Index: lib/Target/ARM/ARMScheduleSwift.td =================================================================== --- lib/Target/ARM/ARMScheduleSwift.td +++ lib/Target/ARM/ARMScheduleSwift.td @@ -25,1050 +25,6 @@ def SW_IDIV : FuncUnit; def SW_FDIV : FuncUnit; -// FIXME: Need bypasses. -// FIXME: Model the multiple stages of IIC_iMOVix2, IIC_iMOVix2addpc, and -// IIC_iMOVix2ld better. -// FIXME: Model the special immediate shifts that are not microcoded. -// FIXME: Do we need to model the fact that uses of r15 in a micro-op force it -// to issue on pipe 1? -// FIXME: Model the pipelined behavior of CMP / TST instructions. -// FIXME: Better model the microcode stages of multiply instructions, especially -// conditional variants. -// FIXME: Add preload instruction when it is documented. -// FIXME: Model non-pipelined nature of FP div / sqrt unit. - -def SwiftItineraries : ProcessorItineraries< - [SW_DIS0, SW_DIS1, SW_DIS2, SW_ALU0, SW_ALU1, SW_LS, SW_IDIV, SW_FDIV], [], [ - // - // Move instructions, unconditional - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - InstrItinData, - InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1]>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>, - InstrStage<1, [SW_ALU0, SW_ALU1]>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [3]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>, - InstrStage<1, [SW_ALU0, SW_ALU1]>, - InstrStage<1, [SW_LS]>], - [5]>, - // - // MVN instructions - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - // - // No operand cycles - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>]>, - // - // Binary Instructions that produce a result - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2, 1, 1, 1]>, - // - // Bitwise Instructions that produce a result - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2, 1, 1, 1]>, - // - // Unary Instructions that produce a result - - // CLZ, RBIT, etc. - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1]>, - - // BFC, BFI, UBFX, SBFX - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2, 1]>, - - // - // Zero and sign extension instructions - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1, 1, 1]>, - // - // Compare instructions - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1]>, - InstrItinData, - InstrStage<2, [SW_ALU0, SW_ALU1]>], - [1, 1]>, - InstrItinData, - InstrStage<2, [SW_ALU0, SW_ALU1]>], - [1, 1, 1]>, - // - // Test instructions - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1]>, - InstrItinData, - InstrStage<2, [SW_ALU0, SW_ALU1]>], - [1, 1]>, - InstrItinData, - InstrStage<2, [SW_ALU0, SW_ALU1]>], - [1, 1, 1]>, - // - // Move instructions, conditional - // FIXME: Correctly model the extra input dep on the destination. - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1]>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2]>, - - // Integer multiply pipeline - // - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [3, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [3, 1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU0], 1>, - InstrStage<1, [SW_ALU0], 3>, - InstrStage<1, [SW_ALU0]>], - [5, 5, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU0], 1>, - InstrStage<1, [SW_ALU0], 1>, - InstrStage<1, [SW_ALU0, SW_ALU1], 3>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [5, 6, 1, 1]>, - // - // Integer divide - InstrItinData, - InstrStage<1, [SW_ALU0], 0>, - InstrStage<14, [SW_IDIV]>], - [14, 1, 1]>, - - // Integer load pipeline - // FIXME: The timings are some rough approximations - // - // Immediate offset - InstrItinData, - InstrStage<1, [SW_LS]>], - [3, 1]>, - InstrItinData, - InstrStage<1, [SW_LS]>], - [3, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_LS], 1>, - InstrStage<1, [SW_LS]>], - [3, 4, 1]>, - // - // Register offset - InstrItinData, - InstrStage<1, [SW_LS]>], - [3, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_LS]>], - [3, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_LS], 1>, - InstrStage<1, [SW_LS], 3>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [3, 4, 1, 1]>, - // - // Scaled register offset - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 2>, - InstrStage<1, [SW_LS]>], - [5, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 2>, - InstrStage<1, [SW_LS]>], - [5, 1, 1]>, - // - // Immediate offset with update - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [3, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [3, 1, 1]>, - // - // Register offset with update - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0], 1>, - InstrStage<1, [SW_LS]>], - [3, 1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0], 1>, - InstrStage<1, [SW_LS]>], - [3, 1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 0>, - InstrStage<1, [SW_LS], 3>, - InstrStage<1, [SW_LS], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [3, 4, 1, 1]>, - // - // Scaled register offset with update - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 2>, - InstrStage<1, [SW_LS], 3>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [5, 3, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 