diff --git a/llvm/include/llvm/Support/AArch64TargetParser.def b/llvm/include/llvm/Support/AArch64TargetParser.def --- a/llvm/include/llvm/Support/AArch64TargetParser.def +++ b/llvm/include/llvm/Support/AArch64TargetParser.def @@ -165,6 +165,10 @@ (AArch64::AEK_CRC)) AARCH64_CPU_NAME("thunderx2t99", ARMV8_1A, FK_CRYPTO_NEON_FP_ARMV8, false, (AArch64::AEK_NONE)) +AARCH64_CPU_NAME("thunderx3t110", ARMV8_3A, FK_CRYPTO_NEON_FP_ARMV8, false, + (AArch64::AEK_CRC | AEK_CRYPTO | AEK_FP | AEK_SIMD | + AEK_LSE | AEK_RAND | AArch64::AEK_PROFILE | + AArch64::AEK_RAS)) AARCH64_CPU_NAME("thunderx", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false, (AArch64::AEK_CRC | AArch64::AEK_PROFILE)) AARCH64_CPU_NAME("thunderxt88", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false, diff --git a/llvm/lib/Target/AArch64/AArch64.td b/llvm/lib/Target/AArch64/AArch64.td --- a/llvm/lib/Target/AArch64/AArch64.td +++ b/llvm/lib/Target/AArch64/AArch64.td @@ -469,7 +469,7 @@ def SVEUnsupported : AArch64Unsupported { let F = [HasSVE, HasSVE2, HasSVE2AES, HasSVE2SM4, HasSVE2SHA3, - HasSVE2BitPerm]; + HasSVE2BitPerm, HasPA]; } include "AArch64SchedA53.td" @@ -482,6 +482,7 @@ include "AArch64SchedExynosM5.td" include "AArch64SchedThunderX.td" include "AArch64SchedThunderX2T99.td" +include "AArch64SchedThunderX3T110.td" def ProcA35 : SubtargetFeature<"a35", "ARMProcFamily", "CortexA35", "Cortex-A35 ARM processors", [ @@ -830,6 +831,25 @@ FeatureLSE, HasV8_1aOps]>; +def ProcThunderX3T110 : SubtargetFeature<"thunderx3t110", "ARMProcFamily", + "ThunderX3T110", + "Marvell ThunderX3 processors", [ + FeatureAggressiveFMA, + FeatureCRC, + FeatureCrypto, + FeatureFPARMv8, + FeatureArithmeticBccFusion, + FeatureNEON, + FeaturePostRAScheduler, + FeaturePredictableSelectIsExpensive, + FeatureLSE, + FeaturePA, + FeatureUseAA, + FeatureBalanceFPOps, + FeaturePerfMon, + FeatureStrictAlign, + HasV8_3aOps]>; + def ProcThunderX : SubtargetFeature<"thunderx", "ARMProcFamily", "ThunderX", "Cavium ThunderX processors", [ FeatureCRC, @@ -929,6 +949,8 @@ def : ProcessorModel<"thunderxt83", ThunderXT8XModel, [ProcThunderXT83]>; // Cavium ThunderX2T9X Processors. Formerly Broadcom Vulcan. def : ProcessorModel<"thunderx2t99", ThunderX2T99Model, [ProcThunderX2T99]>; +// Marvell ThunderX3T110 Processors. +def : ProcessorModel<"thunderx3t110", ThunderX3T110Model, [ProcThunderX3T110]>; // FIXME: HiSilicon TSV110 is currently modeled as a Cortex-A57. def : ProcessorModel<"tsv110", CortexA57Model, [ProcTSV110]>; diff --git a/llvm/lib/Target/AArch64/AArch64SchedThunderX3T110.td b/llvm/lib/Target/AArch64/AArch64SchedThunderX3T110.td new file mode 100644 --- /dev/null +++ b/llvm/lib/Target/AArch64/AArch64SchedThunderX3T110.td @@ -0,0 +1,1998 @@ +//=- AArch64SchedThunderX3T110.td - Marvell ThunderX3 T110 ---*- tablegen -*-=// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// +// +// This file defines the scheduling model for Marvell ThunderX3T110 +// family of processors. +// +//===----------------------------------------------------------------------===// + +//===----------------------------------------------------------------------===// +// Pipeline Description. + +def ThunderX3T110Model : SchedMachineModel { + let IssueWidth = 4; // 4 micro-ops dispatched at a time. + let MicroOpBufferSize = 70; // 70 entries in micro-op re-order buffer. + let LoadLatency = 4; // Optimistic load latency. + let MispredictPenalty = 12; // Extra cycles for mispredicted branch. + // Determined via a mix of micro-arch details and experimentation. + let LoopMicroOpBufferSize = 128; // FIXME: might be much bigger in TX3. + let PostRAScheduler = 1; // Using PostRA sched. + let CompleteModel = 1; + + list UnsupportedFeatures = SVEUnsupported.F; + + // FIXME: Remove when all errors have been fixed. + let FullInstRWOverlapCheck = 0; +} + +let SchedModel = ThunderX3T110Model in { + +// Issue ports. + +// Port 0: ALU. +def THX3T110P0 : ProcResource<1>; + +// Port 1: ALU. +def THX3T110P1 : ProcResource<1>; + +// Port 2: ALU/Branch. +def THX3T110P2 : ProcResource<1>; + +// Port 3: ALU/Branch. +def THX3T110P3 : ProcResource<1>; + +// Port 4: Load/Store. +def THX3T110P4 : ProcResource<1>; + +// Port 5: Load/store. +def THX3T110P5 : ProcResource<1>; + +// Port 6: FP/Neon/SIMD/Crypto. +def THX3T110P6FP0 : ProcResource<1>; + +// Port 7: FP/Neon/SIMD/Crypto. +def THX3T110P7FP1 : ProcResource<1>; + +// Port 8: FP/Neon/SIMD/Crypto. +def THX3T110P8FP2 : ProcResource<1>; + +// Port 9: FP/Neon/SIMD/Crypto. +def THX3T110P9FP3 : ProcResource<1>; + +// Port 10: Store Data Unit. +def THX3T110SD0 : ProcResource<1>; + +// Define groups for the functional units on each issue port. Each group +// created will be used by a WriteRes. + +// Integer divide/mulhi micro-ops only on port I1. +def THX3T110I1 : ProcResGroup<[THX3T110P1]>; + +// Branch micro-ops on ports I2/I3. +def THX3T110I23 : ProcResGroup<[THX3T110P2, THX3T110P3]>; + +// Branch micro-ops on ports I1/I2/I3. +def THX3T110I123 : ProcResGroup<[THX3T110P1, THX3T110P2, THX3T110P3]>; + +// Integer micro-ops on ports I0/I1/I2. +def THX3T110I012 : ProcResGroup<[THX3T110P0, THX3T110P1, THX3T110P2]>; + +// Integer micro-ops on ports I0/I1/I2/I3. +def THX3T110I0123 : ProcResGroup<[THX3T110P0, THX3T110P1, + THX3T110P2, THX3T110P3]>; + +// FP micro-ops on ports FP0/FP1/FP2/FP3. +def THX3T110FP0123 : ProcResGroup<[THX3T110P6FP0, THX3T110P7FP1, + THX3T110P8FP2, THX3T110P9FP3]>; + +// FP micro-ops on ports FP2/FP3. +def THX3T110FP23 : ProcResGroup<[THX3T110P8FP2, THX3T110P9FP3]>; + +// ASIMD micro-ops on ports FP0/FP1/FP2/FP3. +def THX3T110SIMD : ProcResGroup<[THX3T110P6FP0, THX3T110P7FP1, + THX3T110P8FP2, THX3T110P9FP3]>; + +// Store data micro-ops only on port 10. +def THX3T110SD : ProcResGroup<[THX3T110SD0]>; + +// Load/store micro-ops on ports P4/P5. +def THX3T110LS : ProcResGroup<[THX3T110P4, THX3T110P5]>; + +// 70 entry unified scheduler. +def THX3T110ANY: ProcResGroup<[THX3T110P0, THX3T110P1, THX3T110P2, + THX3T110P3, THX3T110P4, THX3T110P5, + THX3T110P6FP0, THX3T110P7FP1, + THX3T110P8FP2, THX3T110P9FP3]> { + let BufferSize = 70; +} + +// Define commonly used write types for InstRW specializations. +// All definitions follow the format: THX3T110Write_Cyc_. + +// 3 cycles on I1. +def THX3T110Write_3Cyc_I1 : SchedWriteRes<[THX3T110I1]> { + let Latency = 3; + let NumMicroOps = 2; +} + +// 4 cycles on I1. +def THX3T110Write_4Cyc_I1 : SchedWriteRes<[THX3T110I1]> { + let Latency = 4; + let NumMicroOps = 2; +} + +// 5 cycles on I1. +def THX3T110Write_5Cyc_I1 : SchedWriteRes<[THX3T110I1]> { + let Latency = 5; + let NumMicroOps = 2; +} + +// 7 cycles on I1. +def THX3T110Write_7Cyc_I1 : SchedWriteRes<[THX3T110I1]> { + let Latency = 7; + let NumMicroOps = 3; +} + +// 23 cycles on I1. +def THX3T110Write_23Cyc_I1 : SchedWriteRes<[THX3T110I1]> { + let Latency = 23; + let ResourceCycles = [13, 23]; + let NumMicroOps = 4; +} + +// 39 cycles on I1. +def THX3T110Write_39Cyc_I1 : SchedWriteRes<[THX3T110I1]> { + let Latency = 39; + let ResourceCycles = [13, 39]; + let NumMicroOps = 4; +} + +// 1 cycle on I2/I3 +def THX3T110Write_1Cyc_I23 : SchedWriteRes<[THX3T110I23]> { + let Latency = 1; + let NumMicroOps = 2; +} + +// 8 cycles on I2/I3 +def THX3T110Write_8Cyc_I23 : SchedWriteRes<[THX3T110I23]> { + let Latency = 8; + let NumMicroOps = 3; +} + +// 1 cycle on I1/I2/I3 +def THX3T110Write_1Cyc_I123 : SchedWriteRes<[THX3T110I123]> { + let Latency = 1; + let NumMicroOps = 2; +} + +// 8 cycles on I1/I2/I3 +def THX3T110Write_8Cyc_I123 : SchedWriteRes<[THX3T110I123]> { + let Latency = 8; + let NumMicroOps = 3; +} + +// 1 cycle on I0/I1/I2/I3. +def THX3T110Write_1Cyc_I0123 : SchedWriteRes<[THX3T110I0123]> { + let Latency = 1; + let NumMicroOps = 2; +} + +// 2 cycles on I0/I1/I2/I3. +def THX3T110Write_2Cyc_I0123 : SchedWriteRes<[THX3T110I0123]> { + let Latency = 2; + let NumMicroOps = 2; +} + +// 3 cycles on I0/I1/I2/I3. +def THX3T110Write_3Cyc_I0123 : SchedWriteRes<[THX3T110I0123]> { + let Latency = 3; + let NumMicroOps = 2; +} + +// 4 cycles on I0/I1/I2/I3. +def THX3T110Write_4Cyc_I0123 : SchedWriteRes<[THX3T110I0123]> { + let Latency = 4; + let NumMicroOps = 3; +} + +// 5 cycles on I0/I1/I2/I3. +def THX3T110Write_5Cyc_I0123 : SchedWriteRes<[THX3T110I0123]> { + let Latency = 5; + let NumMicroOps = 3; +} + +// 6 cycles on I0/I1/I2/I3. +def THX3T110Write_6Cyc_I0123 : SchedWriteRes<[THX3T110I0123]> { + let Latency = 6; + let NumMicroOps = 3; +} + +// 8 cycles on I0/I1/I2/I3. +def THX3T110Write_8Cyc_I0123 : SchedWriteRes<[THX3T110I0123]> { + let Latency = 8; + let NumMicroOps = 4; +} + +// 13 cycles on I0/I1/I2/I3. +def THX3T110Write_13Cyc_I0123 : SchedWriteRes<[THX3T110I0123]> { + let Latency = 13; + let NumMicroOps = 3; +} + +// 23 cycles on I0/I1/I2/I3. +def THX3T110Write_23Cyc_I0123 : SchedWriteRes<[THX3T110I0123]> { + let Latency = 23; + let NumMicroOps = 3; +} + +// 39 cycles on I0/I1/I2/I3. +def THX3T110Write_39Cyc_I0123 : SchedWriteRes<[THX3T110I0123]> { + let Latency = 39; + let NumMicroOps = 3; +} + +// 4 cycles on F2/F3. +def THX3T110Write_4Cyc_F23 : SchedWriteRes<[THX3T110FP23]> { + let