maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Target/Hexagon/HexagonScheduleV60.td

311 lines
16 KiB
TableGen
Raw Normal View History

[Hexagon] Adding skeleton of HVX extension instructions. llvm-svn: 250600
2015-10-17 09:33:04 +08:00
//=-HexagonScheduleV60.td - HexagonV60 Scheduling Definitions *- tablegen -*-=//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
// CVI pipes from the "Hexagon Multimedia Co-Processor Extensions Arch Spec".
def CVI_ST : FuncUnit;
def CVI_XLANE : FuncUnit;
def CVI_SHIFT : FuncUnit;
def CVI_MPY0 : FuncUnit;
def CVI_MPY1 : FuncUnit;
def CVI_LD : FuncUnit;
// Combined functional units.
def CVI_XLSHF : FuncUnit;
def CVI_MPY01 : FuncUnit;
def CVI_ALL : FuncUnit;
Hexagon V60/HVX DFA scheduler support Extended DFA tablegen to: - added "-debug-only dfa-emitter" support to llvm-tblgen - defined CVI_PIPE* resources for the V60 vector coprocessor - allow specification of multiple required resources - supports ANDs of ORs - e.g. [SLOT2, SLOT3], [CVI_MPY0, CVI_MPY1] means: (SLOT2 OR SLOT3) AND (CVI_MPY0 OR CVI_MPY1) - added support for combo resources - allows specifying ORs of ANDs - e.g. [CVI_XLSHF, CVI_MPY01] means: (CVI_XLANE AND CVI_SHIFT) OR (CVI_MPY0 AND CVI_MPY1) - increased DFA input size from 32-bit to 64-bit - allows for a maximum of 4 AND'ed terms of 16 resources - supported expressions now include: expression => term [AND term] [AND term] [AND term] term => resource [OR resource]* resource => one_resource | combo_resource combo_resource => (one_resource [AND one_resource]*) Author: Dan Palermo <dpalermo@codeaurora.org> kparzysz: Verified AMDGPU codegen to be unchanged on all llc tests, except those dealing with instruction encodings. Reapply the previous patch, this time without circular dependencies. llvm-svn: 253793
2015-11-22 04:00:45 +08:00
// Combined functional unit data.
def HexagonComboFuncsV60 :
ComboFuncUnits<[
ComboFuncData<CVI_XLSHF , [CVI_XLANE, CVI_SHIFT]>,
ComboFuncData<CVI_MPY01 , [CVI_MPY0, CVI_MPY1]>,
ComboFuncData<CVI_ALL , [CVI_ST, CVI_XLANE, CVI_SHIFT,
CVI_MPY0, CVI_MPY1, CVI_LD]>
]>;
[Hexagon] Adding skeleton of HVX extension instructions. llvm-svn: 250600
2015-10-17 09:33:04 +08:00
// Note: When adding additional vector scheduling classes, add the
// corresponding methods to the class HexagonInstrInfo.
def CVI_VA : InstrItinClass;
def CVI_VA_DV : InstrItinClass;
def CVI_VX_LONG : InstrItinClass;
def CVI_VX_LATE : InstrItinClass;
def CVI_VX : InstrItinClass;
def CVI_VX_DV_LONG : InstrItinClass;
def CVI_VX_DV : InstrItinClass;
def CVI_VX_DV_SLOT2 : InstrItinClass;
def CVI_VP : InstrItinClass;
def CVI_VP_LONG : InstrItinClass;
def CVI_VP_VS_EARLY : InstrItinClass;
def CVI_VP_VS_LONG_EARLY : InstrItinClass;
def CVI_VP_VS_LONG : InstrItinClass;
def CVI_VP_VS : InstrItinClass;
def CVI_VP_DV : InstrItinClass;
def CVI_VS : InstrItinClass;
def CVI_VINLANESAT : InstrItinClass;
def CVI_VM_LD : InstrItinClass;
def CVI_VM_TMP_LD : InstrItinClass;
def CVI_VM_CUR_LD : InstrItinClass;
def CVI_VM_VP_LDU : InstrItinClass;
def CVI_VM_ST : InstrItinClass;
def CVI_VM_NEW_ST : InstrItinClass;
def CVI_VM_STU : InstrItinClass;
def CVI_HIST : InstrItinClass;
def CVI_VA_EXT : InstrItinClass;
// There are four SLOTS (four parallel pipelines) in Hexagon V60 machine.
