# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py # RUN: llvm-mca -mtriple=aarch64 -mcpu=neoverse-v1 --timeline --timeline-max-iterations=4 < %s | FileCheck %s # LLVM-MCA-BEGIN GPR32-bit ldr w0, [sp] add x0, x0, x0 # LLVM-MCA-END # LLVM-MCA-BEGIN FPR8-bit ldr b0, [sp] fadd d0, d0, d0 # LLVM-MCA-END # LLVM-MCA-BEGIN FPR16-bit ldr h0, [sp] fadd d0, d0, d0 # LLVM-MCA-END # LLVM-MCA-BEGIN FPR32-bit ldr s0, [sp] fadd d0, d0, d0 # LLVM-MCA-END # LLVM-MCA-BEGIN SIMD64-bit-b ld1 {v0.8b}, [sp] add v0.16b, v0.16b, v0.16b # LLVM-MCA-END # LLVM-MCA-BEGIN SIMD64-bit-h ld1 {v0.4h}, [sp] add v0.8h, v0.8h, v0.8h # LLVM-MCA-END # LLVM-MCA-BEGIN SIMD64-bit-s ld1 {v0.2s}, [sp] add v0.4s, v0.4s, v0.4s # LLVM-MCA-END # LLVM-MCA-BEGIN SIMD64-bit-d ld1 {v0.1d}, [sp] add v0.2d, v0.2d, v0.2d # LLVM-MCA-END # LLVM-MCA-BEGIN ins ins v0.b[0], v1.b[1] add v0.16b, v0.16b, v0.16b # LLVM-MCA-END # LLVM-MCA-BEGIN lanewise-load ld1 {v0.b}[0], [sp] add v0.16b, v0.16b, v0.16b # LLVM-MCA-END # CHECK: [0] Code Region - GPR32-bit # CHECK: Iterations: 100 # CHECK-NEXT: Instructions: 200 # CHECK-NEXT: Total Cycles: 41 # CHECK-NEXT: Total uOps: 200 # CHECK: Dispatch Width: 8 # CHECK-NEXT: uOps Per Cycle: 4.88 # CHECK-NEXT: IPC: 4.88 # CHECK-NEXT: Block RThroughput: 0.3 # 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 4 0.33 * ldr w0, [sp] # CHECK-NEXT: 1 1 0.25 add x0, x0, x0 # CHECK: Resources: # CHECK-NEXT: [0.0] - V1UnitB # CHECK-NEXT: [0.1] - V1UnitB # CHECK-NEXT: [1.0] - V1UnitD # CHECK-NEXT: [1.1] - V1UnitD # CHECK-NEXT: [2.0] - V1UnitFlg # CHECK-NEXT: [2.1] - V1UnitFlg # CHECK-NEXT: [2.2] - V1UnitFlg # CHECK-NEXT: [3] - V1UnitL2 # CHECK-NEXT: [4.0] - V1UnitL01 # CHECK-NEXT: [4.1] - V1UnitL01 # CHECK-NEXT: [5] - V1UnitM0 # CHECK-NEXT: [6] - V1UnitM1 # CHECK-NEXT: [7.0] - V1UnitS # CHECK-NEXT: [7.1] - V1UnitS # CHECK-NEXT: [8] - V1UnitV0 # CHECK-NEXT: [9] - V1UnitV1 # CHECK-NEXT: [10] - V1UnitV2 # CHECK-NEXT: [11] - V1UnitV3 # CHECK: Resource pressure per iteration: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 0.22 0.22 0.28 0.28 - - - - # CHECK: Resource pressure by instruction: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] Instructions: # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ldr w0, [sp] # CHECK-NEXT: - - - - - - - - - - 0.22 0.22 0.28 0.28 - - - - add x0, x0, x0 # CHECK: Timeline view: # CHECK-NEXT: Index 012345678 # CHECK: [0,0] DeeeeER . ldr w0, [sp] # CHECK-NEXT: [0,1] D====eER. add x0, x0, x0 # CHECK-NEXT: [1,0] DeeeeE-R. ldr w0, [sp] # CHECK-NEXT: [1,1] D====eER. add x0, x0, x0 # CHECK-NEXT: [2,0] DeeeeE-R. ldr w0, [sp] # CHECK-NEXT: [2,1] D====eER. add x0, x0, x0 # CHECK-NEXT: [3,0] D=eeeeER. ldr w0, [sp] # CHECK-NEXT: [3,1] D=====eER add x0, x0, x0 # 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. 