Latency = 4; + let NumMicroOps = 2; +} + +// 5 cycles on F0/F1/F2/F3. +def THX3T110Write_5Cyc_F01 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 5; + let NumMicroOps = 2; +} + +// 6 cycles on F0/F1/F2/F3. +def THX3T110Write_6Cyc_F01 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 6; + let NumMicroOps = 3; +} + +// 7 cycles on F0/F1/F2/F3. +def THX3T110Write_7Cyc_F01 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 7; + let NumMicroOps = 3; +} + +// 8 cycles on F0/F1/F2/F3. +def THX3T110Write_8Cyc_F01 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 8; + let NumMicroOps = 3; +} + +// 10 cycles on F0/F1/F2/F3. +def THX3T110Write_10Cyc_F01 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 10; + let NumMicroOps = 3; +} + +// 16 cycles on F0/F1/F2/F3. +def THX3T110Write_16Cyc_F01 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 16; + let NumMicroOps = 3; + let ResourceCycles = [8]; +} + +// 23 cycles on F0/F1/F2/F3. +def THX3T110Write_23Cyc_F01 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 23; + let NumMicroOps = 3; + let ResourceCycles = [11]; +} + +// 1 cycle on LS0/LS1. +def THX3T110Write_1Cyc_LS01 : SchedWriteRes<[THX3T110LS]> { + let Latency = 1; + let NumMicroOps = 1; +} + +// 2 cycles on LS0/LS1. +def THX3T110Write_2Cyc_LS01 : SchedWriteRes<[THX3T110LS]> { + let Latency = 2; + let NumMicroOps = 2; +} + +// 4 cycles on LS0/LS1. +def THX3T110Write_4Cyc_LS01 : SchedWriteRes<[THX3T110LS]> { + let Latency = 4; + let NumMicroOps = 2; + let ResourceCycles = [2]; +} + +// 5 cycles on LS0/LS1. +def THX3T110Write_5Cyc_LS01 : SchedWriteRes<[THX3T110LS]> { + let Latency = 5; + let NumMicroOps = 3; +} + +// 6 cycles on LS0/LS1. +def THX3T110Write_6Cyc_LS01 : SchedWriteRes<[THX3T110LS]> { + let Latency = 6; + let NumMicroOps = 3; +} + +// 4 + 5 cycles on LS0/LS1. +// First resource is available after 4 cycles. +// Second resource is available after 5 cycles. +// Load vector pair, immed offset, Q-form [LDP/LDNP]. +def THX3T110Write_4_5Cyc_LS01 : SchedWriteRes<[THX3T110LS]> { + let Latency = 4; + let NumMicroOps = 2; + let ResourceCycles = [4, 5]; +} + +// 4 + 8 cycles on LS0/LS1. +// First resource is available after 4 cycles. +// Second resource is available after 8 cycles. +// Load vector pair, immed offset, S/D-form [LDP/LDNP]. +def THX3T110Write_4_8Cyc_LS01 : SchedWriteRes<[THX3T110LS]> { + let Latency = 4; + let NumMicroOps = 2; + let ResourceCycles = [4, 8]; +} + +// 11 cycles on LS0/LS1 and I1. +def THX3T110Write_11Cyc_LS01_I1 : + SchedWriteRes<[THX3T110LS, THX3T110I1]> { + let Latency = 11; + let NumMicroOps = 4; +} + +// 1 cycles on LS0/LS1 and I0/I1/I2/I3. +def THX3T110Write_1Cyc_LS01_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123]> { + let Latency = 1; + let NumMicroOps = 2; +} + +// 1 cycles on LS0/LS1 and 2 of I0/I1/I2/I3. +def THX3T110Write_1Cyc_LS01_I0123_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123, THX3T110I0123]> { + let Latency = 1; + let NumMicroOps = 3; +} + +// 4 cycles on LS0/LS1 and I0/I1/I2/I3. +def THX3T110Write_4Cyc_LS01_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123]> { + let Latency = 4; + let NumMicroOps = 3; +} + +// 4 cycles on LS0/LS1 and 2 of I0/I1/I2/I3. +def THX3T110Write_4Cyc_LS01_I0123_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123, THX3T110I0123]> { + let Latency = 4; + let NumMicroOps = 3; +} + +// 5 cycles on LS0/LS1 and I0/I1/I2/I3. +def THX3T110Write_5Cyc_LS01_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123]> { + let Latency = 5; + let NumMicroOps = 3; +} + +// 5 cycles on LS0/LS1 and 2 of I0/I1/I2/I3. +def THX3T110Write_5Cyc_LS01_I0123_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123, THX3T110I0123]> { + let Latency = 5; + let NumMicroOps = 3; +} + +// 6 cycles on LS0/LS1 and I0/I1/I2/I3. +def THX3T110Write_6Cyc_LS01_I012 : + SchedWriteRes<[THX3T110LS, THX3T110I0123]> { + let Latency = 6; + let NumMicroOps = 4; +} + +// 6 cycles on LS0/LS1 and 2 of I0/I1/I2/I3. +def THX3T110Write_6Cyc_LS01_I0123_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123, THX3T110I0123]> { + let Latency = 6; + let NumMicroOps = 3; +} + +// 1 cycle on LS0/LS1 and SD. +def THX3T110Write_1Cyc_LS01_SD : + SchedWriteRes<[THX3T110LS, THX3T110SD]> { + let Latency = 1; + let NumMicroOps = 2; +} + +// 2 cycles on LS0/LS1 and SD. +def THX3T110Write_2Cyc_LS01_SD : + SchedWriteRes<[THX3T110LS, THX3T110SD]> { + let Latency = 2; + let NumMicroOps = 2; +} + +// 4 cycles on LS0/LS1 and SD. +def THX3T110Write_4Cyc_LS01_SD : + SchedWriteRes<[THX3T110LS, THX3T110SD]> { + let Latency = 4; + let NumMicroOps = 3; +} + +// 5 cycles on LS0/LS1 and SD. +def THX3T110Write_5Cyc_LS01_SD : + SchedWriteRes<[THX3T110LS, THX3T110SD]> { + let Latency = 5; + let NumMicroOps = 4; +} + +// 6 cycles on LS0/LS1 and SD. +def THX3T110Write_6Cyc_LS01_SD : + SchedWriteRes<[THX3T110LS, THX3T110SD]> { + let Latency = 6; + let NumMicroOps = 5; +} + +// 1 cycle on LS0/LS1, SD and I0/I1/I2/I3. +def THX3T110Write_1Cyc_LS01_SD_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110SD, THX3T110I0123]> { + let Latency = 1; + let NumMicroOps = 2; +} + +// 2 cycles on LS0/LS1, SD and I0/I1/I2/I3. +def THX3T110Write_2Cyc_LS01_SD_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110SD, THX3T110I0123]> { + let Latency = 2; + let NumMicroOps = 2; +} + +// 4 cycles on LS0/LS1, SD and I0/I1/I2/I3. +def THX3T110Write_4Cyc_LS01_SD_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110SD, THX3T110I0123]> { + let Latency = 4; + let NumMicroOps = 3; +} + +// 5 cycles on LS0/LS1, SD and I0/I1/I2/I3. +def THX3T110Write_5Cyc_LS01_SD_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110SD, THX3T110I0123]> { + let Latency = 5; + let NumMicroOps = 4; +} + +// 6 cycles on LS0/LS1, SD and I0/I1/I2/I3. +def THX3T110Write_6Cyc_LS01_SD_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110SD, THX3T110I0123]> { + let Latency = 6; + let NumMicroOps = 5; +} + +// 1 cycles on LS0/LS1 and F0/F1/F2/F3. +def THX3T110Write_1Cyc_LS01_F0123 : + SchedWriteRes<[THX3T110LS, THX3T110FP0123]> { + let Latency = 1; + let NumMicroOps = 2; +} + +// 5 cycles on LS0/LS1 and F0/F1/F2/F3. +def THX3T110Write_5Cyc_LS01_F0123 : + SchedWriteRes<[THX3T110LS, THX3T110FP0123]> { + let Latency = 5; + let NumMicroOps = 3; +} + +// 6 cycles on LS0/LS1 and F0/F1/F2/F3. +def THX3T110Write_6Cyc_LS01_F0123 : + SchedWriteRes<[THX3T110LS, THX3T110FP0123]> { + let Latency = 6; + let NumMicroOps = 3; +} + +// 7 cycles on LS0/LS1 and F0/F1/F2/F3. +def THX3T110Write_7Cyc_LS01_F0123 : + SchedWriteRes<[THX3T110LS, THX3T110FP0123]> { + let Latency = 7; + let NumMicroOps = 3; +} + +// 8 cycles on LS0/LS1 and F0/F1/F2/F3. +def THX3T110Write_8Cyc_LS01_F0123 : + SchedWriteRes<[THX3T110LS, THX3T110FP0123]> { + let Latency = 8; + let NumMicroOps = 3; +} + +// 8 cycles on LS0/LS1 and I0/I1/I2/I3. +def THX3T110Write_8Cyc_LS01_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123]> { + let Latency = 8; + let NumMicroOps = 3; +} + +// 12 cycles on LS0/LS1 and I0/I1/I2/I3. +def THX3T110Write_12Cyc_LS01_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123]> { + let Latency = 12; + let NumMicroOps = 4; +} + +// 16 cycles on LS0/LS1 and I0/I1/I2/I3. +def THX3T110Write_16Cyc_LS01_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123]> { + let Latency = 16; + let NumMicroOps = 5; +} + +// 24 cycles on LS0/LS1 and I0/I1/I2/I3. +def THX3T110Write_24Cyc_LS01_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123]> { + let Latency = 24; + let NumMicroOps = 10; +} + +// 32 cycles on LS0/LS1 and I0/I1/I2/I3. +def THX3T110Write_32Cyc_LS01_I0123 : + SchedWriteRes<[THX3T110LS, THX3T110I0123]> { + let Latency = 32; + let NumMicroOps = 14; +} + +// 3 cycles on F0/F1/F2/F3. +def THX3T110Write_3Cyc_F0123 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 3; + let NumMicroOps = 2; +} + +// 4 cycles on F0/F1/F2/F3. +def THX3T110Write_4Cyc_F0123 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 4; + let NumMicroOps = 2; +} + +// 5 cycles on F0/F1/F2/F3. +def THX3T110Write_5Cyc_F0123 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 5; + let NumMicroOps = 2; +} + +// 10 cycles on F0/F1/F2/F3. +def THX3T110Write_10Cyc_F0123 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 10; + let NumMicroOps = 4; +} + +// 15 cycles on F0/F1/F2/F3. +def THX3T110Write_15Cyc_F0123 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 15; + let NumMicroOps = 7; +} + +// 16 cycles on F0/F1/F2/F3. +def THX3T110Write_16Cyc_F0123 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 16; + let NumMicroOps = 3; +} + +// 18 cycles on F0/F1/F2/F3. +def THX3T110Write_18Cyc_F0123 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 18; + let NumMicroOps = 3; +} + +// 19 cycles on F0/F1/F2/F3. +def THX3T110Write_19Cyc_F0123 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 19; + let NumMicroOps = 4; +} + +// 20 cycles on F0/F1/F2/F3. +def THX3T110Write_20Cyc_F0123 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 20; + let NumMicroOps = 4; +} + +// 23 cycles on F0/F1/F2/F3. +def THX3T110Write_23Cyc_F0123 : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 