822 lines · plain
1# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py2# RUN: llvm-mca -mtriple=aarch64 -mcpu=neoverse-v1 --timeline --timeline-max-iterations=4 < %s | FileCheck %s3 4# LLVM-MCA-BEGIN GPR32-bit5ldr w0, [sp]6add x0, x0, x07# LLVM-MCA-END8 9# LLVM-MCA-BEGIN FPR8-bit10ldr b0, [sp]11fadd d0, d0, d012# LLVM-MCA-END13 14# LLVM-MCA-BEGIN FPR16-bit15ldr h0, [sp]16fadd d0, d0, d017# LLVM-MCA-END18 19# LLVM-MCA-BEGIN FPR32-bit20ldr s0, [sp]21fadd d0, d0, d022# LLVM-MCA-END23 24# LLVM-MCA-BEGIN SIMD64-bit-b25ld1 {v0.8b}, [sp]26add v0.16b, v0.16b, v0.16b27# LLVM-MCA-END28 29# LLVM-MCA-BEGIN SIMD64-bit-h30ld1 {v0.4h}, [sp]31add v0.8h, v0.8h, v0.8h32# LLVM-MCA-END33 34# LLVM-MCA-BEGIN SIMD64-bit-s35ld1 {v0.2s}, [sp]36add v0.4s, v0.4s, v0.4s37# LLVM-MCA-END38 39# LLVM-MCA-BEGIN SIMD64-bit-d40ld1 {v0.1d}, [sp]41add v0.2d, v0.2d, v0.2d42# LLVM-MCA-END43 44# LLVM-MCA-BEGIN ins45ins v0.b[0], v1.b[1]46add v0.16b, v0.16b, v0.16b47# LLVM-MCA-END48 49# LLVM-MCA-BEGIN lanewise-load50ld1 {v0.b}[0], [sp]51add v0.16b, v0.16b, v0.16b52# LLVM-MCA-END53 54# CHECK: [0] Code Region - GPR32-bit55 56# CHECK: Iterations: 10057# CHECK-NEXT: Instructions: 20058# CHECK-NEXT: Total Cycles: 4159# CHECK-NEXT: Total uOps: 20060 61# CHECK: Dispatch Width: 862# CHECK-NEXT: uOps Per Cycle: 4.8863# CHECK-NEXT: IPC: 4.8864# CHECK-NEXT: Block RThroughput: 0.365 66# CHECK: Instruction Info:67# CHECK-NEXT: [1]: #uOps68# CHECK-NEXT: [2]: Latency69# CHECK-NEXT: [3]: RThroughput70# CHECK-NEXT: [4]: MayLoad71# CHECK-NEXT: [5]: MayStore72# CHECK-NEXT: [6]: HasSideEffects (U)73 74# CHECK: [1] [2] [3] [4] [5] [6] Instructions:75# CHECK-NEXT: 1 4 0.33 * ldr w0, [sp]76# CHECK-NEXT: 1 1 0.25 add x0, x0, x077 78# CHECK: Resources:79# CHECK-NEXT: [0.0] - V1UnitB80# CHECK-NEXT: [0.1] - V1UnitB81# CHECK-NEXT: [1.0] - V1UnitD82# CHECK-NEXT: [1.1] - V1UnitD83# CHECK-NEXT: [2.0] - V1UnitFlg84# CHECK-NEXT: [2.1] - V1UnitFlg85# CHECK-NEXT: [2.2] - V1UnitFlg86# CHECK-NEXT: [3] - V1UnitL287# CHECK-NEXT: [4.0] - V1UnitL0188# CHECK-NEXT: [4.1] - V1UnitL0189# CHECK-NEXT: [5] - V1UnitM090# CHECK-NEXT: [6] - V1UnitM191# CHECK-NEXT: [7.0] - V1UnitS92# CHECK-NEXT: [7.1] - V1UnitS93# CHECK-NEXT: [8] - V1UnitV094# CHECK-NEXT: [9] - V1UnitV195# CHECK-NEXT: [10] - V1UnitV296# CHECK-NEXT: [11] - V1UnitV397 98# CHECK: Resource pressure per iteration:99# 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]100# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 0.22 0.22 0.28 0.28 - - - -101 102# CHECK: Resource pressure by instruction:103# 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:104# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ldr w0, [sp]105# CHECK-NEXT: - - - - - - - - - - 0.22 0.22 0.28 0.28 - - - - add x0, x0, x0106 107# CHECK: Timeline view:108# CHECK-NEXT: Index 012345678109 110# CHECK: [0,0] DeeeeER . ldr w0, [sp]111# CHECK-NEXT: [0,1] D====eER. add x0, x0, x0112# CHECK-NEXT: [1,0] DeeeeE-R. ldr w0, [sp]113# CHECK-NEXT: [1,1] D====eER. add