4 1.3 1.3 0.5 ldr w0, [sp] # CHECK-NEXT: 1. 4 5.3 0.0 0.0 add x0, x0, x0 # CHECK-NEXT: 8 3.3 0.6 0.3 # CHECK: [1] Code Region - FPR8-bit # CHECK: Iterations: 100 # CHECK-NEXT: Instructions: 200 # CHECK-NEXT: Total Cycles: 44 # CHECK-NEXT: Total uOps: 200 # CHECK: Dispatch Width: 8 # CHECK-NEXT: uOps Per Cycle: 4.55 # CHECK-NEXT: IPC: 4.55 # CHECK-NEXT: Block RThroughput: 0.3 # 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 6 0.33 * ldr b0, [sp] # CHECK-NEXT: 1 2 0.25 fadd d0, d0, d0 # CHECK: Resources: # CHECK-NEXT: [0.0] - V1UnitB # CHECK-NEXT: [0.1] - V1UnitB # CHECK-NEXT: [1.0] - V1UnitD # CHECK-NEXT: [1.1] - V1UnitD # CHECK-NEXT: [2.0] - V1UnitFlg # CHECK-NEXT: [2.1] - V1UnitFlg # CHECK-NEXT: [2.2] - V1UnitFlg # CHECK-NEXT: [3] - V1UnitL2 # CHECK-NEXT: [4.0] - V1UnitL01 # CHECK-NEXT: [4.1] - V1UnitL01 # CHECK-NEXT: [5] - V1UnitM0 # CHECK-NEXT: [6] - V1UnitM1 # CHECK-NEXT: [7.0] - V1UnitS # CHECK-NEXT: [7.1] - V1UnitS # CHECK-NEXT: [8] - V1UnitV0 # CHECK-NEXT: [9] - V1UnitV1 # CHECK-NEXT: [10] - V1UnitV2 # CHECK-NEXT: [11] - V1UnitV3 # CHECK: Resource pressure per iteration: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25 # CHECK: Resource pressure by instruction: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] Instructions: # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ldr b0, [sp] # CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 fadd d0, d0, d0 # CHECK: Timeline view: # CHECK-NEXT: 01 # CHECK-NEXT: Index 0123456789 # CHECK: [0,0] DeeeeeeER .. ldr b0, [sp] # CHECK-NEXT: [0,1] D======eeER. fadd d0, d0, d0 # CHECK-NEXT: [1,0] DeeeeeeE--R. ldr b0, [sp] # CHECK-NEXT: [1,1] D======eeER. fadd d0, d0, d0 # CHECK-NEXT: [2,0] DeeeeeeE--R. ldr b0, [sp] # CHECK-NEXT: [2,1] D======eeER. fadd d0, d0, d0 # CHECK-NEXT: [3,0] D=eeeeeeE-R. ldr b0, [sp] # CHECK-NEXT: [3,1] D=======eeER fadd d0, d0, d0 # 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. 4 1.3 1.3 1.3 ldr b0, [sp] # CHECK-NEXT: 1. 4 7.3 0.0 0.0 fadd d0, d0, d0 # CHECK-NEXT: 8 4.3 0.6 0.6 # CHECK: [2] Code Region - FPR16-bit # CHECK: Iterations: 100 # CHECK-NEXT: Instructions: 200 # CHECK-NEXT: Total Cycles: 44 # CHECK-NEXT: Total uOps: 200 # CHECK: Dispatch Width: 8 # CHECK-NEXT: uOps Per Cycle: 4.55 # CHECK-NEXT: IPC: 4.55 # CHECK-NEXT: Block RThroughput: 0.3 # 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 6 0.33 * ldr h0, [sp] # CHECK-NEXT: 1 2 0.25 fadd d0, d0, d0 # CHECK: Resources: # CHECK-NEXT: [0.0] - V1UnitB # CHECK-NEXT: [0.1] - V1UnitB # CHECK-NEXT: [1.0] - V1UnitD # CHECK-NEXT: [1.1] - V1UnitD # CHECK-NEXT: [2.0] - V1UnitFlg # CHECK-NEXT: [2.1] - V1UnitFlg # CHECK-NEXT: [2.2] - V1UnitFlg # CHECK-NEXT: [3] - V1UnitL2 # CHECK-NEXT: [4.0] - V1UnitL01 # CHECK-NEXT: [4.1] - V1UnitL01 # CHECK-NEXT: [5] - V1UnitM0 # CHECK-NEXT: [6] - V1UnitM1 # CHECK-NEXT: [7.0] - V1UnitS # CHECK-NEXT: [7.1] - V1UnitS # CHECK-NEXT: [8] - V1UnitV0 # CHECK-NEXT: [9] - V1UnitV1 # CHECK-NEXT: [10] - V1UnitV2 # CHECK-NEXT: [11] - V1UnitV3 # CHECK: Resource pressure per iteration: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25 # CHECK: Resource pressure by instruction: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] Instructions: # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ldr h0, [sp] # CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 fadd d0, d0, d0 # CHECK: Timeline view: # CHECK-NEXT: 01 # CHECK-NEXT: Index 0123456789 # CHECK: [0,0] DeeeeeeER .. ldr h0, [sp] # CHECK-NEXT: [0,1] D======eeER. fadd d0, d0, d0 # CHECK-NEXT: [1,0] DeeeeeeE--R. ldr h0, [sp] # CHECK-NEXT: [1,1] D======eeER. fadd d0, d0, d0 # CHECK-NEXT: [2,0] DeeeeeeE--R. ldr h0, [sp] # CHECK-NEXT: [2,1] D======eeER. fadd d0, d0, d0 # CHECK-NEXT: [3,0] D=eeeeeeE-R. ldr h0, [sp] # CHECK-NEXT: [3,1] D=======eeER fadd d0, d0, d0 # 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. 4 1.3 1.3 1.3 ldr h0, [sp] # CHECK-NEXT: 1. 4 7.3 0.0 0.0 fadd d0, d0, d0 # CHECK-NEXT: 8 4.3 0.6 0.6 # CHECK: [3] Code Region - FPR32-bit # CHECK: Iterations: 100 # CHECK-NEXT: Instructions: 200 # CHECK-NEXT: Total Cycles: 44 # CHECK-NEXT: Total uOps: 200 # CHECK: Dispatch Width: 8 # CHECK-NEXT: uOps Per Cycle: 4.55 # CHECK-NEXT: IPC: 4.55 # CHECK-NEXT: Block RThroughput: 0.3 # 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 6 0.33 * ldr s0, [sp] # CHECK-NEXT: 1 2 0.25 fadd d0, d0, d0 # CHECK: Resources: # CHECK-NEXT: [0.0] - V1UnitB # CHECK-NEXT: [0.1] - V1UnitB # CHECK-NEXT: [1.0] - V1UnitD # CHECK-NEXT: [1.1] - V1UnitD # CHECK-NEXT: [2.0] - V1UnitFlg # CHECK-NEXT: [2.1] - V1UnitFlg # CHECK-NEXT: [2.2] - V1UnitFlg # CHECK-NEXT: [3] - V1UnitL2 # CHECK-NEXT: [4.0] - V1UnitL01 # CHECK-NEXT: [4.1] - V1UnitL01 # CHECK-NEXT: [5] - V1UnitM0 # CHECK-NEXT: [6] - V1UnitM1 # CHECK-NEXT: [7.0] - V1UnitS # CHECK-NEXT: [7.1] - V1UnitS # CHECK-NEXT: [8] - V1UnitV0 # CHECK-NEXT: [9] - V1UnitV1 # CHECK-NEXT: [10] - V1UnitV2 # CHECK-NEXT: [11] - V1UnitV3 # CHECK: Resource pressure per iteration: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25 # CHECK: Resource pressure by instruction: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] Instructions: # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ldr s0, [sp] # CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 