23; + let NumMicroOps = 4; +} + +// 3 cycles on F2/F3 and 4 cycles on F0/F1/F2/F3. +def THX3T110Write_3_4Cyc_F23_F0123 : + SchedWriteRes<[THX3T110FP23, THX3T110FP0123]> { + let Latency = 3; + let NumMicroOps = 2; + let ResourceCycles = [3, 4]; +} + + +// Define commonly used read types. + +// No forwarding is provided for these types. +def : ReadAdvance; +def : ReadAdvance; +def : ReadAdvance; +def : ReadAdvance; +def : ReadAdvance; +def : ReadAdvance; +def : ReadAdvance; +def : ReadAdvance; +def : ReadAdvance; + +//===----------------------------------------------------------------------===// +// 3. Instruction Tables. + +//--- +// 3.1 Branch Instructions +//--- + +// Branch, immed +// Branch and link, immed +// Compare and branch +def : WriteRes { + let Latency = 1; + let NumMicroOps = 2; +} + +// Branch, register +// Branch and link, register != LR +// Branch and link, register = LR +def : WriteRes { + let Latency = 1; + let NumMicroOps = 2; +} + +def : WriteRes { let Latency = 1; } +def : WriteRes { let Latency = 1; } +def : WriteRes { let Latency = 1; } + +def : WriteRes { + let Latency = 4; + let NumMicroOps = 2; +} + +//--- +// Branch +//--- +def : InstRW<[THX3T110Write_1Cyc_I23], (instrs B, BL, BR, BLR)>; +def : InstRW<[THX3T110Write_1Cyc_I23], (instrs Bcc)>; +def : InstRW<[THX3T110Write_1Cyc_I23], (instrs RET)>; +def : InstRW<[THX3T110Write_1Cyc_I23], + (instrs CBZW, CBZX, CBNZW, CBNZX, TBZW, TBZX, TBNZW, TBNZX)>; + +//--- +// 3.2 Arithmetic and Logical Instructions +// 3.3 Move and Shift Instructions +//--- + + +// ALU, basic +// Conditional compare +// Conditional select +// Address generation +def : WriteRes { + let Latency = 1; + let ResourceCycles = [1]; + let NumMicroOps = 2; +} + +def : InstRW<[WriteI], + (instregex "ADD?(W|X)r(i|r|s|x)", "ADDS?(W|X)r(i|r|s|x)(64)?", + "AND?(W|X)r(i|r|s|x)", "ANDS?(W|X)r(i|r|s|x)", + "ADC(W|X)r", + "BIC?(W|X)r(i|r|s|x)", "BICS?(W|X)r(i|r|s|x)", + "EON?(W|X)r(i|r|s|x)", "ORN?(W|X)r(i|r|s|x)", + "ORR?(W|X)r(i|r|s|x)", "SUB?(W|X)r(i|r|s|x)", + "SUBS?(W|X)r(i|r|s|x)", "SBC(W|X)r", + "SBCS(W|X)r", "CCMN(W|X)(i|r)", + "CCMP(W|X)(i|r)", "CSEL(W|X)r", + "CSINC(W|X)r", "CSINV(W|X)r", + "CSNEG(W|X)r")>; + +def : InstRW<[WriteI], (instrs COPY)>; + +// ALU, extend and/or shift +def : WriteRes { + let Latency = 2; + let ResourceCycles = [2]; + let NumMicroOps = 2; +} + +def : InstRW<[WriteISReg], + (instregex "ADD?(W|X)r(i|r|s|x)", "ADDS?(W|X)r(i|r|s|x)(64)?", + "AND?(W|X)r(i|r|s|x)", "ANDS?(W|X)r(i|r|s|x)", + "ADC(W|X)r", + "BIC?(W|X)r(i|r|s|x)", "BICS?(W|X)r(i|r|s|x)", + "EON?(W|X)r(i|r|s|x)", "ORN?(W|X)r(i|r|s|x)", + "ORR?(W|X)r(i|r|s|x)", "SUB?(W|X)r(i|r|s|x)", + "SUBS?(W|X)r(i|r|s|x)", "SBC(W|X)r", + "SBCS(W|X)r", "CCMN(W|X)(i|r)", + "CCMP(W|X)(i|r)", "CSEL(W|X)r", + "CSINC(W|X)r", "CSINV(W|X)r", + "CSNEG(W|X)r")>; + +def : WriteRes { + let Latency = 1; + let ResourceCycles = [1]; + let NumMicroOps = 2; +} + +def : InstRW<[WriteIEReg], + (instregex "ADD?(W|X)r(i|r|s|x)", "ADDS?(W|X)r(i|r|s|x)(64)?", + "AND?(W|X)r(i|r|s|x)", "ANDS?(W|X)r(i|r|s|x)", + "ADC(W|X)r", + "BIC?(W|X)r(i|r|s|x)", "BICS?(W|X)r(i|r|s|x)", + "EON?(W|X)r(i|r|s|x)", "ORN?(W|X)r(i|r|s|x)", + "ORR?(W|X)r(i|r|s|x)", "SUB?(W|X)r(i|r|s|x)", + "SUBS?(W|X)r(i|r|s|x)", "SBC(W|X)r", + "SBCS(W|X)r", "CCMN(W|X)(i|r)", + "CCMP(W|X)(i|r)", "CSEL(W|X)r", + "CSINC(W|X)r", "CSINV(W|X)r", + "CSNEG(W|X)r")>; + +// Move immed +def : WriteRes { + let Latency = 1; + let NumMicroOps = 2; +} + +def : InstRW<[THX3T110Write_1Cyc_I0123], + (instrs MOVKWi, MOVKXi, MOVNWi, MOVNXi, MOVZWi, MOVZXi)>; + +def : InstRW<[THX3T110Write_1Cyc_I0123], + (instrs ASRVWr, ASRVXr, LSLVWr, LSLVXr, RORVWr, RORVXr)>; + +// Variable shift +def : WriteRes { + let Latency = 1; + let NumMicroOps = 2; +} + +//--- +// 3.4 Divide and Multiply Instructions +//--- + +// Divide, W-form +// Latency range of 13-23/13-39. +def : WriteRes { + let Latency = 39; + let ResourceCycles = [39]; + let NumMicroOps = 4; +} + +// Divide, X-form +def : WriteRes { + let Latency = 23; + let ResourceCycles = [23]; + let NumMicroOps = 4; +} + +// Multiply accumulate, W-form +def : WriteRes { + let Latency = 5; + let NumMicroOps = 3; +} + +// Multiply accumulate, X-form +def : WriteRes { + let Latency = 5; + let NumMicroOps = 3; +} + +//def : InstRW<[WriteIM32, ReadIM, ReadIM, ReadIMA, THX3T110Write_5Cyc_I012], +// (instrs MADDWrrr, MSUBWrrr)>; +def : InstRW<[WriteIM32], (instrs MADDWrrr, MSUBWrrr)>; +def : InstRW<[WriteIM32], (instrs MADDXrrr, MSUBXrrr)>; +def : InstRW<[THX3T110Write_5Cyc_I0123], + (instregex "(S|U)(MADDL|MSUBL)rrr")>; + +def : InstRW<[WriteID32], (instrs SDIVWr, UDIVWr)>; +def : InstRW<[WriteID64], (instrs SDIVXr, UDIVXr)>; + +// Bitfield extract, two reg +def : WriteRes { + let Latency = 1; + let NumMicroOps = 2; +} + +// Multiply high +def : InstRW<[THX3T110Write_4Cyc_I1], (instrs SMULHrr, UMULHrr)>; + +// Miscellaneous Data-Processing Instructions +// Bitfield extract +def : InstRW<[THX3T110Write_1Cyc_I0123], (instrs EXTRWrri, EXTRXrri)>; + +// Bitifield move - basic +def : InstRW<[THX3T110Write_1Cyc_I0123], + (instrs SBFMWri, SBFMXri, UBFMWri, UBFMXri)>; + +// Bitfield move, insert +def : InstRW<[THX3T110Write_1Cyc_I0123], (instregex "^BFM")>; +def : InstRW<[THX3T110Write_1Cyc_I0123], (instregex "(S|U)?BFM.*")>; + +// Count leading +def : InstRW<[THX3T110Write_3_4Cyc_F23_F0123], + (instregex "^CLS(W|X)r$", "^CLZ(W|X)r$")>; + +// Reverse bits +def : InstRW<[THX3T110Write_3_4Cyc_F23_F0123], (instrs RBITWr, RBITXr)>; + +// Cryptography Extensions +def : InstRW<[THX3T110Write_4Cyc_F0123], (instregex "^AES[DE]")>; +def : InstRW<[THX3T110Write_4Cyc_F0123], (instregex "^AESI?MC")>; +def : InstRW<[THX3T110Write_4Cyc_F0123], (instregex "^PMULL")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^SHA1SU0")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^SHA1(H|SU1)")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^SHA1[CMP]")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^SHA256SU0")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^SHA256(H|H2|SU1)")>; + +// CRC Instructions +// def : InstRW<[THX3T110Write_4Cyc_I1], (instregex "^CRC32", "^CRC32C")>; +def : InstRW<[THX3T110Write_4Cyc_I1], + (instrs CRC32Brr, CRC32Hrr, CRC32Wrr, CRC32Xrr)>; + +def : InstRW<[THX3T110Write_4Cyc_I1], + (instrs CRC32CBrr, CRC32CHrr, CRC32CWrr, CRC32CXrr)>; + +// Reverse bits/bytes +// NOTE: Handled by WriteI. + +//--- +// 3.6 Load Instructions +// 3.10 FP Load Instructions +//--- + +// Load register, literal +// Load register, unscaled immed +// Load register, immed unprivileged +// Load register, unsigned immed +def : WriteRes { + let Latency = 4; + let NumMicroOps = 4; +} + +// Load register, immed post-index +// NOTE: Handled by WriteLD, WriteI. +// Load register, immed pre-index +// NOTE: Handled by WriteLD, WriteAdr. +def : WriteRes { + let Latency = 1; + let NumMicroOps = 2; +} + +// Load pair, immed offset, normal +// Load pair, immed offset, signed words, base != SP +// Load pair, immed offset signed words, base = SP +// LDP only breaks into *one* LS micro-op. Thus +// the resources are handled by WriteLD. +def : WriteRes { + let Latency = 4; + let NumMicroOps = 4; +} + +// Load register offset, basic +// Load register, register offset, scale by 4/8 +// Load register, register offset, scale by 2 +// Load register offset, extend +// Load register, register offset, extend, scale by 4/8 +// Load register, register offset, extend, scale by 2 +def THX3T110WriteLDIdx : SchedWriteVariant<[ + SchedVar, + SchedVar]>; +def : SchedAlias; + +def THX3T110ReadAdrBase : SchedReadVariant<[ + SchedVar, + SchedVar]>; +def : SchedAlias; + +// Load pair, immed pre-index, normal +// Load pair, immed pre-index, signed words +// Load pair, immed post-index, normal +// Load pair, immed post-index, signed words +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, WriteLDHi], (instrs LDNPDi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, WriteLDHi], (instrs LDNPQi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, WriteLDHi], (instrs LDNPSi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, WriteLDHi], (instrs LDNPWi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, WriteLDHi], (instrs LDNPXi)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, WriteLDHi], (instrs LDPDi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, WriteLDHi], (instrs LDPQi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, WriteLDHi], (instrs LDPSi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, WriteLDHi], (instrs LDPSWi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, WriteLDHi], (instrs LDPWi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, WriteLDHi], (instrs LDPXi)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDRBui)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDRDui)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDRHui)>; +def : InstRW<[THX3T110Write_5Cyc_LS01], (instrs LDRQui)>; +def : InstRW<[THX3T110Write_5Cyc_LS01], (instrs