x0, x0, x0114# CHECK-NEXT: [2,0] DeeeeE-R. ldr w0, [sp]115# CHECK-NEXT: [2,1] D====eER. add x0, x0, x0116# CHECK-NEXT: [3,0] D=eeeeER. ldr w0, [sp]117# CHECK-NEXT: [3,1] D=====eER add x0, x0, x0118 119# CHECK: Average Wait times (based on the timeline view):120# CHECK-NEXT: [0]: Executions121# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue122# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready123# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage124 125# CHECK: [0] [1] [2] [3]126# CHECK-NEXT: 0. 4 1.3 1.3 0.5 ldr w0, [sp]127# CHECK-NEXT: 1. 4 5.3 0.0 0.0 add x0, x0, x0128# CHECK-NEXT: 4 3.3 0.6 0.3 <total>129 130# CHECK: [1] Code Region - FPR8-bit131 132# CHECK: Iterations: 100133# CHECK-NEXT: Instructions: 200134# CHECK-NEXT: Total Cycles: 44135# CHECK-NEXT: Total uOps: 200136 137# CHECK: Dispatch Width: 8138# CHECK-NEXT: uOps Per Cycle: 4.55139# CHECK-NEXT: IPC: 4.55140# CHECK-NEXT: Block RThroughput: 0.3141 142# CHECK: Instruction Info:143# CHECK-NEXT: [1]: #uOps144# CHECK-NEXT: [2]: Latency145# CHECK-NEXT: [3]: RThroughput146# CHECK-NEXT: [4]: MayLoad147# CHECK-NEXT: [5]: MayStore148# CHECK-NEXT: [6]: HasSideEffects (U)149 150# CHECK: [1] [2] [3] [4] [5] [6] Instructions:151# CHECK-NEXT: 1 6 0.33 * ldr b0, [sp]152# CHECK-NEXT: 1 2 0.25 fadd d0, d0, d0153 154# CHECK: Resources:155# CHECK-NEXT: [0.0] - V1UnitB156# CHECK-NEXT: [0.1] - V1UnitB157# CHECK-NEXT: [1.0] - V1UnitD158# CHECK-NEXT: [1.1] - V1UnitD159# CHECK-NEXT: [2.0] - V1UnitFlg160# CHECK-NEXT: [2.1] - V1UnitFlg161# CHECK-NEXT: [2.2] - V1UnitFlg162# CHECK-NEXT: [3] - V1UnitL2163# CHECK-NEXT: [4.0] - V1UnitL01164# CHECK-NEXT: [4.1] - V1UnitL01165# CHECK-NEXT: [5] - V1UnitM0166# CHECK-NEXT: [6] - V1UnitM1167# CHECK-NEXT: [7.0] - V1UnitS168# CHECK-NEXT: [7.1] - V1UnitS169# CHECK-NEXT: [8] - V1UnitV0170# CHECK-NEXT: [9] - V1UnitV1171# CHECK-NEXT: [10] - V1UnitV2172# CHECK-NEXT: [11] - V1UnitV3173 174# CHECK: Resource pressure per iteration:175# 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]176# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25177 178# CHECK: Resource pressure by instruction:179# 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:180# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ldr b0, [sp]181# CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 fadd d0, d0, d0182 183# CHECK: Timeline view:184# CHECK-NEXT: 01185# CHECK-NEXT: Index 0123456789186 187# CHECK: [0,0] DeeeeeeER .. ldr b0, [sp]188# CHECK-NEXT: [0,1] D======eeER. fadd d0, d0, d0189# CHECK-NEXT: [1,0] DeeeeeeE--R. ldr b0, [sp]190# CHECK-NEXT: [1,1] D======eeER. fadd d0, d0, d0191# CHECK-NEXT: [2,0] DeeeeeeE--R. ldr b0, [sp]192# CHECK-NEXT: [2,1] D======eeER. fadd d0, d0, d0193# CHECK-NEXT: [3,0] D=eeeeeeE-R. ldr b0, [sp]194# CHECK-NEXT: [3,1] D=======eeER fadd d0, d0, d0195 196# CHECK: Average Wait times (based on the timeline view):197# CHECK-NEXT: [0]: Executions198# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue199# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready200# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage201 202# CHECK: [0] [1] [2] [3]203# CHECK-NEXT: 0. 