() {
 ; CHECK-NEXT:    [[COND_IN_V:%.*]] = select i1 false, ptr null, ptr null
 ; CHECK-NEXT:    br label [[BB:%.*]]
 ; CHECK:       bb:
-; CHECK-NEXT:    [[V:%.*]] = load i64, ptr [[COND_IN_V]], align 8
-; CHECK-NEXT:    [[BV:%.*]] = icmp eq i64 [[V]], 0
-; CHECK-NEXT:    [[IN_1:%.*]] = getelementptr i64, ptr [[COND_IN_V]], i64 4
-; CHECK-NEXT:    [[V_1:%.*]] = load i64, ptr [[IN_1]], align 8
-; CHECK-NEXT:    [[BV_1:%.*]] = icmp eq i64 [[V_1]], 0
-; CHECK-NEXT:    [[IN_2:%.*]] = getelementptr i64, ptr [[COND_IN_V]], i64 8
-; CHECK-NEXT:    [[V_2:%.*]] = load i64, ptr [[IN_2]], align 8
-; CHECK-NEXT:    [[BV_2:%.*]] = icmp eq i64 [[V_2]], 0
-; CHECK-NEXT:    [[IN_3:%.*]] = getelementptr i64, ptr [[COND_IN_V]], i64 12
-; CHECK-NEXT:    [[V_3:%.*]] = load i64, ptr [[IN_3]], align 8
-; CHECK-NEXT:    [[BV_3:%.*]] = icmp eq i64 [[V_3]], 0
+; CHECK-NEXT:    [[TMP0:%.*]] = call <13 x i64> @llvm.masked.load.v13i64.p0(ptr [[COND_IN_V]], i32 8, <13 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true>, <13 x i64> poison)
+; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <13 x i64> [[TMP0]], <13 x i64> poison, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq <4 x i64> [[TMP1]], zeroinitializer
 ; CHECK-NEXT:    ret void
 ;
 ; CHECK-SLP-THRESHOLD-LABEL: define void @test
@@ -28,11 +20,9 @@ define void @test() {
 ; CHECK-SLP-THRESHOLD-NEXT:    [[COND_IN_V:%.*]] = select i1 false, ptr null, ptr null
 ; CHECK-SLP-THRESHOLD-NEXT:    br label [[BB:%.*]]
 ; CHECK-SLP-THRESHOLD:       bb:
-; CHECK-SLP-THRESHOLD-NEXT:    [[TMP0:%.*]] = insertelement <4 x ptr> poison, ptr [[COND_IN_V]], i32 0
-; CHECK-SLP-THRESHOLD-NEXT:    [[TMP1:%.*]] = shufflevector <4 x ptr> [[TMP0]], <4 x ptr> poison, <4 x i32> zeroinitializer
-; CHECK-SLP-THRESHOLD-NEXT:    [[TMP2:%.*]] = getelementptr i64, <4 x ptr> [[TMP1]], <4 x i64> <i64 12, i64 8, i64 4, i64 0>
-; CHECK-SLP-THRESHOLD-NEXT:    [[TMP3:%.*]] = call <4 x i64> @llvm.masked.gather.v4i64.v4p0(<4 x ptr> [[TMP2]], i32 8, <4 x i1> splat (i1 true), <4 x i64> poison)
-; CHECK-SLP-THRESHOLD-NEXT:    [[TMP4:%.*]] = icmp eq <4 x i64> [[TMP3]], zeroinitializer
+; CHECK-SLP-THRESHOLD-NEXT:    [[TMP0:%.*]] = call <13 x i64> @llvm.masked.load.v13i64.p0(ptr [[COND_IN_V]], i32 8, <13 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true>, <13 x i64> poison)
+; CHECK-SLP-THRESHOLD-NEXT:    [[TMP1:%.*]] = shufflevector <13 x i64> [[TMP0]], <13 x i64> poison, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
+; CHECK-SLP-THRESHOLD-NEXT:    [[TMP2:%.*]] = icmp eq <4 x i64> [[TMP1]], zeroinitializer
 ; CHECK-SLP-THRESHOLD-NEXT:    ret void
 ;
 entry:

Diff for: llvm/test/Transforms/SLPVectorizer/X86/gep-nodes-with-non-gep-inst.ll

@@ -24,20 +24,16 @@ define void @foo() {
 ; SSE-NEXT:    ret void
 ;
 ; AVX-LABEL: @foo(
-; AVX-NEXT:    [[TMP1:%.*]] = load i32, ptr @b, align 16
-; AVX-NEXT:    [[TMP2:%.*]] = load i32, ptr getelementptr inbounds nuw (i8, ptr @b, i64 8), align 8
-; AVX-NEXT:    [[TMP3:%.*]] = insertelement <8 x i32> poison, i32 [[TMP1]], i64 0
-; AVX-NEXT:    [[TMP4:%.*]] = insertelement <8 x i32> [[TMP3]], i32 [[TMP2]], i64 1
-; AVX-NEXT:    [[TMP5:%.*]] = shufflevector <8 x i32> [[TMP4]], <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1>
+; AVX-NEXT:    [[TMP1:%.*]] = load <3 x i32>, ptr @b, align 16
+; AVX-NEXT:    [[TMP2:%.*]] = shufflevector <3 x i32> [[TMP1]], <3 x i32> poison, <2 x i32> <i32 0, i32 2>
+; AVX-NEXT:    [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1>
 ; AVX-NEXT:    store <8 x i32> [[TMP5]], ptr @a, align 16
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @foo(
-; AVX512-NEXT:    [[TMP1:%.*]] = load i32, ptr @b, align 16
-; AVX512-NEXT:    [[TMP2:%.*]] = load i32, ptr getelementptr inbounds nuw (i8, ptr @b, i64 8), align 8
-; AVX512-NEXT:    [[TMP3:%.*]] = insertelement <8 x i32> poison, i32 [[TMP1]], i64 0
-; AVX512-NEXT:    [[TMP4:%.*]] = insertelement <8 x i32> [[TMP3]], i32 [[TMP2]], i64 1
-; AVX512-NEXT:    [[TMP5:%.*]] = shufflevector <8 x i32> [[TMP4]], <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1>
+; AVX512-NEXT:    [[TMP1:%.*]] = load <3 x i32>, ptr @b, align 16
+; AVX512-NEXT:    [[TMP2:%.*]] = shufflevector <3 x i32> [[TMP1]], <3 x i32> poison, <2 x i32> <i32 0, i32 2>
+; AVX512-NEXT:    [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1>
 ; AVX512-NEXT:    store <8 x i32> [[TMP5]], ptr @a, align 16
 ; AVX512-NEXT:    ret void
 ;