LDRSui)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDRDl)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDRQl)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDRWl)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDRXl)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDTRBi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDTRHi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDTRWi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDTRXi)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDTRSBWi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDTRSBXi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDTRSHWi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDTRSHXi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDTRSWi)>; + +def : InstRW<[THX3T110Write_5Cyc_LS01_I0123, WriteLDHi, WriteAdr], + (instrs LDPDpre)>; +def : InstRW<[THX3T110Write_5Cyc_LS01_I0123, WriteLDHi, WriteAdr], + (instrs LDPQpre)>; +def : InstRW<[THX3T110Write_5Cyc_LS01_I0123, WriteLDHi, WriteAdr], + (instrs LDPSpre)>; +def : InstRW<[THX3T110Write_5Cyc_LS01_I0123, WriteLDHi, WriteAdr], + (instrs LDPWpre)>; +def : InstRW<[THX3T110Write_5Cyc_LS01_I0123, WriteLDHi, WriteAdr], + (instrs LDPWpre)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01, WriteAdr], + (instrs LDRBpre, LDRDpre, LDRHpre, LDRQpre, + LDRSpre, LDRWpre, LDRXpre, + LDRSBWpre, LDRSBXpre, LDRSBWpost, LDRSBXpost, + LDRSHWpre, LDRSHXpre, LDRSHWpost, LDRSHXpost, + LDRBBpre, LDRBBpost, LDRHHpre, LDRHHpost)>; + +def : InstRW<[THX3T110Write_5Cyc_LS01_I0123, WriteLDHi, WriteAdr], + (instrs LDPDpost, LDPQpost, LDPSpost, LDPWpost, LDPXpost)>; + +def : InstRW<[THX3T110Write_5Cyc_LS01_I0123, WriteI], + (instrs LDRBpost, LDRDpost, LDRHpost, + LDRQpost, LDRSpost, LDRWpost, LDRXpost)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123_I0123, WriteLDHi, WriteAdr], + (instrs LDPDpre, LDPQpre, LDPSpre, LDPWpre, LDPXpre)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123_I0123, WriteAdr], + (instrs LDRBpre, LDRDpre, LDRHpre, LDRQpre, + LDRSpre, LDRWpre, LDRXpre)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123_I0123, WriteLDHi, WriteAdr], + (instrs LDPDpost, LDPQpost, LDPSpost, LDPWpost, LDPXpost)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123_I0123, WriteI], + (instrs LDRBpost, LDRDpost, LDRHpost, LDRQpost, + LDRSpost, LDRWpost, LDRXpost)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRBroW)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRDroW)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRHroW)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRHHroW)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRQroW)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRSroW)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRSHWroW)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRSHXroW)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRWroW)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRXroW)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRBroX)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRDroX)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRHHroX)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRHroX)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRQroX)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRSroX)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRSHWroX)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRSHXroX)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRWroX)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_I0123, ReadAdrBase], (instrs LDRXroX)>; + +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURBi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURBBi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURDi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURHi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURHHi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURQi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURSi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURXi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURSBWi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURSBXi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURSHWi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURSHXi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instrs LDURSWi)>; + +// Load exclusive +def : InstRW<[THX3T110Write_4Cyc_LS01], (instregex "^LDAR(B|H|W|X)$")>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instregex "^LDAXR(B|H|W|X)$")>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instregex "^LDXR(B|H|W|X)$")>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instregex "^LDAXP(W|X)$")>; +def : InstRW<[THX3T110Write_4Cyc_LS01], (instregex "^LDXP(W|X)$")>; + +//--- +// Prefetch +//--- +def : InstRW<[THX3T110Write_6Cyc_LS01_I012], (instrs PRFMl)>; +def : InstRW<[THX3T110Write_6Cyc_LS01_I012], (instrs PRFUMi)>; +def : InstRW<[THX3T110Write_6Cyc_LS01_I012], (instrs PRFMui)>; +def : InstRW<[THX3T110Write_6Cyc_LS01_I012], (instrs PRFMroW)>; +def : InstRW<[THX3T110Write_6Cyc_LS01_I012], (instrs PRFMroX)>; + +//-- +// 3.7 Store Instructions +// 3.11 FP Store Instructions +//-- + +// Store register, unscaled immed +// Store register, immed unprivileged +// Store register, unsigned immed +def : WriteRes { + let Latency = 1; + let NumMicroOps = 2; +} + +// Store register, immed post-index +// NOTE: Handled by WriteAdr, WriteST, ReadAdrBase + +// Store register, immed pre-index +// NOTE: Handled by WriteAdr, WriteST + +// Store register, register offset, basic +// Store register, register offset, scaled by 4/8 +// Store register, register offset, scaled by 2 +// Store register, register offset, extend +// Store register, register offset, extend, scale by 4/8 +// Store register, register offset, extend, scale by 1 +def : WriteRes { + let Latency = 1; + let NumMicroOps = 2; +} + +// Store pair, immed offset, W-form +// Store pair, immed offset, X-form +def : WriteRes { + let Latency = 1; + let NumMicroOps = 2; +} + +// Store pair, immed post-index, W-form +// Store pair, immed post-index, X-form +// Store pair, immed pre-index, W-form +// Store pair, immed pre-index, X-form +// NOTE: Handled by WriteAdr, WriteSTP. +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STURBi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STURBBi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STURDi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STURHi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STURHHi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STURQi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STURSi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STURWi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STURXi)>; + +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_SD], (instrs STTRBi)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_SD], (instrs STTRHi)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_SD], (instrs STTRWi)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_SD], (instrs STTRXi)>; + +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STNPDi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STNPQi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STNPXi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STNPWi)>; + +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STPDi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STPQi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STPXi)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_SD], (instrs STPWi)>; + +def : InstRW<[THX3T110Write_1Cyc_LS01_I0123], (instrs STRBui)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_I0123], (instrs STRDui)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_I0123], (instrs STRHui)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_I0123], (instrs STRQui)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_I0123], (instrs STRXui)>; +def : InstRW<[THX3T110Write_1Cyc_LS01_I0123], (instrs STRWui)>; + +def : InstRW<[WriteSTP, THX3T110Write_1Cyc_LS01_SD], (instrs STRBui)>; +def : InstRW<[WriteSTP, THX3T110Write_1Cyc_LS01_SD], (instrs STRDui)>; +def : InstRW<[WriteSTP, THX3T110Write_1Cyc_LS01_SD], (instrs STRHui)>; +def : InstRW<[WriteSTP, THX3T110Write_1Cyc_LS01_SD], (instrs STRQui)>; +def : InstRW<[WriteSTP, THX3T110Write_1Cyc_LS01_SD], (instrs STRXui)>; +def : InstRW<[WriteSTP, THX3T110Write_1Cyc_LS01_SD], (instrs STRWui)>; + +def : InstRW<[WriteSTIdx, THX3T110Write_1Cyc_LS01_SD_I0123], (instrs STRBui)>; +def : InstRW<[WriteSTIdx, THX3T110Write_1Cyc_LS01_SD_I0123], (instrs STRDui)>; +def : InstRW<[WriteSTIdx, THX3T110Write_1Cyc_LS01_SD_I0123], (instrs STRHui)>; +def : InstRW<[WriteSTIdx, THX3T110Write_1Cyc_LS01_SD_I0123], (instrs STRQui)>; +def : InstRW<[WriteSTIdx, THX3T110Write_1Cyc_LS01_SD_I0123], (instrs STRXui)>; +def : InstRW<[WriteSTIdx, THX3T110Write_1Cyc_LS01_SD_I0123], (instrs