4 1.3 1.3 1.3 ldr b0, [sp]204# CHECK-NEXT: 1. 4 7.3 0.0 0.0 fadd d0, d0, d0205# CHECK-NEXT: 4 4.3 0.6 0.6 <total>206 207# CHECK: [2] Code Region - FPR16-bit208 209# CHECK: Iterations: 100210# CHECK-NEXT: Instructions: 200211# CHECK-NEXT: Total Cycles: 44212# CHECK-NEXT: Total uOps: 200213 214# CHECK: Dispatch Width: 8215# CHECK-NEXT: uOps Per Cycle: 4.55216# CHECK-NEXT: IPC: 4.55217# CHECK-NEXT: Block RThroughput: 0.3218 219# CHECK: Instruction Info:220# CHECK-NEXT: [1]: #uOps221# CHECK-NEXT: [2]: Latency222# CHECK-NEXT: [3]: RThroughput223# CHECK-NEXT: [4]: MayLoad224# CHECK-NEXT: [5]: MayStore225# CHECK-NEXT: [6]: HasSideEffects (U)226 227# CHECK: [1] [2] [3] [4] [5] [6] Instructions:228# CHECK-NEXT: 1 6 0.33 * ldr h0, [sp]229# CHECK-NEXT: 1 2 0.25 fadd d0, d0, d0230 231# CHECK: Resources:232# CHECK-NEXT: [0.0] - V1UnitB233# CHECK-NEXT: [0.1] - V1UnitB234# CHECK-NEXT: [1.0] - V1UnitD235# CHECK-NEXT: [1.1] - V1UnitD236# CHECK-NEXT: [2.0] - V1UnitFlg237# CHECK-NEXT: [2.1] - V1UnitFlg238# CHECK-NEXT: [2.2] - V1UnitFlg239# CHECK-NEXT: [3] - V1UnitL2240# CHECK-NEXT: [4.0] - V1UnitL01241# CHECK-NEXT: [4.1] - V1UnitL01242# CHECK-NEXT: [5] - V1UnitM0243# CHECK-NEXT: [6] - V1UnitM1244# CHECK-NEXT: [7.0] - V1UnitS245# CHECK-NEXT: [7.1] - V1UnitS246# CHECK-NEXT: [8] - V1UnitV0247# CHECK-NEXT: [9] - V1UnitV1248# CHECK-NEXT: [10] - V1UnitV2249# CHECK-NEXT: [11] - V1UnitV3250 251# CHECK: Resource pressure per iteration:252# 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]253# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25254 255# CHECK: Resource pressure by instruction:256# 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:257# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ldr h0, [sp]258# CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 fadd d0, d0, d0259 260# CHECK: Timeline view:261# CHECK-NEXT: 01262# CHECK-NEXT: Index 0123456789263 264# CHECK: [0,0] DeeeeeeER .. ldr h0, [sp]265# CHECK-NEXT: [0,1] D======eeER. fadd d0, d0, d0266# CHECK-NEXT: [1,0] DeeeeeeE--R. ldr h0, [sp]267# CHECK-NEXT: [1,1] D======eeER. fadd d0, d0, d0268# CHECK-NEXT: [2,0] DeeeeeeE--R. ldr h0, [sp]269# CHECK-NEXT: [2,1] D======eeER. fadd d0, d0, d0270# CHECK-NEXT: [3,0] D=eeeeeeE-R. ldr h0, [sp]271# CHECK-NEXT: [3,1] D=======eeER fadd d0, d0, d0272 273# CHECK: Average Wait times (based on the timeline view):274# CHECK-NEXT: [0]: Executions275# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue276# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready277# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage278 279# CHECK: [0] [1] [2] [3]280# CHECK-NEXT: 0. 4 1.3 1.3 1.3 ldr h0, [sp]281# CHECK-NEXT: 1. 