2>, - InstrStage<1, [SW_LS], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [5, 3, 1, 1]>, - // - // Load multiple, def is the 5th operand. - // FIXME: This assumes 3 to 4 registers. - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [1, 1, 1, 1, 3], [], -1>, // dynamic uops - - // - // Load multiple + update, defs are the 1st and 5th operands. - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 0>, - InstrStage<1, [SW_LS], 3>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2, 1, 1, 1, 3], [], -1>, // dynamic uops - // - // Load multiple plus branch - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [1, 1, 1, 1, 3], [], -1>, // dynamic uops - // - // Pop, def is the 3rd operand. - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [1, 1, 3], [], -1>, // dynamic uops - // - // Pop + branch, def is the 3rd operand. - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [1, 1, 3], [], -1>, // dynamic uops - - // - // iLoadi + iALUr for t2LDRpci_pic. - InstrItinData, - InstrStage<1, [SW_LS], 3>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [4, 1]>, - - // Integer store pipeline - /// - // Immediate offset - InstrItinData, - InstrStage<1, [SW_LS]>], - [1, 1]>, - InstrItinData, - InstrStage<1, [SW_LS]>], - [1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_LS], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [1, 1]>, - // - // Register offset - InstrItinData, - InstrStage<1, [SW_LS]>], - [1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_LS]>], - [1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_LS], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [1, 1, 1]>, - // - // Scaled register offset - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 2>, - InstrStage<1, [SW_LS]>], - [1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 2>, - InstrStage<1, [SW_LS]>], - [1, 1, 1]>, - // - // Immediate offset with update - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [1, 1, 1]>, - // - // Register offset with update - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [1, 1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [1, 1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [1, 1, 1, 1]>, - // - // Scaled register offset with update - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 2>, - InstrStage<1, [SW_LS], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>], - [3, 1, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 2>, - InstrStage<1, [SW_LS], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>], - [3, 1, 1, 1]>, - // - // Store multiple - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS], 1>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS], 1>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [], [], -1>, // dynamic uops - // - // Store multiple + update - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS], 1>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS], 1>, - InstrStage<1, [SW_ALU0, SW_ALU1], 1>, - InstrStage<1, [SW_LS]>], - [2], [], -1>, // dynamic uops - - // - // Preload - InstrItinData], [1, 1]>, - - // Branch - // - // no delay slots, so the latency of a branch is unimportant - InstrItinData]>, - - // FP Special Register to Integer Register File Move - InstrItinData, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [1]>, - // - // Single-precision FP Unary - // - // Most floating-point moves get issued on ALU0. - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1]>, - // - // Double-precision FP Unary - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1]>, - - // - // Single-precision FP Compare - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [1, 1]>, - // - // Double-precision FP Compare - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [1, 1]>, - // - // Single to Double FP Convert - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1]>, - // - // Double to Single FP Convert - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1]>, - - // - // Single to Half FP Convert - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU1], 4>, - InstrStage<1, [SW_ALU1]>], - [6, 1]>, - // - // Half to Single FP Convert - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1]>, - - // - // Single-Precision FP to Integer Convert - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1]>, - // - // Double-Precision FP to Integer Convert - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1]>, - // - // Integer to Single-Precision FP Convert - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1]>, - // - // Integer to Double-Precision FP Convert - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1]>, - // - // Single-precision FP ALU - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1, 1]>, - // - // Double-precision FP ALU - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1, 1]>, - // - // Single-precision FP Multiply - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1, 1]>, - // - // Double-precision FP Multiply - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [6, 1, 1]>, - // - // Single-precision FP MAC - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [8, 1, 1]>, - // - // Double-precision FP MAC - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [12, 1, 1]>, - // - // Single-precision Fused FP MAC - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [8, 1, 1]>, - // - // Double-precision Fused FP MAC - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [12, 1, 1]>, - // - // Single-precision FP DIV - InstrItinData, - InstrStage<1, [SW_ALU1], 0>, - InstrStage<15, [SW_FDIV]>], - [17, 1, 1]>, - // - // Double-precision FP DIV - InstrItinData, - InstrStage<1, [SW_ALU1], 0>, - InstrStage<30, [SW_FDIV]>], - [32, 1, 1]>, - // - // Single-precision FP SQRT - InstrItinData, - InstrStage<1, [SW_ALU1], 0>, - InstrStage<15, [SW_FDIV]>], - [17, 1]>, - // - // Double-precision FP SQRT - InstrItinData, - InstrStage<1, [SW_ALU1], 0>, - InstrStage<30, [SW_FDIV]>], - [32, 1, 1]>, - - // - // Integer to Single-precision Move - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_LS], 4>, - InstrStage<1, [SW_ALU0]>], - [6, 1]>, - // - // Integer to Double-precision Move - InstrItinData, - InstrStage<1, [SW_LS]>], - [4, 1]>, - // - // Single-precision to Integer Move - InstrItinData, - InstrStage<1, [SW_LS]>], - [3, 1]>, - // - // Double-precision to Integer Move - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_LS], 3>, - InstrStage<1, [SW_LS]>], - [3, 4, 1]>, - // - // Single-precision FP Load - InstrItinData, - InstrStage<1, [SW_LS]>], - [4, 1]>, - // - // Double-precision FP Load - InstrItinData, - InstrStage<1, [SW_LS]>], - [4, 1]>, - // - // FP Load Multiple - // FIXME: Assumes a single Q register. - InstrItinData, - InstrStage<1, [SW_LS]>], - [1, 1, 1, 4], [], -1>, // dynamic uops - // - // FP Load Multiple + update - // FIXME: Assumes a single Q register. - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_LS], 4>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2, 1, 1, 1, 4], [], -1>, // dynamic uops - // - // Single-precision FP Store - InstrItinData, - InstrStage<1, [SW_LS]>], - [1, 1]>, - // - // Double-precision FP Store - InstrItinData, - InstrStage<1, [SW_LS]>], - [1, 1]>, - // - // FP Store Multiple - // FIXME: Assumes a single Q register. - InstrItinData, - InstrStage<1, [SW_LS]>], - [1, 1, 1], [], -1>, // dynamic uops - // - // FP Store Multiple + update - // FIXME: Assumes a single Q register. - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_LS], 4>, - InstrStage<1, [SW_ALU0, SW_ALU1]>], - [2, 1, 1, 1], [], -1>, // dynamic uops - // NEON - // - // Double-register Integer Unary - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1]>, - // - // Quad-register Integer Unary - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1]>, - // - // Double-register Integer Q-Unary - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1]>, - // - // Quad-register Integer CountQ-Unary - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1]>, - // - // Double-register Integer Binary - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1, 1]>, - // - // Quad-register Integer Binary - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1, 1]>, - // - // Double-register Integer Subtract - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1, 1]>, - // - // Quad-register Integer Subtract - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1, 1]>, - // - // Double-register Integer Shift - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1, 1]>, - // - // Quad-register Integer Shift - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1, 1]>, - // - // Double-register Integer Shift (4 cycle) - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - // - // Quad-register Integer Shift (4 cycle) - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - // - // Double-register Integer Binary (4 cycle) - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - // - // Quad-register Integer Binary (4 cycle) - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - // - // Double-register Integer Subtract (4 cycle) - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - // - // Quad-register Integer Subtract (4 cycle) - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - - // - // Double-register Integer Count - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1, 1]>, - // - // Quad-register Integer Count - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1, 1]>, - // - // Double-register Absolute Difference and Accumulate - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1, 1]>, - // - // Quad-register Absolute Difference and Accumulate - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1, 1]>, - // - // Double-register Integer Pair Add Long - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - // - // Quad-register Integer Pair Add Long - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - - // - // Double-register Integer Multiply (.8, .16) - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1, 1]>, - // - // Quad-register Integer Multiply (.8, .16) - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1, 1]>, - - // - // Double-register Integer Multiply (.32) - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1, 1]>, - // - // Quad-register Integer Multiply (.32) - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1, 