STRWui)>; + +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STPDpre, STPDpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STPDpre, STPDpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STPQpre, STPQpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STPQpre, STPQpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STPSpre, STPSpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STPSpre, STPSpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STPWpre, STPWpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STPWpre, STPWpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STPXpre, STPXpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STPXpre, STPXpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STRBpre, STRBpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRBpre, STRBpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STRBBpre, STRBBpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRBBpre, STRBBpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STRDpre, STRDpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRDpre, STRDpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STRHpre, STRHpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRHpre, STRHpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STRHHpre, STRHHpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRHHpre, STRHHpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STRQpre, STRQpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRQpre, STRQpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STRSpre, STRSpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRSpre, STRSpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STRWpre, STRWpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRWpre, STRWpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123], + (instrs STRXpre, STRXpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRXpre, STRXpost)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRBroW, STRBroX)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRBBroW, STRBBroX)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRDroW, STRDroX)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRHroW, STRHroX)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRHHroW, STRHHroX)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRQroW, STRQroX)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRSroW, STRSroX)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRWroW, STRWroX)>; +def : InstRW<[WriteAdr, THX3T110Write_1Cyc_LS01_I0123, ReadAdrBase], + (instrs STRXroW, STRXroX)>; + +// Store exclusive +def : InstRW<[THX3T110Write_4Cyc_LS01_SD], (instrs STNPWi, STNPXi)>; +def : InstRW<[THX3T110Write_4Cyc_LS01_SD], (instregex "^STLR(B|H|W|X)$")>; +def : InstRW<[THX3T110Write_4Cyc_LS01_SD], (instregex "^STXP(W|X)$")>; +def : InstRW<[THX3T110Write_4Cyc_LS01_SD], (instregex "^STXR(B|H|W|X)$")>; +def : InstRW<[THX3T110Write_4Cyc_LS01_SD], (instregex "^STLXP(W|X)$")>; +def : InstRW<[THX3T110Write_4Cyc_LS01_SD], (instregex "^STLXR(B|H|W|X)$")>; + +//--- +// 3.8 FP Data Processing Instructions +//--- + +// FP absolute value +// FP min/max +// FP negate +def : WriteRes { + let Latency = 5; + let NumMicroOps = 2; +} + +// FP arithmetic +def : InstRW<[THX3T110Write_6Cyc_F01], (instregex "^FADD", "^FSUB")>; + +// FP compare +def : WriteRes { + let Latency = 5; + let NumMicroOps = 2; +} + +// FP Mul, Div, Sqrt +def : WriteRes { + let Latency = 22; + let ResourceCycles = [19]; +} + +def THX3T110XWriteFDiv : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 16; + let ResourceCycles = [8]; + let NumMicroOps = 4; +} + +def THX3T110XWriteFDivSP : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 16; + let ResourceCycles = [8]; + let NumMicroOps = 4; +} + +def THX3T110XWriteFDivDP : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 23; + let ResourceCycles = [12]; + let NumMicroOps = 4; +} + +def THX3T110XWriteFSqrtSP : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 16; + let ResourceCycles = [8]; + let NumMicroOps = 4; +} + +def THX3T110XWriteFSqrtDP : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 23; + let ResourceCycles = [12]; + let NumMicroOps = 4; +} + +// FP divide, S-form +// FP square root, S-form +def : InstRW<[THX3T110XWriteFDivSP], (instrs FDIVSrr)>; +def : InstRW<[THX3T110XWriteFSqrtSP], (instrs FSQRTSr)>; +def : InstRW<[THX3T110XWriteFDivSP], (instregex "^FDIVv.*32$")>; +def : InstRW<[THX3T110XWriteFSqrtSP], (instregex "^.*SQRT.*32$")>; +def : InstRW<[THX3T110Write_16Cyc_F01], (instregex "^FDIVSrr", "^FSQRTSr")>; + +// FP divide, D-form +// FP square root, D-form +def : InstRW<[THX3T110XWriteFDivDP], (instrs FDIVDrr)>; +def : InstRW<[THX3T110XWriteFSqrtDP], (instrs FSQRTDr)>; +def : InstRW<[THX3T110XWriteFDivDP], (instregex "^FDIVv.*64$")>; +def : InstRW<[THX3T110XWriteFSqrtDP], (instregex "^.*SQRT.*64$")>; +def : InstRW<[THX3T110Write_23Cyc_F01], (instregex "^FDIVDrr", "^FSQRTDr")>; + +// FP multiply +// FP multiply accumulate +def : WriteRes { + let Latency = 6; + let ResourceCycles = [2]; + let NumMicroOps = 3; +} + +def THX3T110XWriteFMul : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 6; + let ResourceCycles = [2]; + let NumMicroOps = 3; +} + +def THX3T110XWriteFMulAcc : SchedWriteRes<[THX3T110FP0123]> { + let Latency = 6; + let ResourceCycles = [2]; + let NumMicroOps = 3; +} + +def : InstRW<[THX3T110XWriteFMul], (instregex "^FMUL", "^FNMUL")>; +def : InstRW<[THX3T110XWriteFMulAcc], + (instregex "^FMADD", "^FMSUB", "^FNMADD", "^FNMSUB")>; + +// FP round to integral +def : InstRW<[THX3T110Write_7Cyc_F01], + (instregex "^FRINT(A|I|M|N|P|X|Z)(Sr|Dr)")>; + +// FP select +def : InstRW<[THX3T110Write_3_4Cyc_F23_F0123], (instregex "^FCSEL")>; + +//--- +// 3.9 FP Miscellaneous Instructions +//--- + +// FP convert, from vec to vec reg +// FP convert, from gen to vec reg +// FP convert, from vec to gen reg +def : WriteRes { + let Latency = 7; + let NumMicroOps = 3; +} + +// FP move, immed +// FP move, register +def : WriteRes { + let Latency = 4; + let NumMicroOps = 2; +} + +// FP transfer, from gen to vec reg +// FP transfer, from vec to gen reg +def : WriteRes { + let Latency = 4; + let NumMicroOps = 2; +} + +def : InstRW<[THX3T110Write_5Cyc_F01], (instrs FMOVXDHighr, FMOVDXHighr)>; + +//--- +// 3.12 ASIMD Integer Instructions +//--- + +// ASIMD absolute diff, D-form +// ASIMD absolute diff, Q-form +// ASIMD absolute diff accum, D-form +// ASIMD absolute diff accum, Q-form +// ASIMD absolute diff accum long +// ASIMD absolute diff long +// ASIMD arith, basic +// ASIMD arith, complex +// ASIMD compare +// ASIMD logical (AND, BIC, EOR) +// ASIMD max/min, basic +// ASIMD max/min, reduce, 4H/4S +// ASIMD max/min, reduce, 8B/8H +// ASIMD max/min, reduce, 16B +// ASIMD multiply, D-form +// ASIMD multiply, Q-form +// ASIMD multiply accumulate long +// ASIMD multiply accumulate saturating long +// ASIMD multiply long +// ASIMD pairwise add and accumulate +// ASIMD shift accumulate +// ASIMD shift by immed, basic +// ASIMD shift by immed and insert, basic, D-form +// ASIMD shift by immed and insert, basic, Q-form +// ASIMD shift by immed, complex +// ASIMD shift by register, basic, D-form +// ASIMD shift by register, basic, Q-form +// ASIMD shift by register, complex, D-form +// ASIMD shift by register, complex, Q-form +def : WriteRes { + let Latency = 5; + let NumMicroOps = 4; + let ResourceCycles = [4]; +} + +// ASIMD arith, reduce, 4H/4S +// ASIMD arith, reduce, 8B/8H +// ASIMD arith, reduce, 16B + +// ASIMD logical (MVN (alias for NOT), ORN, ORR) +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^ANDv", "^BICv", "^EORv", "^ORRv", "^ORNv", "^NOTv")>; + +// ASIMD arith, reduce +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^ADDVv", "^SADDLVv", "^UADDLVv")>; + +// ASIMD polynomial (8x8) multiply long +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^(S|U|SQD)MULL")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "(S|U|SQD)(MLAL|MLSL|MULL)v.*")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^PMULL(v8i8|v16i8)")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^PMULL(v1i64|v2i64)")>; + +// ASIMD absolute diff accum, D-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^[SU]ABA(v8i8|v4i16|v2i32)$")>; +// ASIMD absolute diff accum, Q-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^[SU]ABA(v16i8|v8i16|v4i32)$")>; +// ASIMD absolute diff accum long +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^[SU]ABAL")>; +// ASIMD arith, reduce, 4H/4S +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^[SU]?ADDL?V(v8i8|v4i16|v2i32)v$")>; +// ASIMD arith, reduce, 8B +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^[SU]?ADDL?V(v8i16|v4i32)v$")>; +// ASIMD arith, reduce, 16B/16H +def : InstRW<[THX3T110Write_10Cyc_F0123], + (instregex "^[SU]?ADDL?Vv16i8v$")>; +// ASIMD max/min, reduce, 4H/4S +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^[SU](MIN|MAX)V(v4i16|v4i32)v$")>; +// ASIMD max/min, reduce, 8B/8H +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^[SU](MIN|MAX)V(v8i8|v8i16)v$")>; +// ASIMD max/min, reduce, 16B/16H +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^[SU](MIN|MAX)Vv16i8v$")>; +// ASIMD multiply, D-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^(P?MUL|SQR?DMULH)" # + "(v8i8|v4i16|v2i32|v1i8|v1i16|v1i32|v1i64)" # + "(_indexed)?