| # NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py |
| # RUN: llvm-mca -mtriple=riscv64 -mcpu=mips-p8700 -timeline -iterations=1 < %s | FileCheck %s |
| |
| # A few instructions to test the pipeline: |
| # - Integer division (IDiv) exercises the p8700GpDiv resource. |
| # - Integer multiplication (IMul) uses p8700GpMul. |
| # - Floating-point multiplication uses the FPUL pipeline. |
| # - Load/Store instructions use the LSU pipeline. |
| # - Simple ALU instructions test the p8700WriteEitherALU and p8700IssueAL2 resources. |
| # - A jump instruction to test the CTI pipeline. |
| |
| # Integer division: a0 = a1 / a2 |
| # Exercises p8700GpDiv resource. |
| div a0, a1, a2 |
| |
| # Integer multiplication: a4 = a1 * a2 |
| # Exercises p8700GpMul resource. |
| mul a4, a1, a2 |
| |
| # Floating-point multiply: f1 = f2 * f3 (single precision) |
| # Exercises p8700FpuLong + p8700FpuApu resources. |
| fmul.s f1, f2, f3 |
| |
| # Load/Store: load word from a0 into a3, then store a3 into a1 |
| # Exercises p8700IssueLSU resource. |
| lw a3, 0(a0) |
| sw a3, 0(a1) |
| |
| # Simple ALU operations (adding two registers, rotating bits) |
| # Exercises p8700WriteEitherALU. |
| add a5, a1, a2 |
| ror a6, a5, a2 |
| |
| # A jump instruction: a simple forward jump |
| # Exercises p8700IssueCTI resource. |
| jal x0, .Lend |
| |
| add a7, a4, a0 # Instruction after jump (won't execute) |
| .Lend: |
| nop |
| |
| # CHECK: Iterations: 1 |
| # CHECK-NEXT: Instructions: 10 |
| # CHECK-NEXT: Total Cycles: 17 |
| # CHECK-NEXT: Total uOps: 10 |
| |
| # CHECK: Dispatch Width: 4 |
| # CHECK-NEXT: uOps Per Cycle: 0.59 |
| # CHECK-NEXT: IPC: 0.59 |
| # CHECK-NEXT: Block RThroughput: 7.0 |
| |
| # CHECK: Instruction Info: |
| # CHECK-NEXT: [1]: #uOps |
| # CHECK-NEXT: [2]: Latency |
| # CHECK-NEXT: [3]: RThroughput |
| # CHECK-NEXT: [4]: MayLoad |
| # CHECK-NEXT: [5]: MayStore |
| # CHECK-NEXT: [6]: HasSideEffects (U) |
| |
| # CHECK: [1] [2] [3] [4] [5] [6] Instructions: |
| # CHECK-NEXT: 1 7 7.00 div a0, a1, a2 |
| # CHECK-NEXT: 1 4 1.00 mul a4, a1, a2 |
| # CHECK-NEXT: 1 5 1.00 fmul.s ft1, ft2, ft3 |
| # CHECK-NEXT: 1 4 1.00 * lw a3, 0(a0) |
| # CHECK-NEXT: 1 3 1.00 * sw a3, 0(a1) |
| # CHECK-NEXT: 1 1 0.50 add a5, a1, a2 |
| # CHECK-NEXT: 1 1 0.50 ror a6, a5, a2 |
| # CHECK-NEXT: 1 1 1.00 j .Lend |
| # CHECK-NEXT: 1 1 0.50 add a7, a4, a0 |
| # CHECK-NEXT: 1 0 0.50 nop |
| |
| # CHECK: Resources: |
| # CHECK-NEXT: [0.0] - p8700AGQ |
| # CHECK-NEXT: [0.1] - p8700AGQ |
| # CHECK-NEXT: [0.2] - p8700AGQ |
| # CHECK-NEXT: [1] - p8700ALQ |
| # CHECK-NEXT: [2.0] - p8700FPQ |
| # CHECK-NEXT: [2.1] - p8700FPQ |
| # CHECK-NEXT: [2.2] - p8700FPQ |
| # CHECK-NEXT: [3] - p8700FpuApu |
| # CHECK-NEXT: [4] - p8700FpuLong |
| # CHECK-NEXT: [5] - p8700GpDiv |
