# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py # RUN: llvm-mca -mtriple=aarch64 -mcpu=neoverse-v2 -instruction-tables < %p/../Inputs/bf16-instructions.s | FileCheck %s # 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 3 0.50 bfcvt h0, s0 # CHECK-NEXT: 2 4 1.00 bfcvtn v0.4h, v0.4s # CHECK-NEXT: 2 4 1.00 bfcvtn2 v0.8h, v0.4s # CHECK-NEXT: 1 2 0.25 bfdot v0.2s, v24.4h, v14.2h[2] # CHECK-NEXT: 1 5 0.25 bfdot v0.2s, v0.4h, v0.4h # CHECK-NEXT: 1 5 0.25 bfdot v0.4s, v0.8h, v0.8h # CHECK-NEXT: 1 5 0.25 bfmlalb v0.4s, v0.8h, v0.8h # CHECK-NEXT: 1 5 0.25 bfmlalb v0.4s, v0.8h, v0.h[3] # CHECK-NEXT: 1 5 0.25 bfmlalt v0.4s, v0.8h, v0.8h # CHECK-NEXT: 1 5 0.25 bfmlalt v0.4s, v0.8h, v0.h[3] # CHECK-NEXT: 1 6 0.25 bfmmla v0.4s, v0.8h, v0.8h # CHECK: Resources: # CHECK-NEXT: [0.0] - V2UnitB # CHECK-NEXT: [0.1] - V2UnitB # CHECK-NEXT: [1.0] - V2UnitD # CHECK-NEXT: [1.1] - V2UnitD # CHECK-NEXT: [2.0] - V2UnitFlg # CHECK-NEXT: [2.1] - V2UnitFlg # CHECK-NEXT: [2.2] - V2UnitFlg # CHECK-NEXT: [3] - V2UnitL2 # CHECK-NEXT: [4.0] - V2UnitL01 # CHECK-NEXT: [4.1] - V2UnitL01 # CHECK-NEXT: [5] - V2UnitM0 # CHECK-NEXT: [6] - V2UnitM1 # CHECK-NEXT: [7] - V2UnitS0 # CHECK-NEXT: [8] - V2UnitS1 # CHECK-NEXT: [9] - V2UnitS2 # CHECK-NEXT: [10] - V2UnitS3 # CHECK-NEXT: [11] - V2UnitV0 # CHECK-NEXT: [12] - V2UnitV1 # CHECK-NEXT: [13] - V2UnitV2 # CHECK-NEXT: [14] - V2UnitV3 # 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] [8] [9] [10] [11] [12] [13] [14] # CHECK-NEXT: - - - - - - - - - - - - - - - - 4.50 2.00 4.50 2.00 # 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] [8] [9] [10] [11] [12] [13] [14] Instructions: # CHECK-NEXT: - - - - - - - - - - - - - - - - 0.50 - 0.50 - bfcvt h0, s0 # CHECK-NEXT: - - - - - - - - - - - - - - - - 1.00 - 1.00 - bfcvtn v0.4h, v0.4s # CHECK-NEXT: - - - - - - - - - - - - - - - - 1.00 - 1.00 - bfcvtn2 v0.8h, v0.4s # CHECK-NEXT: - - - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 bfdot v0.2s, v24.4h, v14.2h[2] # CHECK-NEXT: - - - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 bfdot v0.2s, v0.4h, v0.4h # CHECK-NEXT: - - - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 bfdot v0.4s, v0.8h, v0.8h # CHECK-NEXT: - - - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 bfmlalb v0.4s, v0.8h, v0.8h # CHECK-NEXT: - - - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 bfmlalb v0.4s, v0.8h, v0.h[3] # CHECK-NEXT: - - - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 bfmlalt v0.4s, v0.8h, v0.8h # CHECK-NEXT: - - - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 bfmlalt v0.4s, v0.8h, v0.h[3] # CHECK-NEXT: - - - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 bfmmla v0.4s, v0.8h, v0.8h