4 7.3 0.0 0.0 fadd d0, d0, d0282# CHECK-NEXT: 4 4.3 0.6 0.6 <total>283 284# CHECK: [3] Code Region - FPR32-bit285 286# CHECK: Iterations: 100287# CHECK-NEXT: Instructions: 200288# CHECK-NEXT: Total Cycles: 44289# CHECK-NEXT: Total uOps: 200290 291# CHECK: Dispatch Width: 8292# CHECK-NEXT: uOps Per Cycle: 4.55293# CHECK-NEXT: IPC: 4.55294# CHECK-NEXT: Block RThroughput: 0.3295 296# CHECK: Instruction Info:297# CHECK-NEXT: [1]: #uOps298# CHECK-NEXT: [2]: Latency299# CHECK-NEXT: [3]: RThroughput300# CHECK-NEXT: [4]: MayLoad301# CHECK-NEXT: [5]: MayStore302# CHECK-NEXT: [6]: HasSideEffects (U)303 304# CHECK: [1] [2] [3] [4] [5] [6] Instructions:305# CHECK-NEXT: 1 6 0.33 * ldr s0, [sp]306# CHECK-NEXT: 1 2 0.25 fadd d0, d0, d0307 308# CHECK: Resources:309# CHECK-NEXT: [0.0] - V1UnitB310# CHECK-NEXT: [0.1] - V1UnitB311# CHECK-NEXT: [1.0] - V1UnitD312# CHECK-NEXT: [1.1] - V1UnitD313# CHECK-NEXT: [2.0] - V1UnitFlg314# CHECK-NEXT: [2.1] - V1UnitFlg315# CHECK-NEXT: [2.2] - V1UnitFlg316# CHECK-NEXT: [3] - V1UnitL2317# CHECK-NEXT: [4.0] - V1UnitL01318# CHECK-NEXT: [4.1] - V1UnitL01319# CHECK-NEXT: [5] - V1UnitM0320# CHECK-NEXT: [6] - V1UnitM1321# CHECK-NEXT: [7.0] - V1UnitS322# CHECK-NEXT: [7.1] - V1UnitS323# CHECK-NEXT: [8] - V1UnitV0324# CHECK-NEXT: [9] - V1UnitV1325# CHECK-NEXT: [10] - V1UnitV2326# CHECK-NEXT: [11] - V1UnitV3327 328# CHECK: Resource pressure per iteration:329# 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]330# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25331 332# CHECK: Resource pressure by instruction:333# 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:334# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ldr s0, [sp]335# CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 fadd d0, d0, d0336 337# CHECK: Timeline view:338# CHECK-NEXT: 01339# CHECK-NEXT: Index 0123456789340 341# CHECK: [0,0] DeeeeeeER .. ldr s0, [sp]342# CHECK-NEXT: [0,1] D======eeER. fadd d0, d0, d0343# CHECK-NEXT: [1,0] DeeeeeeE--R. ldr s0, [sp]344# CHECK-NEXT: [1,1] D======eeER. fadd d0, d0, d0345# CHECK-NEXT: [2,0] DeeeeeeE--R. ldr s0, [sp]346# CHECK-NEXT: [2,1] D======eeER. fadd d0, d0, d0347# CHECK-NEXT: [3,0] D=eeeeeeE-R. ldr s0, [sp]348# CHECK-NEXT: [3,1] D=======eeER fadd d0, d0, d0349 350# CHECK: Average Wait times (based on the timeline view):351# CHECK-NEXT: [0]: Executions352# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue353# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready354# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage355 356# CHECK: [0] [1] [2] [3]357# CHECK-NEXT: 0. 4 1.3 1.3 1.3 ldr s0, [sp]358# CHECK-NEXT: 1. 4 7.3 0.0 0.0 fadd d0, d0, d0359# CHECK-NEXT: 4 4.3 0.6 0.6 <total>360 361# CHECK: [4] Code Region - SIMD64-bit-b362 363# CHECK: Iterations: 100364# CHECK-NEXT: Instructions: 200365# CHECK-NEXT: Total Cycles: 44366# CHECK-NEXT: Total uOps: 200367 368# CHECK: Dispatch Width: 8369# CHECK-NEXT: uOps Per Cycle: 4.55370# CHECK-NEXT: IPC: 4.55371# CHECK-NEXT: Block RThroughput: 0.3372 373# CHECK: Instruction Info:374# CHECK-NEXT: [1]: #uOps375# CHECK-NEXT: [2]: Latency376# CHECK-NEXT: [3]: RThroughput377# CHECK-NEXT: [4]: MayLoad378# CHECK-NEXT: [5]: MayStore379# CHECK-NEXT: [6]: HasSideEffects (U)380 381# CHECK: [1] [2] [3] [4] [5] [6] Instructions:382# CHECK-NEXT: 1 6 0.33 * ld1 { v0.8b }, [sp]383# CHECK-NEXT: 1 2 0.25 add v0.16b, v0.16b, v0.16b384 385# CHECK: Resources:386# CHECK-NEXT: [0.0] - V1UnitB387# CHECK-NEXT: [0.1] - V1UnitB388# CHECK-NEXT: [1.0] - V1UnitD389# CHECK-NEXT: [1.1] - V1UnitD390# CHECK-NEXT: [2.0] - V1UnitFlg391# CHECK-NEXT: [2.1] - V1UnitFlg392# CHECK-NEXT: [2.2] - V1UnitFlg393# CHECK-NEXT: [3] - V1UnitL2394# CHECK-NEXT: [4.0] - V1UnitL01395# CHECK-NEXT: [4.1] - V1UnitL01396# CHECK-NEXT: [5] - V1UnitM0397# CHECK-NEXT: [6] - V1UnitM1398# CHECK-NEXT: [7.0] - V1UnitS399# CHECK-NEXT: [7.1] - V1UnitS400# CHECK-NEXT: [8] - V1UnitV0401# CHECK-NEXT: [9] - V1UnitV1402# CHECK-NEXT: [10] - V1UnitV2403# CHECK-NEXT: [11] - V1UnitV3404 405# CHECK: Resource pressure per iteration:406# 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]407# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25408 409# CHECK: Resource pressure by instruction:410# 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:411# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ld1 { v0.8b }, [sp]412# CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 add v0.16b, v0.16b, v0.16b413 414# CHECK: Timeline view:415# CHECK-NEXT: 01416# CHECK-NEXT: Index 0123456789417 418# CHECK: [0,0] DeeeeeeER .. ld1 { v0.8b }, [sp]419# CHECK-NEXT: [0,1] D======eeER. add v0.16b, v0.16b, v0.16b420# CHECK-NEXT: [1,0] DeeeeeeE--R. ld1 { v0.8b }, [sp]421# CHECK-NEXT: [1,1] D======eeER. add v0.16b, v0.16b, v0.16b422# CHECK-NEXT: [2,0] DeeeeeeE--R. ld1 { v0.8b }, [sp]423# CHECK-NEXT: [2,1] D======eeER. add v0.16b, v0.16b, v0.16b424# CHECK-NEXT: [3,0] D=eeeeeeE-R. ld1 { v0.8b }, [sp]425# CHECK-NEXT: [3,1] D=======eeER add v0.16b, v0.16b, v0.16b426 427# CHECK: Average Wait times (based on the timeline view):428# CHECK-NEXT: [0]: Executions429# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue430# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready431# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage432 433# CHECK: [0] [1] [2] [3]434# CHECK-NEXT: 0. 4 1.3 1.3 1.3 ld1 { v0.8b }, [sp]435# CHECK-NEXT: 1. 4 7.3 0.0 0.0 add v0.16b, v0.16b, v0.16b436# CHECK-NEXT: 4 4.3 0.6 0.6 <total>437 438# CHECK: [5] Code Region - SIMD64-bit-h439 440# CHECK: Iterations: 100441# CHECK-NEXT: Instructions: 200442# CHECK-NEXT: Total Cycles: 44443# CHECK-NEXT: Total uOps: 200444 445# CHECK: Dispatch Width: 8446# CHECK-NEXT: uOps Per Cycle: 4.55447# CHECK-NEXT: IPC: 4.55448# CHECK-NEXT: Block RThroughput: 0.3449 450# CHECK: Instruction Info:451# CHECK-NEXT: [1]: #uOps452# CHECK-NEXT: [2]: Latency453# CHECK-NEXT: [3]: RThroughput454# CHECK-NEXT: [4]: MayLoad455# CHECK-NEXT: [5]: MayStore456# CHECK-NEXT: [6]: HasSideEffects (U)457 458# CHECK: [1] [2] [3] [4] [5] [6] Instructions:459# CHECK-NEXT: 1 6 0.33 * ld1 { v0.4h }, [sp]460# CHECK-NEXT: 