// This file describes that machine information.
//
// |===========|==================================================|
// | PIPELINE | Instruction Classes |
// |===========|==================================================|
// | SLOT0 | LD ST ALU32 MEMOP NV SYSTEM |
// |-----------|--------------------------------------------------|
// | SLOT1 | LD ST ALU32 |
// |-----------|--------------------------------------------------|
// | SLOT2 | XTYPE ALU32 J JR |
// |-----------|--------------------------------------------------|
// | SLOT3 | XTYPE ALU32 J CR |
// |===========|==================================================|
//
//
// In addition to using the above SLOTS, there are also six vector pipelines
// in the CVI co-processor in the Hexagon V60 machine.
//
// |=========| |=========| |=========| |=========| |=========| |=========|
// SLOT | CVI_LD | |CVI_MPY3 | |CVI_MPY2 | |CVI_SHIFT| |CVI_XLANE| | CVI_ST |
// ==== |=========| |=========| |=========| |=========| |=========| |=========|
// S0-3 | | | CVI_VA | | CVI_VA | | CVI_VA | | CVI_VA | | |
// S2-3 | | | CVI_VX | | CVI_VX | | | | | | |
// S0-3 | | | | | | | | | CVI_VP | | |
// S0-3 | | | | | | | CVI_VS | | | | |
// S0-1 |(CVI_LD) | | CVI_LD | | CVI_LD | | CVI_LD | | CVI_LD | | |
// S0-1 |(C*TMP_LD) | | | | | | | | | |
// S01 |(C*_LDU) | | | | | | | | C*_LDU | | |
// S0 | | | CVI_ST | | CVI_ST | | CVI_ST | | CVI_ST | |(CVI_ST) |
// S0 | | | | | | | | | | |(C*TMP_ST)
// S01 | | | | | | | | | VSTU | |(C*_STU) |
// |=========| |=========| |=========| |=========| |=========| |=========|
// |=====================| |=====================|
// | CVI_MPY2 & CVI_MPY3 | |CVI_XLANE & CVI_SHIFT|
// |=====================| |=====================|
// S0-3 | CVI_VA_DV | | CVI_VA_DV |
// S0-3 | | | CVI_VP_DV |
// S2-3 | CVI_VX_DV | | |
// |=====================| |=====================|
// |=====================================================================|
// S0-3 | CVI_HIST Histogram |
// S0123| CVI_VA_EXT Extract |
// |=====================================================================|
def HexagonItinerariesV60 :
ProcessorItineraries<[SLOT0, SLOT1, SLOT2, SLOT3, SLOT_ENDLOOP,
CVI_ST, CVI_XLANE, CVI_SHIFT, CVI_MPY0, CVI_MPY1,
CVI_LD, CVI_XLSHF, CVI_MPY01, CVI_ALL], [], [
// ALU32
InstrItinData<ALU32_2op_tc_1_SLOT0123 ,
[InstrStage<1, [SLOT0, SLOT1, SLOT2, SLOT3]>]>,
InstrItinData<ALU32_2op_tc_2early_SLOT0123,
[InstrStage<2, [SLOT0, SLOT1, SLOT2, SLOT3]>]>,
InstrItinData<ALU32_3op_tc_1_SLOT0123 ,
[InstrStage<1, [SLOT0, SLOT1, SLOT2, SLOT3]>]>,
InstrItinData<ALU32_3op_tc_2_SLOT0123 ,
[InstrStage<2, [SLOT0, SLOT1, SLOT2, SLOT3]>]>,
InstrItinData<ALU32_3op_tc_2early_SLOT0123,
[InstrStage<2, [SLOT0, SLOT1, SLOT2, SLOT3]>]>,
InstrItinData<ALU32_ADDI_tc_1_SLOT0123 ,
[InstrStage<1, [SLOT0, SLOT1, SLOT2, SLOT3]>]>,