$")>; +// ASIMD multiply, Q-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^(P?MUL|SQR?DMULH)(v16i8|v8i16|v4i32)(_indexed)?$")>; +// ASIMD multiply accumulate, D-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^ML[AS](v8i8|v4i16|v2i32)(_indexed)?$")>; +// ASIMD multiply accumulate, Q-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^ML[AS](v16i8|v8i16|v4i32)(_indexed)?$")>; +// ASIMD shift accumulate +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "SRSRAv","SSRAv","URSRAv","USRAv")>; + +// ASIMD shift by immed, basic +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "RSHRNv","SHRNv", "SQRSHRNv","SQRSHRUNv", + "SQSHRNv","SQSHRUNv", "UQRSHRNv", + "UQSHRNv","SQXTNv","SQXTUNv","UQXTNv")>; +// ASIMD shift by immed, complex +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^[SU]?(Q|R){1,2}SHR")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^SQSHLU")>; +// ASIMD shift by register, basic, Q-form +def : InstRW<[THX3T110Write_5Cyc_F01], + (instregex "^[SU]SHL(v16i8|v8i16|v4i32|v2i64)")>; +// ASIMD shift by register, complex, D-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^[SU][QR]{1,2}SHL" # + "(v1i8|v1i16|v1i32|v1i64|v8i8|v4i16|v2i32|b|d|h|s)")>; +// ASIMD shift by register, complex, Q-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^[SU][QR]{1,2}SHL(v16i8|v8i16|v4i32|v2i64)")>; + +// ASIMD Arithmetic +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "(ADD|SUB)(v8i8|v4i16|v2i32|v1i64)")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "(ADD|SUB)(v16i8|v8i16|v4i32|v2i64)")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "(ADD|SUB)HNv.*")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "(RADD|RSUB)HNv.*")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^SQADD", "^SQNEG", "^SQSUB", "^SRHADD", + "^SUQADD", "^UQADD", "^UQSUB", "^URHADD", "^USQADD")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "ADDP(v16i8|v8i16|v4i32|v2i64)")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "((AND|ORN|EOR|EON)S?(Xr[rsi]|v16i8|v8i16|v4i32)|" # + "(ORR|BIC)S?(Xr[rs]|v16i8|v8i16|v4i32))")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "(CLS|CLZ|CNT)(v4i32|v8i16|v16i8)")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^SADALP","^UADALP")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^SADDLPv","^UADDLPv")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^SADDLV","^UADDLV")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^ADDVv","^SMAXVv","^UMAXVv","^SMINVv","^UMINVv")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^SABAv","^UABAv","^SABALv","^UABALv")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^SQADDv","^SQSUBv","^UQADDv","^UQSUBv")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^SUQADDv","^USQADDv")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^ADDHNv","^RADDHNv", "^RSUBHNv", + "^SQABS", "^SQADD", "^SQNEG", "^SQSUB", + "^SRHADD", "^SUBHNv", "^SUQADD", + "^UQADD", "^UQSUB", "^URHADD", "^USQADD")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^CMEQv","^CMGEv","^CMGTv", + "^CMLEv","^CMLTv", "^CMHIv","^CMHSv")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^SMAXv","^SMINv","^UMAXv","^UMINv", + "^SMAXPv","^SMINPv","^UMAXPv","^UMINPv")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^SABDv","^UABDv", "^SABDLv","^UABDLv")>; + +//--- +// 3.13 ASIMD Floating-point Instructions +//--- + +// ASIMD FP absolute value +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^FABSv")>; + +// ASIMD FP arith, normal, D-form +// ASIMD FP arith, normal, Q-form +def : InstRW<[THX3T110Write_3_4Cyc_F23_F0123], + (instregex "^FABDv", "^FADDv", "^FSUBv")>; + +// ASIMD FP arith,pairwise, D-form +// ASIMD FP arith, pairwise, Q-form +def : InstRW<[THX3T110Write_3_4Cyc_F23_F0123], (instregex "^FADDPv")>; + +// ASIMD FP compare, D-form +// ASIMD FP compare, Q-form +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^FACGEv", "^FACGTv")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^FCMEQv", "^FCMGEv", + "^FCMGTv", "^FCMLEv", + "^FCMLTv")>; + +// ASIMD FP round, D-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^FRINT[AIMNPXZ](v2f32)")>; +// ASIMD FP round, Q-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^FRINT[AIMNPXZ](v4f32|v2f64)")>; + +// ASIMD FP convert, long +// ASIMD FP convert, narrow +// ASIMD FP convert, other, D-form +// ASIMD FP convert, other, Q-form +// NOTE: Handled by WriteV. + +// ASIMD FP convert, long and narrow +def : InstRW<[THX3T110Write_5Cyc_F01], (instregex "^FCVT(L|N|XN)v")>; +// ASIMD FP convert, other, D-form +def : InstRW<[THX3T110Write_5Cyc_F01], + (instregex "^[FVSU]CVT([AMNPZ][SU])?(_Int)?(v2f32|v1i32|v2i32|v1i64)")>; +// ASIMD FP convert, other, Q-form +def : InstRW<[THX3T110Write_5Cyc_F01], + (instregex "^[FVSU]CVT([AMNPZ][SU])?(_Int)?(v4f32|v2f64|v4i32|v2i64)")>; + +// ASIMD FP divide, D-form, F32 +def : InstRW<[THX3T110Write_16Cyc_F0123], (instrs FDIVv2f32)>; +def : InstRW<[THX3T110Write_16Cyc_F0123], (instregex "FDIVv2f32")>; + +// ASIMD FP divide, Q-form, F32 +def : InstRW<[THX3T110Write_16Cyc_F0123], (instrs FDIVv4f32)>; +def : InstRW<[THX3T110Write_16Cyc_F0123], (instregex "FDIVv4f32")>; + +// ASIMD FP divide, Q-form, F64 +def : InstRW<[THX3T110Write_23Cyc_F0123], (instrs FDIVv2f64)>; +def : InstRW<[THX3T110Write_23Cyc_F0123], (instregex "FDIVv2f64")>; + +// ASIMD FP max/min, normal, D-form +// ASIMD FP max/min, normal, Q-form +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^FMAXv", "^FMAXNMv", + "^FMINv", "^FMINNMv")>; + +// ASIMD FP max/min, pairwise, D-form +// ASIMD FP max/min, pairwise, Q-form +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^FMAXPv", "^FMAXNMPv", + "^FMINPv", "^FMINNMPv")>; + +// ASIMD FP max/min, reduce +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^FMAXVv", "^FMAXNMVv", + "^FMINVv", "^FMINNMVv")>; + +// ASIMD FP multiply, D-form, FZ +// ASIMD FP multiply, D-form, no FZ +// ASIMD FP multiply, Q-form, FZ +// ASIMD FP multiply, Q-form, no FZ +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^FMULv", "^FMULXv")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^FMULX?(v2f32|v1i32|v2i32|v1i64|32|64)")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^FMULX?(v4f32|v2f64|v4i32|v2i64)")>; + +// ASIMD FP multiply accumulate, Dform, FZ +// ASIMD FP multiply accumulate, Dform, no FZ +// ASIMD FP multiply accumulate, Qform, FZ +// ASIMD FP multiply accumulate, Qform, no FZ +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^FMLAv", "^FMLSv")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^FML[AS](v2f32|v1i32|v2i32|v1i64)")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^FML[AS](v4f32|v2f64|v4i32|v2i64)")>; + +// ASIMD FP negate +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^FNEGv")>; + +//-- +// 3.14 ASIMD Miscellaneous Instructions +//-- + +// ASIMD bit reverse +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^RBITv")>; + +// ASIMD bitwise insert, D-form +// ASIMD bitwise insert, Q-form +def : InstRW<[THX3T110Write_3_4Cyc_F23_F0123], + (instregex "^BIFv", "^BITv", "^BSLv")>; + +// ASIMD count, D-form +// ASIMD count, Q-form +def : InstRW<[THX3T110Write_3_4Cyc_F23_F0123], + (instregex "^CLSv", "^CLZv", "^CNTv")>; + +// ASIMD duplicate, gen reg +// ASIMD duplicate, element +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^DUPv")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^CPY")>; +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^DUPv.+gpr")>; + +// ASIMD extract +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^EXTv")>; + +// ASIMD extract narrow +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^XTNv")>; + +// ASIMD extract narrow, saturating +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^SQXTNv", "^SQXTUNv", "^UQXTNv")>; + +// ASIMD insert, element to element +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^INSv")>; + +// ASIMD transfer, element to gen reg +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^[SU]MOVv")>; + +// ASIMD move, integer immed +def : InstRW<[THX3T110Write_3_4Cyc_F23_F0123], (instregex "^MOVIv")>; + +// ASIMD move, FP immed +def : InstRW<[THX3T110Write_3_4Cyc_F23_F0123], (instregex "^FMOVv")>; + +// ASIMD transpose +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^TRN1", "^TRN2")>; + +// ASIMD unzip/zip +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^UZP1", "^UZP2", "^ZIP1", "^ZIP2")>; + +// ASIMD reciprocal estimate, D-form +// ASIMD reciprocal estimate, Q-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^FRECPEv", "^FRECPXv", "^URECPEv", + "^FRSQRTEv", "^URSQRTEv")>; + +// ASIMD reciprocal step, D-form, FZ +// ASIMD reciprocal step, D-form, no FZ +// ASIMD reciprocal step, Q-form, FZ +// ASIMD reciprocal step, Q-form, no FZ +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^FRECPSv", "^FRSQRTSv")>; + +// ASIMD reverse +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^REV16v", "^REV32v", "^REV64v")>; + +// ASIMD table lookup, D-form +// ASIMD table lookup, Q-form +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instrs TBLv8i8One, TBLv16i8One, TBXv8i8One, TBXv16i8One)>; +def : InstRW<[THX3T110Write_10Cyc_F0123], + (instrs TBLv8i8Two, TBLv16i8Two, TBXv8i8Two, TBXv16i8Two)>; +def : InstRW<[THX3T110Write_15Cyc_F0123], + (instrs TBLv8i8Three, TBLv16i8Three, TBXv8i8Three, TBXv16i8Three)>; +def : InstRW<[THX3T110Write_20Cyc_F0123], + (instrs TBLv8i8Four, TBLv16i8Four, TBXv8i8Four, TBXv16i8Four)>; + +// ASIMD transfer, element to word or word +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^[SU]MOVv")>; + +// ASIMD transfer, element to gen reg +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "(S|U)MOVv.