fadd d0, d0, d0 # CHECK: Timeline view: # CHECK-NEXT: 01 # CHECK-NEXT: Index 0123456789 # CHECK: [0,0] DeeeeeeER .. ldr s0, [sp] # CHECK-NEXT: [0,1] D======eeER. fadd d0, d0, d0 # CHECK-NEXT: [1,0] DeeeeeeE--R. ldr s0, [sp] # CHECK-NEXT: [1,1] D======eeER. fadd d0, d0, d0 # CHECK-NEXT: [2,0] DeeeeeeE--R. ldr s0, [sp] # CHECK-NEXT: [2,1] D======eeER. fadd d0, d0, d0 # CHECK-NEXT: [3,0] D=eeeeeeE-R. ldr s0, [sp] # CHECK-NEXT: [3,1] D=======eeER fadd d0, d0, d0 # 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. 4 1.3 1.3 1.3 ldr s0, [sp] # CHECK-NEXT: 1. 4 7.3 0.0 0.0 fadd d0, d0, d0 # CHECK-NEXT: 8 4.3 0.6 0.6 # CHECK: [4] Code Region - SIMD64-bit-b # CHECK: Iterations: 100 # CHECK-NEXT: Instructions: 200 # CHECK-NEXT: Total Cycles: 44 # CHECK-NEXT: Total uOps: 200 # CHECK: Dispatch Width: 8 # CHECK-NEXT: uOps Per Cycle: 4.55 # CHECK-NEXT: IPC: 4.55 # CHECK-NEXT: Block RThroughput: 0.3 # 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 6 0.33 * ld1 { v0.8b }, [sp] # CHECK-NEXT: 1 2 0.25 add v0.16b, v0.16b, v0.16b # CHECK: Resources: # CHECK-NEXT: [0.0] - V1UnitB # CHECK-NEXT: [0.1] - V1UnitB # CHECK-NEXT: [1.0] - V1UnitD # CHECK-NEXT: [1.1] - V1UnitD # CHECK-NEXT: [2.0] - V1UnitFlg # CHECK-NEXT: [2.1] - V1UnitFlg # CHECK-NEXT: [2.2] - V1UnitFlg # CHECK-NEXT: [3] - V1UnitL2 # CHECK-NEXT: [4.0] - V1UnitL01 # CHECK-NEXT: [4.1] - V1UnitL01 # CHECK-NEXT: [5] - V1UnitM0 # CHECK-NEXT: [6] - V1UnitM1 # CHECK-NEXT: [7.0] - V1UnitS # CHECK-NEXT: [7.1] - V1UnitS # CHECK-NEXT: [8] - V1UnitV0 # CHECK-NEXT: [9] - V1UnitV1 # CHECK-NEXT: [10] - V1UnitV2 # CHECK-NEXT: [11] - V1UnitV3 # CHECK: Resource pressure per iteration: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25 # CHECK: Resource pressure by instruction: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] Instructions: # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ld1 { v0.8b }, [sp] # CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 add v0.16b, v0.16b, v0.16b # CHECK: Timeline view: # CHECK-NEXT: 01 # CHECK-NEXT: Index 0123456789 # CHECK: [0,0] DeeeeeeER .. ld1 { v0.8b }, [sp] # CHECK-NEXT: [0,1] D======eeER. add v0.16b, v0.16b, v0.16b # CHECK-NEXT: [1,0] DeeeeeeE--R. ld1 { v0.8b }, [sp] # CHECK-NEXT: [1,1] D======eeER. add v0.16b, v0.16b, v0.16b # CHECK-NEXT: [2,0] DeeeeeeE--R. ld1 { v0.8b }, [sp] # CHECK-NEXT: [2,1] D======eeER. add v0.16b, v0.16b, v0.16b # CHECK-NEXT: [3,0] D=eeeeeeE-R. ld1 { v0.8b }, [sp] # CHECK-NEXT: [3,1] D=======eeER add v0.16b, v0.16b, v0.16b # 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. 4 1.3 1.3 1.3 ld1 { v0.8b }, [sp] # CHECK-NEXT: 1. 