// ALU64
InstrItinData<ALU64_tc_1_SLOT23 , [InstrStage<1, [SLOT2, SLOT3]>]>,
InstrItinData<ALU64_tc_2_SLOT23 , [InstrStage<2, [SLOT2, SLOT3]>]>,
InstrItinData<ALU64_tc_2early_SLOT23, [InstrStage<2, [SLOT2, SLOT3]>]>,
InstrItinData<ALU64_tc_3x_SLOT23 , [InstrStage<3, [SLOT2, SLOT3]>]>,
// CR -> System
InstrItinData<CR_tc_2_SLOT3 , [InstrStage<2, [SLOT3]>]>,
InstrItinData<CR_tc_2early_SLOT3 , [InstrStage<2, [SLOT3]>]>,
InstrItinData<CR_tc_3x_SLOT3 , [InstrStage<3, [SLOT3]>]>,
// Jump (conditional/unconditional/return etc)
InstrItinData<CR_tc_2early_SLOT23, [InstrStage<2, [SLOT2, SLOT3]>]>,
InstrItinData<CR_tc_3x_SLOT23 , [InstrStage<3, [SLOT2, SLOT3]>]>,
InstrItinData<CJ_tc_1_SLOT23 , [InstrStage<1, [SLOT2, SLOT3]>]>,
InstrItinData<CJ_tc_2early_SLOT23, [InstrStage<2, [SLOT2, SLOT3]>]>,
InstrItinData<J_tc_2early_SLOT23 , [InstrStage<2, [SLOT2, SLOT3]>]>,
InstrItinData<J_tc_2early_CJUMP_UCJUMP_ARCHDEPSLOT , [InstrStage<1, [SLOT2, SLOT3]>]>,
// JR
InstrItinData<J_tc_2early_SLOT2 , [InstrStage<2, [SLOT2]>]>,
InstrItinData<J_tc_3stall_SLOT2 , [InstrStage<3, [SLOT2]>]>,
// Extender
InstrItinData<EXTENDER_tc_1_SLOT0123, [InstrStage<1,
[SLOT0, SLOT1, SLOT2, SLOT3]>]>,
// Load
InstrItinData<LD_tc_ld_SLOT01 , [InstrStage<3, [SLOT0, SLOT1]>]>,
InstrItinData<LD_tc_3or4stall_SLOT0, [InstrStage<4, [SLOT0]>]>,
InstrItinData<LD_tc_ld_SLOT0 , [InstrStage<3, [SLOT0]>]>,
// M
InstrItinData<M_tc_1_SLOT23 , [InstrStage<1, [SLOT2, SLOT3]>]>,
InstrItinData<M_tc_2_SLOT23 , [InstrStage<2, [SLOT2, SLOT3]>]>,
InstrItinData<M_tc_3_SLOT23 , [InstrStage<3, [SLOT2, SLOT3]>]>,
InstrItinData<M_tc_3x_SLOT23 , [InstrStage<3, [SLOT2, SLOT3]>]>,
InstrItinData<M_tc_3or4x_SLOT23 , [InstrStage<4, [SLOT2, SLOT3]>]>,
InstrItinData<M_tc_3stall_SLOT23, [InstrStage<3, [SLOT2, SLOT3]>]>,
// Store
InstrItinData<ST_tc_st_SLOT01 , [InstrStage<1, [SLOT0, SLOT1]>]>,
InstrItinData<ST_tc_3stall_SLOT0, [InstrStage<3, [SLOT0]>]>,
InstrItinData<ST_tc_ld_SLOT0 , [InstrStage<3, [SLOT0]>]>,
InstrItinData<ST_tc_st_SLOT0 , [InstrStage<1, [SLOT0]>]>,
// Subinsn
InstrItinData<SUBINSN_tc_2early_SLOT0, [InstrStage<2, [SLOT0]>]>,
InstrItinData<SUBINSN_tc_3stall_SLOT0, [InstrStage<3, [SLOT0]>]>,
InstrItinData<SUBINSN_tc_ld_SLOT0 , [InstrStage<3, [SLOT0]>]>,
InstrItinData<SUBINSN_tc_1_SLOT01 , [InstrStage<1, [SLOT0, SLOT1]>]>,
InstrItinData<SUBINSN_tc_2early_SLOT01,
[InstrStage<2, [SLOT0, SLOT1]>]>,
InstrItinData<SUBINSN_tc_ld_SLOT01 , [InstrStage<3, [SLOT0, SLOT1]>]>,
InstrItinData<SUBINSN_tc_st_SLOT01 , [InstrStage<1, [SLOT0, SLOT1]>]>,
// S
InstrItinData<S_2op_tc_1_SLOT23 , [InstrStage<1, [SLOT2, SLOT3]>]>,
InstrItinData<S_2op_tc_2_SLOT23 , [InstrStage<2, [SLOT2, SLOT3]>]>,
InstrItinData<S_2op_tc_2early_SLOT23, [InstrStage<2, [SLOT2, SLOT3]>]>,
// The S_2op_tc_3x_SLOT23 slots are 4 cycles on v60.