*")>; + +// ASIMD transfer gen reg to element +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^INSv")>; + +// ASIMD transpose +def : InstRW<[THX3T110Write_5Cyc_F0123], + (instregex "^TRN1v", "^TRN2v", "^UZP1v", "^UZP2v")>; + +// ASIMD unzip/zip +def : InstRW<[THX3T110Write_5Cyc_F0123], (instregex "^ZIP1v", "^ZIP2v")>; + +//-- +// 3.15 ASIMD Load Instructions +//-- + +// ASIMD load, 1 element, multiple, 1 reg, D-form +// ASIMD load, 1 element, multiple, 1 reg, Q-form +def : InstRW<[THX3T110Write_4Cyc_LS01], + (instregex "^LD1Onev(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_4Cyc_LS01, WriteAdr], + (instregex "^LD1Onev(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +// ASIMD load, 1 element, multiple, 2 reg, D-form +// ASIMD load, 1 element, multiple, 2 reg, Q-form +def : InstRW<[THX3T110Write_4Cyc_LS01], + (instregex "^LD1Twov(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_4Cyc_LS01, WriteAdr], + (instregex "^LD1Twov(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +// ASIMD load, 1 element, multiple, 3 reg, D-form +// ASIMD load, 1 element, multiple, 3 reg, Q-form +def : InstRW<[THX3T110Write_5Cyc_LS01], + (instregex "^LD1Threev(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_5Cyc_LS01, WriteAdr], + (instregex "^LD1Threev(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +// ASIMD load, 1 element, multiple, 4 reg, D-form +// ASIMD load, 1 element, multiple, 4 reg, Q-form +def : InstRW<[THX3T110Write_6Cyc_LS01], + (instregex "^LD1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_6Cyc_LS01, WriteAdr], + (instregex "^LD1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +// ASIMD load, 1 element, one lane, B/H/S +// ASIMD load, 1 element, one lane, D +def : InstRW<[THX3T110Write_5Cyc_LS01_F0123], + (instregex "^LD1i(8|16|32|64)$")>; +def : InstRW<[THX3T110Write_5Cyc_LS01_F0123, WriteAdr], + (instregex "^LD1i(8|16|32|64)_POST$")>; + +// ASIMD load, 1 element, all lanes, D-form, B/H/S +// ASIMD load, 1 element, all lanes, D-form, D +// ASIMD load, 1 element, all lanes, Q-form +def : InstRW<[THX3T110Write_5Cyc_LS01_F0123], + (instregex "^LD1Rv(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_5Cyc_LS01_F0123, WriteAdr], + (instregex "^LD1Rv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +// ASIMD load, 2 element, multiple, D-form, B/H/S +// ASIMD load, 2 element, multiple, Q-form, D +def : InstRW<[THX3T110Write_5Cyc_LS01_F0123], + (instregex "^LD2Twov(8b|4h|2s|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_5Cyc_LS01_F0123, WriteAdr], + (instregex "^LD2Twov(8b|4h|2s|16b|8h|4s|2d)_POST$")>; + +// ASIMD load, 2 element, one lane, B/H +// ASIMD load, 2 element, one lane, S +// ASIMD load, 2 element, one lane, D +def : InstRW<[THX3T110Write_5Cyc_LS01_F0123], + (instregex "^LD2i(8|16|32|64)$")>; +def : InstRW<[THX3T110Write_5Cyc_LS01_F0123, WriteAdr], + (instregex "^LD2i(8|16|32|64)_POST$")>; + +// ASIMD load, 2 element, all lanes, D-form, B/H/S +// ASIMD load, 2 element, all lanes, D-form, D +// ASIMD load, 2 element, all lanes, Q-form +def : InstRW<[THX3T110Write_5Cyc_LS01_F0123], + (instregex "^LD2Rv(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_5Cyc_LS01_F0123, WriteAdr], + (instregex "^LD2Rv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +// ASIMD load, 3 element, multiple, D-form, B/H/S +// ASIMD load, 3 element, multiple, Q-form, B/H/S +// ASIMD load, 3 element, multiple, Q-form, D +def : InstRW<[THX3T110Write_8Cyc_LS01_F0123], + (instregex "^LD3Threev(8b|4h|2s|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_8Cyc_LS01_F0123, WriteAdr], + (instregex "^LD3Threev(8b|4h|2s|16b|8h|4s|2d)_POST$")>; + +// ASIMD load, 3 element, one lone, B/H +// ASIMD load, 3 element, one lane, S +// ASIMD load, 3 element, one lane, D +def : InstRW<[THX3T110Write_7Cyc_LS01_F0123], + (instregex "^LD3i(8|16|32|64)$")>; +def : InstRW<[THX3T110Write_7Cyc_LS01_F0123, WriteAdr], + (instregex "^LD3i(8|16|32|64)_POST$")>; + +// ASIMD load, 3 element, all lanes, D-form, B/H/S +// ASIMD load, 3 element, all lanes, D-form, D +// ASIMD load, 3 element, all lanes, Q-form, B/H/S +// ASIMD load, 3 element, all lanes, Q-form, D +def : InstRW<[THX3T110Write_7Cyc_LS01_F0123], + (instregex "^LD3Rv(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_7Cyc_LS01_F0123, WriteAdr], + (instregex "^LD3Rv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +// ASIMD load, 4 element, multiple, D-form, B/H/S +// ASIMD load, 4 element, multiple, Q-form, B/H/S +// ASIMD load, 4 element, multiple, Q-form, D +def : InstRW<[THX3T110Write_8Cyc_LS01_F0123], + (instregex "^LD4Fourv(8b|4h|2s|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_8Cyc_LS01_F0123, WriteAdr], + (instregex "^LD4Fourv(8b|4h|2s|16b|8h|4s|2d)_POST$")>; + +// ASIMD load, 4 element, one lane, B/H +// ASIMD load, 4 element, one lane, S +// ASIMD load, 4 element, one lane, D +def : InstRW<[THX3T110Write_6Cyc_LS01_F0123], + (instregex "^LD4i(8|16|32|64)$")>; +def : InstRW<[THX3T110Write_6Cyc_LS01_F0123, WriteAdr], + (instregex "^LD4i(8|16|32|64)_POST$")>; + +// ASIMD load, 4 element, all lanes, D-form, B/H/S +// ASIMD load, 4 element, all lanes, D-form, D +// ASIMD load, 4 element, all lanes, Q-form, B/H/S +// ASIMD load, 4 element, all lanes, Q-form, D +def : InstRW<[THX3T110Write_6Cyc_LS01_F0123], + (instregex "^LD4Rv(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_6Cyc_LS01_F0123, WriteAdr], + (instregex "^LD4Rv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +//-- +// 3.16 ASIMD Store Instructions +//-- + +// ASIMD store, 1 element, multiple, 1 reg, D-form +// ASIMD store, 1 element, multiple, 1 reg, Q-form +def : InstRW<[THX3T110Write_1Cyc_LS01], + (instregex "^ST1Onev(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_1Cyc_LS01, WriteAdr], + (instregex "^ST1Onev(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +// ASIMD store, 1 element, multiple, 2 reg, D-form +// ASIMD store, 1 element, multiple, 2 reg, Q-form +def : InstRW<[THX3T110Write_1Cyc_LS01], + (instregex "^ST1Twov(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_1Cyc_LS01, WriteAdr], + (instregex "^ST1Twov(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +// ASIMD store, 1 element, multiple, 3 reg, D-form +// ASIMD store, 1 element, multiple, 3 reg, Q-form +def : InstRW<[THX3T110Write_1Cyc_LS01], + (instregex "^ST1Threev(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_1Cyc_LS01, WriteAdr], + (instregex "^ST1Threev(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +// ASIMD store, 1 element, multiple, 4 reg, D-form +// ASIMD store, 1 element, multiple, 4 reg, Q-form +def : InstRW<[THX3T110Write_1Cyc_LS01], + (instregex "^ST1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_1Cyc_LS01, WriteAdr], + (instregex "^ST1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>; + +// ASIMD store, 1 element, one lane, B/H/S +// ASIMD store, 1 element, one lane, D +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123], + (instregex "^ST1i(8|16|32|64)$")>; +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123, WriteAdr], + (instregex "^ST1i(8|16|32|64)_POST$")>; + +// ASIMD store, 2 element, multiple, D-form, B/H/S +// ASIMD store, 2 element, multiple, Q-form, B/H/S +// ASIMD store, 2 element, multiple, Q-form, D +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123], + (instregex "^ST2Twov(8b|4h|2s|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123, WriteAdr], + (instregex "^ST2Twov(8b|4h|2s|16b|8h|4s|2d)_POST$")>; + +// ASIMD store, 2 element, one lane, B/H/S +// ASIMD store, 2 element, one lane, D +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123], + (instregex "^ST2i(8|16|32|64)$")>; +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123, WriteAdr], + (instregex "^ST2i(8|16|32|64)_POST$")>; + +// ASIMD store, 3 element, multiple, D-form, B/H/S +// ASIMD store, 3 element, multiple, Q-form, B/H/S +// ASIMD store, 3 element, multiple, Q-form, D +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123], + (instregex "^ST3Threev(8b|4h|2s|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123, WriteAdr], + (instregex "^ST3Threev(8b|4h|2s|16b|8h|4s|2d)_POST$")>; + +// ASIMD store, 3 element, one lane, B/H +// ASIMD store, 3 element, one lane, S +// ASIMD store, 3 element, one lane, D +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123], + (instregex "^ST3i(8|16|32|64)$")>; +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123, WriteAdr], + (instregex "^ST3i(8|16|32|64)_POST$")>; + +// ASIMD store, 4 element, multiple, D-form, B/H/S +// ASIMD store, 4 element, multiple, Q-form, B/H/S +// ASIMD store, 4 element, multiple, Q-form, D +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123], + (instregex "^ST4Fourv(8b|4h|2s|16b|8h|4s|2d)$")>; +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123, WriteAdr], + (instregex "^ST4Fourv(8b|4h|2s|16b|8h|4s|2d)_POST$")>; + +// ASIMD store, 4 element, one lane, B/H +// ASIMD store, 4 element, one lane, S +// ASIMD store, 4 element, one lane, D +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123], + (instregex "^ST4i(8|16|32|64)$")>; +def : InstRW<[THX3T110Write_1Cyc_LS01_F0123, WriteAdr], + (instregex "^ST4i(8|16|32|64)_POST$")>; + +// V8.1a Atomics (LSE) +def : InstRW<[THX3T110Write_4Cyc_I0123, WriteAtomic], + (instrs CASB, CASH, CASW, CASX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs CASAB, CASAH, CASAW, CASAX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs CASLB, CASLH, CASLW, CASLX)>; + +def : InstRW<[THX3T110Write_8Cyc_I0123, WriteAtomic], + (instrs CASALB, CASALH, CASALW, CASALX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs LDLARB, LDLARH, LDLARW, LDLARX)>; + +def : InstRW<[THX3T110Write_4Cyc_I0123, WriteAtomic], + (instrs LDADDB, LDADDH, LDADDW, LDADDX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs LDADDAB, LDADDAH, LDADDAW, LDADDAX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs LDADDLB, LDADDLH, LDADDLW, LDADDLX)>; + +def : InstRW<[THX3T110Write_8Cyc_I0123, WriteAtomic], + (instrs LDADDALB, LDADDALH, LDADDALW, LDADDALX)>; + +def : InstRW<[THX3T110Write_4Cyc_I0123, WriteAtomic], + (instrs LDCLRB, LDCLRH, LDCLRW, LDCLRX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs LDCLRAB, LDCLRAH, LDCLRAW, LDCLRAX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs LDCLRLB, LDCLRLH, LDCLRLW, LDCLRLX)>; + +def : InstRW<[THX3T110Write_8Cyc_I0123, WriteAtomic], + (instrs LDCLRALB, LDCLRALH, LDCLRALW, LDCLRALX)>; + +def : InstRW<[THX3T110Write_4Cyc_I0123, WriteAtomic], + (instrs LDEORB, LDEORH, LDEORW, LDEORX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs LDEORAB, LDEORAH, LDEORAW, LDEORAX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs LDEORLB, LDEORLH, LDEORLW, LDEORLX)>; + +def : InstRW<[THX3T110Write_8Cyc_I0123, WriteAtomic], + (instrs LDEORALB, LDEORALH, LDEORALW, LDEORALX)>; + +def : InstRW<[THX3T110Write_4Cyc_I0123, WriteAtomic], + (instrs LDSETB, LDSETH, LDSETW, LDSETX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs LDSETAB, LDSETAH, LDSETAW, LDSETAX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs LDSETLB, LDSETLH, LDSETLW, LDSETLX)>; + +def : InstRW<[THX3T110Write_8Cyc_I0123, WriteAtomic], + (instrs LDSETALB, LDSETALH, LDSETALW, LDSETALX)>; + +def : InstRW<[THX3T110Write_4Cyc_I0123, WriteAtomic], + (instrs LDSMAXB, LDSMAXH, LDSMAXW, LDSMAXX, + LDSMAXAB, LDSMAXAH, LDSMAXAW, LDSMAXAX, + LDSMAXLB, LDSMAXLH, LDSMAXLW, LDSMAXLX, + LDSMAXALB, LDSMAXALH, LDSMAXALW, LDSMAXALX)>; + +def : InstRW<[THX3T110Write_4Cyc_I0123, WriteAtomic], + (instrs LDSMINB, LDSMINH, LDSMINW, LDSMINX, + LDSMINAB, LDSMINAH, LDSMINAW, LDSMINAX, + LDSMINLB, LDSMINLH, LDSMINLW, LDSMINLX, + LDSMINALB, LDSMINALH, LDSMINALW, LDSMINALX)>; + +def : InstRW<[THX3T110Write_4Cyc_I0123, WriteAtomic], + (instrs LDUMAXB, LDUMAXH, LDUMAXW, LDUMAXX, + LDUMAXAB, LDUMAXAH, LDUMAXAW, LDUMAXAX, + LDUMAXLB, LDUMAXLH, LDUMAXLW, LDUMAXLX, + LDUMAXALB, LDUMAXALH, LDUMAXALW, LDUMAXALX)>; + +def : InstRW<[THX3T110Write_4Cyc_I0123, WriteAtomic], + (instrs LDUMINB, LDUMINH, LDUMINW, LDUMINX, + LDUMINAB, LDUMINAH, LDUMINAW, LDUMINAX, + LDUMINLB, LDUMINLH, LDUMINLW, LDUMINLX, + LDUMINALB, LDUMINALH, LDUMINALW, LDUMINALX)>; + +def : InstRW<[THX3T110Write_4Cyc_I0123, WriteAtomic], + (instrs SWPB, SWPH, SWPW, SWPX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs SWPAB, SWPAH, SWPAW, SWPAX)>; + +def : InstRW<[THX3T110Write_6Cyc_I0123, WriteAtomic], + (instrs SWPLB, SWPLH, SWPLW, SWPLX)>; + +def : InstRW<[THX3T110Write_8Cyc_I0123, WriteAtomic], + (instrs SWPALB, SWPALH, SWPALW, SWPALX)>; + +def : InstRW<[THX3T110Write_4Cyc_I0123, WriteAtomic], + (instrs STLLRB, STLLRH, STLLRW, STLLRX)>; + +// V8.3a PAC +def : InstRW<[THX3T110Write_11Cyc_LS01_I1], (instregex "^LDRAA", "^LDRAB")>; +def : InstRW<[THX3T110Write_8Cyc_I123], + (instrs BLRAA, BLRAAZ, BLRAB, BLRABZ, + BRAA, BRAAZ, BRAB, BRABZ)>; +def : InstRW<[THX3T110Write_8Cyc_I123], (instrs RETAA, RETAB)>; + +} // SchedModel = ThunderX3T110Model + diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h --- a/llvm/lib/Target/AArch64/AArch64Subtarget.h +++ b/llvm/lib/Target/AArch64/AArch64Subtarget.h @@ -66,7 +66,8 @@ ThunderXT81, ThunderXT83, ThunderXT88, - TSV110 + TSV110, + ThunderX3T110 }; protected: diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp --- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp +++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp @@ -168,6 +168,17 @@ PrefFunctionLogAlignment = 4; PrefLoopLogAlignment = 2; break; + case ThunderX3T110: + CacheLineSize = 64; + PrefFunctionLogAlignment = 4; + PrefLoopLogAlignment = 2; + MaxInterleaveFactor = 4; + PrefetchDistance = 128; + MinPrefetchStride = 1024; + MaxPrefetchIterationsAhead = 4; + // FIXME: remove this to enable 64-bit SLP if performance looks good. + MinVectorRegisterBitWidth = 128; + break; } } diff --git a/llvm/test/CodeGen/AArch64/aarch64-combine-fmul-fsub.mir b/llvm/test/CodeGen/AArch64/aarch64-combine-fmul-fsub.mir --- a/llvm/test/CodeGen/AArch64/aarch64-combine-fmul-fsub.mir +++ b/llvm/test/CodeGen/AArch64/aarch64-combine-fmul-fsub.mir @@ -2,6 +2,7 @@ # RUN: llc -run-pass=machine-combiner -o - -mtriple=aarch64-unknown-linux -mcpu=falkor -enable-unsafe-fp-math %s -machine-combiner-verify-pattern-order=true | FileCheck --check-prefixes=PROFITABLE,ALL %s # RUN: llc -run-pass=machine-combiner -o - -mtriple=aarch64-unknown-linux -mcpu=exynos-m3 -enable-unsafe-fp-math -machine-combiner-verify-pattern-order=true %s | FileCheck --check-prefixes=PROFITABLE,ALL %s # RUN: llc -run-pass=machine-combiner -o - -mtriple=aarch64-unknown-linux -mcpu=thunderx2t99 -enable-unsafe-fp-math -machine-combiner-verify-pattern-order=true %s | FileCheck --check-prefixes=PROFITABLE,ALL %s +# RUN: llc -run-pass=machine-combiner -o - -mtriple=aarch64-unknown-linux -mcpu=thunderx3t110 -enable-unsafe-fp-math -machine-combiner-verify-pattern-order=true %s | FileCheck --check-prefixes=PROFITABLE,ALL %s # name: f1_2s registers: diff --git a/llvm/test/CodeGen/AArch64/cpus.ll b/llvm/test/CodeGen/AArch64/cpus.ll --- a/llvm/test/CodeGen/AArch64/cpus.ll +++ b/llvm/test/CodeGen/AArch64/cpus.ll @@ -24,6 +24,7 @@ ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=saphira 2>&1 | FileCheck %s ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=kryo 2>&1 | FileCheck %s ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=thunderx2t99 2>&1 | FileCheck %s +; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=thunderx3t110 2>&1 | FileCheck %s ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=tsv110 2>&1 | FileCheck %s ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=apple-latest 2>&1 | FileCheck %s ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=a64fx 2>&1 | FileCheck %s diff --git a/llvm/test/CodeGen/AArch64/machine-combiner-madd.ll b/llvm/test/CodeGen/AArch64/machine-combiner-madd.ll --- a/llvm/test/CodeGen/AArch64/machine-combiner-madd.ll +++ b/llvm/test/CodeGen/AArch64/machine-combiner-madd.ll @@ -6,6 +6,7 @@ ; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=exynos-m3 < %s | FileCheck %s ; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=kryo < %s | FileCheck %s ; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=thunderx2t99 < %s | FileCheck %s +; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=thunderx3t110 < %s | FileCheck %s ; Make sure that inst-combine fuses the multiply add in the addressing mode of ; the load. diff --git a/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll b/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll --- a/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll +++ b/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll @@ -19,6 +19,7 @@ ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=thunderxt83 < %s | FileCheck --check-prefixes=ALIGN3,CHECK %s ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=thunderxt88 < %s | FileCheck --check-prefixes=ALIGN3,CHECK %s ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=thunderx2t99 < %s | FileCheck --check-prefixes=ALIGN3,CHECK %s +; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=thunderx3t110 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=exynos-m3 < %s | FileCheck --check-prefixes=ALIGN5,CHECK %s define void @test() { diff --git a/llvm/test/CodeGen/AArch64/remat.ll b/llvm/test/CodeGen/AArch64/remat.ll --- a/llvm/test/CodeGen/AArch64/remat.ll +++ b/llvm/test/CodeGen/AArch64/remat.ll @@ -19,6 +19,7 @@ ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=thunderx2t99 -o - %s | FileCheck %s ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=tsv110 -o - %s | FileCheck %s ; RUN: llc -mtriple=aarch64-linux-gnuabi -mattr=+custom-cheap-as-move -o - %s | FileCheck %s +; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=thunderx3t110 -o - %s | FileCheck %s %X = type { i64, i64, i64 } declare void @f(%X*)