4 7.3 0.0 0.0 add v0.16b, v0.16b, v0.16b # CHECK-NEXT: 8 4.3 0.6 0.6 # CHECK: [5] Code Region - SIMD64-bit-h # CHECK: Iterations: 100 # CHECK-NEXT: Instructions: 200 # CHECK-NEXT: Total Cycles: 44 # CHECK-NEXT: Total uOps: 200 # CHECK: Dispatch Width: 8 # CHECK-NEXT: uOps Per Cycle: 4.55 # CHECK-NEXT: IPC: 4.55 # CHECK-NEXT: Block RThroughput: 0.3 # 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 6 0.33 * ld1 { v0.4h }, [sp] # CHECK-NEXT: 1 2 0.25 add v0.8h, v0.8h, v0.8h # CHECK: Resources: # CHECK-NEXT: [0.0] - V1UnitB # CHECK-NEXT: [0.1] - V1UnitB # CHECK-NEXT: [1.0] - V1UnitD # CHECK-NEXT: [1.1] - V1UnitD # CHECK-NEXT: [2.0] - V1UnitFlg # CHECK-NEXT: [2.1] - V1UnitFlg # CHECK-NEXT: [2.2] - V1UnitFlg # CHECK-NEXT: [3] - V1UnitL2 # CHECK-NEXT: [4.0] - V1UnitL01 # CHECK-NEXT: [4.1] - V1UnitL01 # CHECK-NEXT: [5] - V1UnitM0 # CHECK-NEXT: [6] - V1UnitM1 # CHECK-NEXT: [7.0] - V1UnitS # CHECK-NEXT: [7.1] - V1UnitS # CHECK-NEXT: [8] - V1UnitV0 # CHECK-NEXT: [9] - V1UnitV1 # CHECK-NEXT: [10] - V1UnitV2 # CHECK-NEXT: [11] - V1UnitV3 # CHECK: Resource pressure per iteration: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25 # CHECK: Resource pressure by instruction: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] Instructions: # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ld1 { v0.4h }, [sp] # CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 add v0.8h, v0.8h, v0.8h # CHECK: Timeline view: # CHECK-NEXT: 01 # CHECK-NEXT: Index 0123456789 # CHECK: [0,0] DeeeeeeER .. ld1 { v0.4h }, [sp] # CHECK-NEXT: [0,1] D======eeER. add v0.8h, v0.8h, v0.8h # CHECK-NEXT: [1,0] DeeeeeeE--R. ld1 { v0.4h }, [sp] # CHECK-NEXT: [1,1] D======eeER. add v0.8h, v0.8h, v0.8h # CHECK-NEXT: [2,0] DeeeeeeE--R. ld1 { v0.4h }, [sp] # CHECK-NEXT: [2,1] D======eeER. add v0.8h, v0.8h, v0.8h # CHECK-NEXT: [3,0] D=eeeeeeE-R. ld1 { v0.4h }, [sp] # CHECK-NEXT: [3,1] D=======eeER add v0.8h, v0.8h, v0.8h # 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. 4 1.3 1.3 1.3 ld1 { v0.4h }, [sp] # CHECK-NEXT: 1. 4 7.3 0.0 0.0 add v0.8h, v0.8h, v0.8h # CHECK-NEXT: 8 4.3 0.6 0.6 # CHECK: [6] Code Region - SIMD64-bit-s # CHECK: Iterations: 100 # CHECK-NEXT: Instructions: 200 # CHECK-NEXT: Total Cycles: 44 # CHECK-NEXT: Total uOps: 200 # CHECK: Dispatch Width: 8 # CHECK-NEXT: uOps Per Cycle: 4.55 # CHECK-NEXT: IPC: 4.55 # CHECK-NEXT: Block RThroughput: 0.3 # 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 6 0.33 * ld1 { v0.2s }, [sp] # CHECK-NEXT: 1 2 0.25 add v0.4s, v0.4s, v0.4s # CHECK: Resources: # CHECK-NEXT: [0.0] - V1UnitB # CHECK-NEXT: [0.1] - V1UnitB # CHECK-NEXT: [1.0] - V1UnitD # CHECK-NEXT: [1.1] - V1UnitD # CHECK-NEXT: [2.0] - V1UnitFlg # CHECK-NEXT: [2.1] - V1UnitFlg # CHECK-NEXT: [2.2] - V1UnitFlg # CHECK-NEXT: [3] - V1UnitL2 # CHECK-NEXT: [4.0] - V1UnitL01 # CHECK-NEXT: [4.1] - V1UnitL01 # CHECK-NEXT: [5] - V1UnitM0 # CHECK-NEXT: [6] - V1UnitM1 # CHECK-NEXT: [7.0] - V1UnitS # CHECK-NEXT: [7.1] - V1UnitS # CHECK-NEXT: [8] - V1UnitV0 # CHECK-NEXT: [9] - V1UnitV1 # CHECK-NEXT: [10] - V1UnitV2 # CHECK-NEXT: [11] - V1UnitV3 # CHECK: Resource pressure per iteration: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25 # CHECK: Resource pressure by instruction: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] Instructions: # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ld1 { v0.2s }, [sp] # CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 add v0.4s, v0.4s, v0.4s # CHECK: Timeline view: # CHECK-NEXT: 01 # CHECK-NEXT: Index 0123456789 # CHECK: [0,0] DeeeeeeER .. ld1 { v0.2s }, [sp] # CHECK-NEXT: [0,1] D======eeER. add v0.4s, v0.4s, v0.4s # CHECK-NEXT: [1,0] DeeeeeeE--R. ld1 { v0.2s }, [sp] # CHECK-NEXT: [1,1] D======eeER. add v0.4s, v0.4s, v0.4s # CHECK-NEXT: [2,0] DeeeeeeE--R. ld1 { v0.2s }, [sp] # CHECK-NEXT: [2,1] D======eeER. add v0.4s, v0.4s, v0.4s # CHECK-NEXT: [3,0] D=eeeeeeE-R. ld1 { v0.2s }, [sp] # CHECK-NEXT: [3,1] D=======eeER add v0.4s, v0.4s, v0.4s # 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. 4 1.3 1.3 1.3 ld1 { v0.2s }, [sp] # CHECK-NEXT: 1. 4 7.3 0.0 0.0 add v0.4s, v0.4s, v0.4s # CHECK-NEXT: 8 4.3 0.6 0.6 # CHECK: [7] Code Region - SIMD64-bit-d # CHECK: Iterations: 100 # CHECK-NEXT: Instructions: 200 # CHECK-NEXT: Total Cycles: 44 # CHECK-NEXT: Total uOps: 200 # CHECK: Dispatch Width: 8 # CHECK-NEXT: uOps Per Cycle: 4.55 # CHECK-NEXT: IPC: 4.55 # CHECK-NEXT: Block RThroughput: 0.3 # 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 6 0.33 * ld1 { v0.1d }, [sp] # CHECK-NEXT: 1 2 0.25 add v0.2d, v0.2d, v0.2d # CHECK: Resources: # CHECK-NEXT: [0.0] - V1UnitB # CHECK-NEXT: [0.1] - V1UnitB # CHECK-NEXT: [1.0] - V1UnitD # CHECK-NEXT: [1.1] - V1UnitD # CHECK-NEXT: [2.0] - V1UnitFlg # CHECK-NEXT: [2.1] - V1UnitFlg # CHECK-NEXT: [2.2] - V1UnitFlg # CHECK-NEXT: [3] - V1UnitL2 # CHECK-NEXT: [4.0] - V1UnitL01 # CHECK-NEXT: [4.1] - V1UnitL01 # CHECK-NEXT: [5] - V1UnitM0 # CHECK-NEXT: [6] - V1UnitM1 # CHECK-NEXT: [7.0] - V1UnitS # CHECK-NEXT: [7.1] - V1UnitS # CHECK-NEXT: [8] - V1UnitV0 # CHECK-NEXT: [9] - V1UnitV1 # CHECK-NEXT: [10] - V1UnitV2 # CHECK-NEXT: [11] - V1UnitV3 # CHECK: Resource pressure per iteration: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25 # CHECK: Resource pressure by instruction: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] Instructions: # CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ld1 { v0.1d }, [sp] # CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 add v0.2d, v0.2d, v0.2d # CHECK: Timeline view: # CHECK-NEXT: 01 # CHECK-NEXT: Index 0123456789 # CHECK: [0,0] DeeeeeeER .. ld1 { v0.1d }, [sp] # CHECK-NEXT: [0,1] D======eeER. add v0.2d, v0.2d, v0.2d # CHECK-NEXT: [1,0] DeeeeeeE--R. ld1 { v0.1d }, [sp] # CHECK-NEXT: [1,1] D======eeER. add v0.2d, v0.2d, v0.2d # CHECK-NEXT: [2,0] DeeeeeeE--R. ld1 { v0.1d }, [sp] # CHECK-NEXT: [2,1] D======eeER. add v0.2d, v0.2d, v0.2d # CHECK-NEXT: [3,0] D=eeeeeeE-R. ld1 { v0.1d }, [sp] # CHECK-NEXT: [3,1] D=======eeER add v0.2d, v0.2d, v0.2d # 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. 4 1.3 1.3 1.3 ld1 { v0.1d }, [sp] # CHECK-NEXT: 1. 4 7.3 0.0 0.0 add v0.2d, v0.2d, v0.2d # CHECK-NEXT: 8 4.3 0.6 0.6 # CHECK: [8] Code Region - ins # CHECK: Iterations: 100 # CHECK-NEXT: Instructions: 200 # CHECK-NEXT: Total Cycles: 403 # CHECK-NEXT: Total uOps: 200 # CHECK: Dispatch Width: 8 # CHECK-NEXT: uOps Per Cycle: 0.50 # CHECK-NEXT: IPC: 0.50 # CHECK-NEXT: Block RThroughput: 0.5 # 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 2 0.25 mov v0.b[0], v1.b[1] # CHECK-NEXT: 1 2 0.25 add v0.16b, v0.16b, v0.16b # CHECK: Resources: # CHECK-NEXT: [0.0] - V1UnitB # CHECK-NEXT: [0.1] - V1UnitB # CHECK-NEXT: [1.0] - V1UnitD # CHECK-NEXT: [1.1] - V1UnitD # CHECK-NEXT: [2.0] - V1UnitFlg # CHECK-NEXT: [2.1] - V1UnitFlg # CHECK-NEXT: [2.2] - V1UnitFlg # CHECK-NEXT: [3] - V1UnitL2 # CHECK-NEXT: [4.0] - V1UnitL01 # CHECK-NEXT: [4.1] - V1UnitL01 # CHECK-NEXT: [5] - V1UnitM0 # CHECK-NEXT: [6] - V1UnitM1 # CHECK-NEXT: [7.0] - V1UnitS # CHECK-NEXT: [7.1] - V1UnitS # CHECK-NEXT: [8] - V1UnitV0 # CHECK-NEXT: [9] - V1UnitV1 # CHECK-NEXT: [10] - V1UnitV2 # CHECK-NEXT: [11] - V1UnitV3 # CHECK: Resource pressure per iteration: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] # CHECK-NEXT: - - - - - - - - - - - - - - 0.50 0.50 0.50 0.50 # CHECK: Resource pressure by instruction: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] Instructions: # CHECK-NEXT: - - - - - - - - - - - - - - - 0.50 - 0.50 mov v0.b[0], v1.b[1] # CHECK-NEXT: - - - - - - - - - - - - - - 0.50 - 0.50 - add v0.16b, v0.16b, v0.16b # CHECK: Timeline view: # CHECK-NEXT: 012345678 # CHECK-NEXT: Index 0123456789 # CHECK: [0,0] DeeER. . . . mov v0.b[0], v1.b[1] # CHECK-NEXT: [0,1] D==eeER . . . add v0.16b, v0.16b, v0.16b # CHECK-NEXT: [1,0] D====eeER . . . mov v0.b[0], v1.b[1] # CHECK-NEXT: [1,1] D======eeER . . add v0.16b, v0.16b, v0.16b # CHECK-NEXT: [2,0] D========eeER . . mov v0.b[0], v1.b[1] # CHECK-NEXT: [2,1] D==========eeER. . add v0.16b, v0.16b, v0.16b # CHECK-NEXT: [3,0] D============eeER . mov v0.b[0], v1.b[1] # CHECK-NEXT: [3,1] D==============eeER add v0.16b, v0.16b, v0.16b # 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. 