InstrItinData<S_2op_tc_3or4x_SLOT23 , [InstrStage<4, [SLOT2, SLOT3]>]>,
InstrItinData<S_3op_tc_1_SLOT23 , [InstrStage<1, [SLOT2, SLOT3]>]>,
InstrItinData<S_3op_tc_2_SLOT23 , [InstrStage<2, [SLOT2, SLOT3]>]>,
InstrItinData<S_3op_tc_2early_SLOT23, [InstrStage<2, [SLOT2, SLOT3]>]>,
InstrItinData<S_3op_tc_3_SLOT23 , [InstrStage<3, [SLOT2, SLOT3]>]>,
InstrItinData<S_3op_tc_3stall_SLOT23, [InstrStage<3, [SLOT2, SLOT3]>]>,
InstrItinData<S_3op_tc_3x_SLOT23 , [InstrStage<3, [SLOT2, SLOT3]>]>,
// New Value Compare Jump
InstrItinData<NCJ_tc_3or4stall_SLOT0, [InstrStage<4, [SLOT0]>]>,
// Mem ops
InstrItinData<V2LDST_tc_st_SLOT0 , [InstrStage<1, [SLOT0]>]>,
InstrItinData<V2LDST_tc_ld_SLOT01 , [InstrStage<2, [SLOT0, SLOT1]>]>,
InstrItinData<V2LDST_tc_st_SLOT01 , [InstrStage<1, [SLOT0, SLOT1]>]>,
InstrItinData<V4LDST_tc_st_SLOT0 , [InstrStage<1, [SLOT0]>]>,
InstrItinData<V4LDST_tc_ld_SLOT01 , [InstrStage<3, [SLOT0, SLOT1]>]>,
InstrItinData<V4LDST_tc_st_SLOT01 , [InstrStage<1, [SLOT0, SLOT1]>]>,
// Endloop
InstrItinData<J_tc_2early_SLOT0123, [InstrStage<2, [SLOT_ENDLOOP]>]>,
// Vector
InstrItinData<COPROC_VMEM_vtc_long_SLOT01,
[InstrStage<3, [SLOT0, SLOT1]>]>,
InstrItinData<COPROC_VX_vtc_long_SLOT23 ,
[InstrStage<3, [SLOT2, SLOT3]>]>,
InstrItinData<COPROC_VX_vtc_SLOT23 ,
[InstrStage<3, [SLOT2, SLOT3]>]>,
InstrItinData<MAPPING_tc_1_SLOT0123 ,
[InstrStage<1, [SLOT0, SLOT1, SLOT2, SLOT3]>]>,
// Duplex and Compound
InstrItinData<DUPLEX , [InstrStage<1, [SLOT0]>]>,
InstrItinData<COMPOUND_CJ_ARCHDEPSLOT , [InstrStage<1, [SLOT2, SLOT3]>]>,
InstrItinData<COMPOUND , [InstrStage<1, [SLOT2, SLOT3]>]>,
// Misc
InstrItinData<PREFIX , [InstrStage<1, [SLOT0, SLOT1, SLOT2, SLOT3]>]>,
InstrItinData<PSEUDO , [InstrStage<1, [SLOT0, SLOT1, SLOT2, SLOT3]>]>,
InstrItinData<PSEUDOM , [InstrStage<1, [SLOT2, SLOT3], 0>,
InstrStage<1, [SLOT2, SLOT3]>]>,
// Latest CVI spec definitions.
