1 # NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py 2 # RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=1500 -timeline -timeline-max-iterations=3 < %s | FileCheck %s 3 4 # perf stat reports a throughput of 0.60 IPC for this code snippet. 5 # Each lzcnt has a false dependency on %ecx; the first lzcnt has to wait on the 6 # imul. However, the folded load can start immediately. 7 # The last lzcnt has a false dependency on %cx. However, even in this case, the 8 # folded load can start immediately. 9 10 imul %edx, %ecx 11 lzcnt (%rsp), %cx 12 lzcnt 2(%rsp), %cx 13 14 # CHECK: Iterations: 1500 15 # CHECK-NEXT: Instructions: 4500 16 # CHECK-NEXT: Total Cycles: 7504 17 # CHECK-NEXT: Dispatch Width: 2 18 # CHECK-NEXT: IPC: 0.60 19 # CHECK-NEXT: Block RThroughput: 2.0 20 21 # CHECK: Instruction Info: 22 # CHECK-NEXT: [1]: #uOps 23 # CHECK-NEXT: [2]: Latency 24 # CHECK-NEXT: [3]: RThroughput 25 # CHECK-NEXT: [4]: MayLoad 26 # CHECK-NEXT: [5]: MayStore 27 # CHECK-NEXT: [6]: HasSideEffects (U) 28 29 # CHECK: [1] [2] [3] [4] [5] [6] Instructions: 30 # CHECK-NEXT: 2 3 1.00 imull %edx, %ecx 31 # CHECK-NEXT: 1 4 1.00 * lzcntw (%rsp), %cx 32 # CHECK-NEXT: 1 4 1.00 * lzcntw 2(%rsp), %cx 33 34 # CHECK: Resources: 35 # CHECK-NEXT: [0] - JALU0 36 # CHECK-NEXT: [1] - JALU1 37 # CHECK-NEXT: [2] - JDiv 38 # CHECK-NEXT: [3] - JFPA 39 # CHECK-NEXT: [4] - JFPM 40 # CHECK-NEXT: [5] - JFPU0 41 # CHECK-NEXT: [6] - JFPU1 42 # CHECK-NEXT: [7] - JLAGU 43 # CHECK-NEXT: [8] - JMul 44 # CHECK-NEXT: [9] - JSAGU 45 # CHECK-NEXT: [10] - JSTC 46 # CHECK-NEXT: [11] - JVALU0 47 # CHECK-NEXT: [12] - JVALU1 48 # CHECK-NEXT: [13] - JVIMUL 49 50 # CHECK: Resource pressure per iteration: 51 # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] 52 # CHECK-NEXT: 1.50 1.50 - - - - - 2.00 1.00 - - - - - 53 54 # CHECK: Resource pressure by instruction: 55 # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: 56 # CHECK-NEXT: - 1.00 - - - - - - 1.00 - - - - - imull %edx, %ecx 57 # CHECK-NEXT: 1.00 - - - - - - 1.00 - - - - - - lzcntw (%rsp), %cx 58 # CHECK-NEXT: 0.50 0.50 - - - - - 1.00 - - - - - - lzcntw 2(%rsp), %cx 59 60 # CHECK: Timeline view: 61 # CHECK-NEXT: 012345678 62 # CHECK-NEXT: Index 0123456789 63 64 # CHECK: [0,0] DeeeER . . . imull %edx, %ecx 65 # CHECK-NEXT: [0,1] .DeeeeER . . . lzcntw (%rsp), %cx 66 # CHECK-NEXT: [0,2] .D=eeeeER . . . lzcntw 2(%rsp), %cx 67 # CHECK-NEXT: [1,0] . D====eeeER . . imull %edx, %ecx 68 # CHECK-NEXT: [1,1] . D===eeeeER . . lzcntw (%rsp), %cx 69 # CHECK-NEXT: [1,2] . D====eeeeER . . lzcntw 2(%rsp), %cx 70 # CHECK-NEXT: [2,0] . D=======eeeER . imull %edx, %ecx 71 # CHECK-NEXT: [2,1] . D======eeeeER. lzcntw (%rsp), %cx 72 # CHECK-NEXT: [2,2] . D=======eeeeER lzcntw 2(%rsp), %cx 73 74 # CHECK: Average Wait times (based on the timeline view): 75 # CHECK-NEXT: [0]: Executions 76 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue 77 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready 78 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage 79 80 # CHECK: [0] [1] [2] [3] 81 # CHECK-NEXT: 0. 3 4.7 0.3 0.0 imull %edx, %ecx 82 # CHECK-NEXT: 1. 3 4.0 0.3 0.0 lzcntw (%rsp), %cx 83 # CHECK-NEXT: 2. 3 5.0 0.0 0.0 lzcntw 2(%rsp), %cx 84