4 7.0 0.3 0.0 mov v0.b[0], v1.b[1] # CHECK-NEXT: 1. 4 9.0 0.0 0.0 add v0.16b, v0.16b, v0.16b # CHECK-NEXT: 8 8.0 0.1 0.0 # CHECK: [9] Code Region - lanewise-load # CHECK: Iterations: 100 # CHECK-NEXT: Instructions: 200 # CHECK-NEXT: Total Cycles: 1003 # CHECK-NEXT: Total uOps: 300 # CHECK: Dispatch Width: 8 # CHECK-NEXT: uOps Per Cycle: 0.30 # CHECK-NEXT: IPC: 0.20 # CHECK-NEXT: Block RThroughput: 0.5 # 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: 2 8 0.33 * ld1 { v0.b }[0], [sp] # CHECK-NEXT: 1 2 0.25 add v0.16b, v0.16b, v0.16b # CHECK: Resources: # CHECK-NEXT: [0.0] - V1UnitB # CHECK-NEXT: [0.1] - V1UnitB # CHECK-NEXT: [1.0] - V1UnitD # CHECK-NEXT: [1.1] - V1UnitD # CHECK-NEXT: [2.0] - V1UnitFlg # CHECK-NEXT: [2.1] - V1UnitFlg # CHECK-NEXT: [2.2] - V1UnitFlg # CHECK-NEXT: [3] - V1UnitL2 # CHECK-NEXT: [4.0] - V1UnitL01 # CHECK-NEXT: [4.1] - V1UnitL01 # CHECK-NEXT: [5] - V1UnitM0 # CHECK-NEXT: [6] - V1UnitM1 # CHECK-NEXT: [7.0] - V1UnitS # CHECK-NEXT: [7.1] - V1UnitS # CHECK-NEXT: [8] - V1UnitV0 # CHECK-NEXT: [9] - V1UnitV1 # CHECK-NEXT: [10] - V1UnitV2 # CHECK-NEXT: [11] - V1UnitV3 # CHECK: Resource pressure per iteration: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] # CHECK-NEXT: - - - - - - - - 0.50 0.50 - - - - 0.50 0.50 0.50 0.50 # CHECK: Resource pressure by instruction: # CHECK-NEXT: [0.0] [0.1] [1.0] [1.1] [2.0] [2.1] [2.2] [3] [4.0] [4.1] [5] [6] [7.0] [7.1] [8] [9] [10] [11] Instructions: # CHECK-NEXT: - - - - - - - - 0.50 0.50 - - - - - 0.50 - 0.50 ld1 { v0.b }[0], [sp] # CHECK-NEXT: - - - - - - - - - - - - - - 0.50 - 0.50 - add v0.16b, v0.16b, v0.16b # CHECK: Timeline view: # CHECK-NEXT: 0123456789 0123456789 # CHECK-NEXT: Index 0123456789 0123456789 012 # CHECK: [0,0] DeeeeeeeeER . . . . . . . ld1 { v0.b }[0], [sp] # CHECK-NEXT: [0,1] D========eeER . . . . . . . add v0.16b, v0.16b, v0.16b # CHECK-NEXT: [1,0] D==========eeeeeeeeER . . . . . ld1 { v0.b }[0], [sp] # CHECK-NEXT: [1,1] D==================eeER . . . . . add v0.16b, v0.16b, v0.16b # CHECK-NEXT: [2,0] D====================eeeeeeeeER . . . ld1 { v0.b }[0], [sp] # CHECK-NEXT: [2,1] .D===========================eeER . . . add v0.16b, v0.16b, v0.16b # CHECK-NEXT: [3,0] .D=============================eeeeeeeeER . ld1 { v0.b }[0], [sp] # CHECK-NEXT: [3,1] .D=====================================eeER add v0.16b, v0.16b, v0.16b # 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. 4 15.8 0.3 0.0 ld1 { v0.b }[0], [sp] # CHECK-NEXT: 1. 4 23.5 0.0 0.0 add v0.16b, v0.16b, v0.16b # CHECK-NEXT: 8 19.6 0.1 0.0