1]>, - // - // Double-register Integer Multiply-Accumulate (.8, .16) - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1, 1, 1]>, - // - // Double-register Integer Multiply-Accumulate (.32) - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1, 1, 1]>, - // - // Quad-register Integer Multiply-Accumulate (.8, .16) - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1, 1, 1]>, - // - // Quad-register Integer Multiply-Accumulate (.32) - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1, 1, 1]>, - - // - // Move - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1]>, - // - // Move Immediate - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2]>, - // - // Double-register Permute Move - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [2, 1]>, - // - // Quad-register Permute Move - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [2, 1]>, - // - // Integer to Single-precision Move - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_LS], 4>, - InstrStage<1, [SW_ALU0]>], - [6, 1]>, - // - // Integer to Double-precision Move - InstrItinData, - InstrStage<1, [SW_LS]>], - [4, 1, 1]>, - // - // Single-precision to Integer Move - InstrItinData, - InstrStage<1, [SW_LS]>], - [3, 1]>, - // - // Double-precision to Integer Move - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_LS], 3>, - InstrStage<1, [SW_LS]>], - [3, 4, 1]>, - // - // Integer to Lane Move - // FIXME: I think this is correct, but it is not clear from the tuning guide. - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_LS], 4>, - InstrStage<1, [SW_ALU0]>], - [6, 1]>, - - // - // Vector narrow move - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [2, 1]>, - // - // Double-register FP Unary - // FIXME: VRECPE / VRSQRTE has a longer latency than VABS, which is used here, - // and they issue on a different pipeline. - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1]>, - // - // Quad-register FP Unary - // FIXME: VRECPE / VRSQRTE has a longer latency than VABS, which is used here, - // and they issue on a different pipeline. - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [2, 1]>, - // - // Double-register FP Binary - // FIXME: We're using this itin for many instructions. - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - - // - // VPADD, etc. - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - // - // Double-register FP VMUL - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1, 1]>, - // - // Quad-register FP Binary - InstrItinData, - InstrStage<1, [SW_ALU0]>], - [4, 1, 1]>, - // - // Quad-register FP VMUL - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [4, 1, 1]>, - // - // Double-register FP Multiple-Accumulate - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [8, 1, 1]>, - // - // Quad-register FP Multiple-Accumulate - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [8, 1, 1]>, - // - // Double-register Fused FP Multiple-Accumulate - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [8, 1, 1]>, - // - // Quad-register FusedF P Multiple-Accumulate - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [8, 1, 1]>, - // - // Double-register Reciprical Step - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [8, 1, 1]>, - // - // Quad-register Reciprical Step - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [8, 1, 1]>, - // - // Double-register Permute - // FIXME: The latencies are unclear from the documentation. - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1]>], - [3, 4, 3, 4]>, - // - // Quad-register Permute - // FIXME: The latencies are unclear from the documentation. - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1]>], - [3, 4, 3, 4]>, - // - // Quad-register Permute (3 cycle issue on A9) - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1]>], - [3, 4, 3, 4]>, - - // - // Double-register VEXT - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [2, 1, 1]>, - // - // Quad-register VEXT - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [2, 1, 1]>, - // - // VTB - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [2, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1]>], - [4, 1, 3, 3]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1]>], - [6, 1, 3, 5, 5]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1]>], - [8, 1, 3, 5, 7, 7]>, - // - // VTBX - InstrItinData, - InstrStage<1, [SW_ALU1]>], - [2, 1, 1]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1]>], - [4, 1, 3, 3]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1]>], - [6, 1, 3, 5, 5]>, - InstrItinData, - InstrStage<1, [SW_DIS1], 0>, - InstrStage<1, [SW_DIS2], 0>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1], 2>, - InstrStage<1, [SW_ALU1]>], - [8, 1, 3, 5, 7, 7]> -]>; - // ===---------------------------------------------------------------------===// // This following definitions describe the simple machine model which // will replace itineraries. @@ -1079,8 +35,6 @@ let MicroOpBufferSize = 45; // Based on NEON renamed registers. let LoadLatency = 3; let MispredictPenalty = 14; // A branch direction mispredict. - - let Itineraries = SwiftItineraries; } // Swift predicates.