| # CHECK-NEXT: [6] - p8700GpMul |
| # CHECK-NEXT: [7] - p8700IssueAL2 |
| # CHECK-NEXT: [8] - p8700IssueCTI |
| # CHECK-NEXT: [9] - p8700IssueFPUL |
| # CHECK-NEXT: [10] - p8700IssueFPUS |
| # CHECK-NEXT: [11] - p8700IssueLSU |
| |
| # CHECK: Resource pressure per iteration: |
| # CHECK-NEXT: [0.0] [0.1] [0.2] [1] [2.0] [2.1] [2.2] [3] [4] [5] [6] [7] [8] [9] [10] [11] |
| # CHECK-NEXT: 1.00 1.00 1.00 2.00 - - - 1.00 1.00 7.00 1.00 2.00 1.00 - - 2.00 |
| |
| # CHECK: Resource pressure by instruction: |
| # CHECK-NEXT: [0.0] [0.1] [0.2] [1] [2.0] [2.1] [2.2] [3] [4] [5] [6] [7] [8] [9] [10] [11] Instructions: |
| # CHECK-NEXT: - - - - - - - - - 7.00 - - - - - - div a0, a1, a2 |
| # CHECK-NEXT: - - - - - - - - - - 1.00 - - - - - mul a4, a1, a2 |
| # CHECK-NEXT: - - - - - - - 1.00 1.00 - - - - - - - fmul.s ft1, ft2, ft3 |
| # CHECK-NEXT: - 1.00 - - - - - - - - - - - - - 1.00 lw a3, 0(a0) |
| # CHECK-NEXT: 1.00 - - - - - - - - - - - - - - 1.00 sw a3, 0(a1) |
| # CHECK-NEXT: - - - - - - - - - - - 1.00 - - - - add a5, a1, a2 |
| # CHECK-NEXT: - - - 1.00 - - - - - - - - - - - - ror a6, a5, a2 |
| # CHECK-NEXT: - - 1.00 - - - - - - - - - 1.00 - - - j .Lend |
| # CHECK-NEXT: - - - 1.00 - - - - - - - - - - - - add a7, a4, a0 |
| # CHECK-NEXT: - - - - - - - - - - - 1.00 - - - - nop |
| |
| # CHECK: Timeline view: |
| # CHECK-NEXT: 0123456 |
| # CHECK-NEXT: Index 0123456789 |
| |
| # CHECK: [0,0] DeeeeeeeER. .. div a0, a1, a2 |
| # CHECK-NEXT: [0,1] DeeeeE---R. .. mul a4, a1, a2 |
| # CHECK-NEXT: [0,2] DeeeeeE--R. .. fmul.s ft1, ft2, ft3 |
| # CHECK-NEXT: [0,3] D=======eeeeER .. lw a3, 0(a0) |
| # CHECK-NEXT: [0,4] .D==========eeeER sw a3, 0(a1) |
| # CHECK-NEXT: [0,5] .DeE------------R add a5, a1, a2 |
| # CHECK-NEXT: [0,6] .D=eE-----------R ror a6, a5, a2 |
| # CHECK-NEXT: [0,7] .DeE------------R j .Lend |
| # CHECK-NEXT: [0,8] . D=====eE------R add a7, a4, a0 |
| # CHECK-NEXT: [0,9] . DE------------R nop |
| |
| # CHECK: Average Wait times (based on the timeline view): |
| # CHECK-NEXT: [0]: Executions |
| # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue |
| # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready |
| # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage |
| |
| # CHECK: [0] [1] [2] [3] |
| # CHECK-NEXT: 0. 1 1.0 1.0 0.0 div a0, a1, a2 |
| # CHECK-NEXT: 1. 1 1.0 1.0 3.0 mul a4, a1, a2 |
| # CHECK-NEXT: 2. 1 1.0 1.0 2.0 fmul.s ft1, ft2, ft3 |
| # CHECK-NEXT: 3. 1 8.0 0.0 0.0 lw a3, 0(a0) |
| # CHECK-NEXT: 4. 1 11.0 0.0 0.0 sw a3, 0(a1) |
| # CHECK-NEXT: 5. 1 1.0 1.0 12.0 add a5, a1, a2 |
| # CHECK-NEXT: 6. 1 2.0 0.0 11.0 ror a6, a5, a2 |
| # CHECK-NEXT: 7. 1 1.0 1.0 12.0 j .Lend |
| # CHECK-NEXT: 8. 1 6.0 0.0 6.0 add a7, a4, a0 |
| # CHECK-NEXT: 9. 1 1.0 1.0 12.0 nop |
| # CHECK-NEXT: 1 3.3 0.6 5.8 <total> |