InstrItinData<CVI_VA,[InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_XLANE,CVI_SHIFT,
CVI_MPY0, CVI_MPY1]>]>,
InstrItinData<CVI_VA_DV,
[InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_XLSHF, CVI_MPY01]>]>,
InstrItinData<CVI_VX_LONG, [InstrStage<1, [SLOT2, SLOT3], 0>,
InstrStage<1, [CVI_MPY0, CVI_MPY1]>]>,
InstrItinData<CVI_VX_LATE, [InstrStage<1, [SLOT2, SLOT3], 0>,
InstrStage<1, [CVI_MPY0, CVI_MPY1]>]>,
InstrItinData<CVI_VX,[InstrStage<1, [SLOT2, SLOT3], 0>,
InstrStage<1, [CVI_MPY0, CVI_MPY1]>]>,
InstrItinData<CVI_VX_DV_LONG,
[InstrStage<1, [SLOT2, SLOT3], 0>,
InstrStage<1, [CVI_MPY01]>]>,
InstrItinData<CVI_VX_DV,
[InstrStage<1, [SLOT2, SLOT3], 0>,
InstrStage<1, [CVI_MPY01]>]>,
InstrItinData<CVI_VX_DV_SLOT2,
[InstrStage<1, [SLOT2], 0>,
InstrStage<1, [CVI_MPY01]>]>,
InstrItinData<CVI_VP, [InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_XLANE]>]>,
InstrItinData<CVI_VP_LONG, [InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_XLANE]>]>,
InstrItinData<CVI_VP_VS_EARLY,
[InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_XLSHF]>]>,
InstrItinData<CVI_VP_VS_LONG,
[InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_XLSHF]>]>,
InstrItinData<CVI_VP_VS,
[InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_XLSHF]>]>,
InstrItinData<CVI_VP_VS_LONG_EARLY,
[InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_XLSHF]>]>,
InstrItinData<CVI_VP_DV , [InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_XLSHF]>]>,
InstrItinData<CVI_VS,
[InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_SHIFT]>]>,
InstrItinData<CVI_VINLANESAT,
[InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_SHIFT]>]>,
InstrItinData<CVI_VM_LD , [InstrStage<1, [SLOT0, SLOT1], 0>,
InstrStage<1, [CVI_LD], 0>,
InstrStage<1, [CVI_XLANE, CVI_SHIFT,
CVI_MPY0, CVI_MPY1]>]>,
InstrItinData<CVI_VM_TMP_LD,[InstrStage<1,[SLOT0, SLOT1], 0>,
InstrStage<1, [CVI_LD]>]>,
InstrItinData<CVI_VM_CUR_LD,[InstrStage<1,[SLOT0, SLOT1], 0>,
InstrStage<1, [CVI_LD], 0>,
InstrStage<1, [CVI_XLANE, CVI_SHIFT,
CVI_MPY0, CVI_MPY1]>]>,
InstrItinData<CVI_VM_VP_LDU,[InstrStage<1,[SLOT0], 0>,
InstrStage<1, [SLOT1], 0>,
InstrStage<1, [CVI_LD], 0>,
InstrStage<1, [CVI_XLANE]>]>,
InstrItinData<CVI_VM_ST , [InstrStage<1, [SLOT0], 0>,
InstrStage<1, [CVI_ST], 0>,
InstrStage<1, [CVI_XLANE, CVI_SHIFT,
CVI_MPY0, CVI_MPY1]>]>,
InstrItinData<CVI_VM_NEW_ST,[InstrStage<1,[SLOT0], 0>,
InstrStage<1, [CVI_ST]>]>,
InstrItinData<CVI_VM_STU , [InstrStage<1, [SLOT0], 0>,
InstrStage<1, [SLOT1], 0>,
InstrStage<1, [CVI_ST], 0>,
InstrStage<1, [CVI_XLANE]>]>,
InstrItinData<CVI_HIST , [InstrStage<1, [SLOT0,SLOT1,SLOT2,SLOT3], 0>,
InstrStage<1, [CVI_ALL]>]>
]>;
def HexagonModelV60 : SchedMachineModel {
// Max issue per cycle == bundle width.
let IssueWidth = 4;
let Itineraries = HexagonItinerariesV60;
let LoadLatency = 1;
}
//===----------------------------------------------------------------------===//
// Hexagon V60 Resource Definitions -
//===----------------------------------------------------------------------===//