113 lines · plain
1; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 52; RUN: opt < %s -mtriple=aarch64--linux-gnu -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output | FileCheck %s3 4target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"5 6define <8 x i8> @sel_v8i8(<8 x i8> %v0, <8 x i8> %v1) {7; CHECK-LABEL: 'sel_v8i8'8; CHECK-NEXT: Cost Model: Found costs of RThru:32 CodeSize:16 Lat:32 SizeLat:32 for: %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>9; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x i8> %tmp010;11 %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>12 ret <8 x i8> %tmp013}14 15define <16 x i8> @sel_v16i8(<16 x i8> %v0, <16 x i8> %v1) {16; CHECK-LABEL: 'sel_v16i8'17; CHECK-NEXT: Cost Model: Found costs of RThru:64 CodeSize:32 Lat:64 SizeLat:64 for: %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23, i32 8, i32 25, i32 10, i32 27, i32 12, i32 29, i32 14, i32 31>18; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <16 x i8> %tmp019;20 %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23, i32 8, i32 25, i32 10, i32 27, i32 12, i32 29, i32 14, i32 31>21 ret <16 x i8> %tmp022}23 24define <4 x i16> @sel_v4i16(<4 x i16> %v0, <4 x i16> %v1) {25; CHECK-LABEL: 'sel_v4i16'26; CHECK-NEXT: Cost Model: Found costs of 2 for: %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>27; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x i16> %tmp028;29 %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>30 ret <4 x i16> %tmp031}32 33define <8 x i16> @sel_v8i16(<8 x i16> %v0, <8 x i16> %v1) {34; CHECK-LABEL: 'sel_v8i16'35; CHECK-NEXT: Cost Model: Found costs of RThru:32 CodeSize:16 Lat:32 SizeLat:32 for: %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>36; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x i16> %tmp037;38 %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>39 ret <8 x i16> %tmp040}41 42define <2 x i32> @sel_v2i32(<2 x i32> %v0, <2 x i32> %v1) {43; CHECK-LABEL: 'sel_v2i32'44; CHECK-NEXT: Cost Model: Found costs of 1 for: %tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 0, i32 3>45; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <2 x i32> %tmp046;47 %tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 0, i32 3>48 ret <2 x i32> %tmp049}50 51define <4 x i32> @sel_v4i32(<4 x i32> %v0, <4 x i32> %v1) {52; CHECK-LABEL: 'sel_v4i32'53; CHECK-NEXT: Cost Model: Found costs of 2 for: %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>54; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x i32> %tmp055;56 %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>57 ret <4 x i32> %tmp058}59 60define <2 x i64> @sel_v2i64(<2 x i64> %v0, <2 x i64> %v1) {61; CHECK-LABEL: 'sel_v2i64'62; CHECK-NEXT: Cost Model: Found costs of 1 for: %tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 0, i32 3>63; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <2 x i64> %tmp064;65 %tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 0, i32 3>66 ret <2 x i64> %tmp067}68 69define <4 x half> @sel_v4f16(<4 x half> %v0, <4 x half> %v1) {70; CHECK-LABEL: 'sel_v4f16'71; CHECK-NEXT: Cost Model: Found costs of 2 for: %tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>72; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x half> %tmp073;74 %tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>75 ret <4 x half> %tmp076}77 78define <8 x half> @sel_v8f16(<8 x half> %v0, <8 x half> %v1) {79; CHECK-LABEL: 'sel_v8f16'80; CHECK-NEXT: Cost Model: Found costs of RThru:28 CodeSize:14 Lat:28 SizeLat:28 for: %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>81; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %tmp082;83 %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>84 ret <8 x half> %tmp085}86 87define <2 x float> @sel_v2f32(<2 x float> %v0, <2 x float> %v1) {88; CHECK-LABEL: 'sel_v2f32'89; CHECK-NEXT: Cost Model: Found costs of 1 for: %tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 0, i32 3>90; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <2 x float> %tmp091;92 %tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 0, i32 3>93 ret <2 x float> %tmp094}95 96define <4 x float> @sel_v4f32(<4 x float> %v0, <4 x float> %v1) {97; CHECK-LABEL: 'sel_v4f32'98; CHECK-NEXT: Cost Model: Found costs of 2 for: %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>99; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x float> %tmp0100;101 %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>102 ret <4 x float> %tmp0103}104 105define <2 x double> @sel_v2f64(<2 x double> %v0, <2 x double> %v1) {106; CHECK-LABEL: 'sel_v2f64'107; CHECK-NEXT: Cost Model: Found costs of 1 for: %tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 0, i32 3>108; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <2 x double> %tmp0109;110 %tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 0, i32 3>111 ret <2 x double> %tmp0112}113