1 2 0.25 add v0.8h, v0.8h, v0.8h461 462# CHECK: Resources:463# CHECK-NEXT: [0.0] - V1UnitB464# CHECK-NEXT: [0.1] - V1UnitB465# CHECK-NEXT: [1.0] - V1UnitD466# CHECK-NEXT: [1.1] - V1UnitD467# CHECK-NEXT: [2.0] - V1UnitFlg468# CHECK-NEXT: [2.1] - V1UnitFlg469# CHECK-NEXT: [2.2] - V1UnitFlg470# CHECK-NEXT: [3] - V1UnitL2471# CHECK-NEXT: [4.0] - V1UnitL01472# CHECK-NEXT: [4.1] - V1UnitL01473# CHECK-NEXT: [5] - V1UnitM0474# CHECK-NEXT: [6] - V1UnitM1475# CHECK-NEXT: [7.0] - V1UnitS476# CHECK-NEXT: [7.1] - V1UnitS477# CHECK-NEXT: [8] - V1UnitV0478# CHECK-NEXT: [9] - V1UnitV1479# CHECK-NEXT: [10] - V1UnitV2480# CHECK-NEXT: [11] - V1UnitV3481 482# CHECK: Resource pressure per iteration:483# 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]484# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25485 486# CHECK: Resource pressure by instruction:487# 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:488# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ld1 { v0.4h }, [sp]489# CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 add v0.8h, v0.8h, v0.8h490 491# CHECK: Timeline view:492# CHECK-NEXT: 01493# CHECK-NEXT: Index 0123456789494 495# CHECK: [0,0] DeeeeeeER .. ld1 { v0.4h }, [sp]496# CHECK-NEXT: [0,1] D======eeER. add v0.8h, v0.8h, v0.8h497# CHECK-NEXT: [1,0] DeeeeeeE--R. ld1 { v0.4h }, [sp]498# CHECK-NEXT: [1,1] D======eeER. add v0.8h, v0.8h, v0.8h499# CHECK-NEXT: [2,0] DeeeeeeE--R. ld1 { v0.4h }, [sp]500# CHECK-NEXT: [2,1] D======eeER. add v0.8h, v0.8h, v0.8h501# CHECK-NEXT: [3,0] D=eeeeeeE-R. ld1 { v0.4h }, [sp]502# CHECK-NEXT: [3,1] D=======eeER add v0.8h, v0.8h, v0.8h503 504# CHECK: Average Wait times (based on the timeline view):505# CHECK-NEXT: [0]: Executions506# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue507# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready508# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage509 510# CHECK: [0] [1] [2] [3]511# CHECK-NEXT: 0. 4 1.3 1.3 1.3 ld1 { v0.4h }, [sp]512# CHECK-NEXT: 1. 4 7.3 0.0 0.0 add v0.8h, v0.8h, v0.8h513# CHECK-NEXT: 4 4.3 0.6 0.6 <total>514 515# CHECK: [6] Code Region - SIMD64-bit-s516 517# CHECK: Iterations: 100518# CHECK-NEXT: Instructions: 200519# CHECK-NEXT: Total Cycles: 44520# CHECK-NEXT: Total uOps: 200521 522# CHECK: Dispatch Width: 8523# CHECK-NEXT: uOps Per Cycle: 4.55524# CHECK-NEXT: IPC: 4.55525# CHECK-NEXT: Block RThroughput: 0.3526 527# CHECK: Instruction Info:528# CHECK-NEXT: [1]: #uOps529# CHECK-NEXT: [2]: Latency530# CHECK-NEXT: [3]: RThroughput531# CHECK-NEXT: [4]: MayLoad532# CHECK-NEXT: [5]: MayStore533# CHECK-NEXT: [6]: HasSideEffects (U)534 535# CHECK: [1] [2] [3] [4] [5] [6] Instructions:536# CHECK-NEXT: 1 6 0.33 * ld1 { v0.2s }, [sp]537# CHECK-NEXT: 1 2 0.25 add v0.4s, v0.4s, v0.4s538 539# CHECK: Resources:540# CHECK-NEXT: [0.0] - V1UnitB541# CHECK-NEXT: [0.1] - V1UnitB542# CHECK-NEXT: [1.0] - V1UnitD543# CHECK-NEXT: [1.1] - V1UnitD544# CHECK-NEXT: [2.0] - V1UnitFlg545# CHECK-NEXT: [2.1] - V1UnitFlg546# CHECK-NEXT: [2.2] - V1UnitFlg547# CHECK-NEXT: [3] - V1UnitL2548# CHECK-NEXT: [4.0] - V1UnitL01549# CHECK-NEXT: [4.1] - V1UnitL01550# CHECK-NEXT: [5] - V1UnitM0551# CHECK-NEXT: [6] - V1UnitM1552# CHECK-NEXT: [7.0] - V1UnitS553# CHECK-NEXT: [7.1] - V1UnitS554# CHECK-NEXT: [8] - V1UnitV0555# CHECK-NEXT: [9] - V1UnitV1556# CHECK-NEXT: [10] - V1UnitV2557# CHECK-NEXT: [11] - V1UnitV3558 559# CHECK: Resource pressure per iteration:560# 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]561# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25562 563# CHECK: Resource pressure by instruction:564# 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:565# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ld1 { v0.2s }, [sp]566# CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 add v0.4s, v0.4s, v0.4s567 568# CHECK: Timeline view:569# CHECK-NEXT: 01570# CHECK-NEXT: Index 0123456789571 572# CHECK: [0,0] DeeeeeeER .. ld1 { v0.2s }, [sp]573# CHECK-NEXT: [0,1] D======eeER. add v0.4s, v0.4s, v0.4s574# CHECK-NEXT: [1,0] DeeeeeeE--R. ld1 { v0.2s }, [sp]575# CHECK-NEXT: [1,1] D======eeER. add v0.4s, v0.4s, v0.4s576# CHECK-NEXT: [2,0] DeeeeeeE--R. ld1 { v0.2s }, [sp]577# CHECK-NEXT: [2,1] D======eeER. add v0.4s, v0.4s, v0.4s578# CHECK-NEXT: [3,0] D=eeeeeeE-R. ld1 { v0.2s }, [sp]579# CHECK-NEXT: [3,1] D=======eeER add v0.4s, v0.4s, v0.4s580 581# CHECK: Average Wait times (based on the timeline view):582# CHECK-NEXT: [0]: Executions583# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue584# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready585# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage586 587# CHECK: [0] [1] [2] [3]588# CHECK-NEXT: 0. 4 1.3 1.3 1.3 ld1 { v0.2s }, [sp]589# CHECK-NEXT: 1. 4 7.3 0.0 0.0 add v0.4s, v0.4s, v0.4s590# CHECK-NEXT: 4 4.3 0.6 0.6 <total>591 592# CHECK: [7] Code Region - SIMD64-bit-d593 594# CHECK: Iterations: 100595# CHECK-NEXT: Instructions: 200596# CHECK-NEXT: Total Cycles: 44597# CHECK-NEXT: Total uOps: 200598 599# CHECK: Dispatch Width: 8600# CHECK-NEXT: uOps Per Cycle: 4.55601# CHECK-NEXT: IPC: 4.55602# CHECK-NEXT: Block RThroughput: 0.3603 604# CHECK: Instruction Info:605# CHECK-NEXT: [1]: #uOps606# CHECK-NEXT: [2]: Latency607# CHECK-NEXT: [3]: RThroughput608# CHECK-NEXT: [4]: MayLoad609# CHECK-NEXT: [5]: MayStore610# CHECK-NEXT: [6]: HasSideEffects (U)611 612# CHECK: [1] [2] [3] [4] [5] [6] Instructions:613# CHECK-NEXT: 1 6 0.33 * ld1 { v0.1d }, [sp]614# CHECK-NEXT: 1 2 0.25 add v0.2d, v0.2d, v0.2d615 616# CHECK: Resources:617# CHECK-NEXT: [0.0] - V1UnitB618# CHECK-NEXT: [0.1] - V1UnitB619# CHECK-NEXT: [1.0] - V1UnitD620# CHECK-NEXT: [1.1] - V1UnitD621# CHECK-NEXT: [2.0] - V1UnitFlg622# CHECK-NEXT: [2.1] - V1UnitFlg623# CHECK-NEXT: [2.2] - V1UnitFlg624# CHECK-NEXT: [3] - V1UnitL2625# CHECK-NEXT: [4.0] - V1UnitL01626# CHECK-NEXT: [4.1] - V1UnitL01627# CHECK-NEXT: [5] - V1UnitM0628# CHECK-NEXT: [6] - V1UnitM1629# CHECK-NEXT: [7.0] - V1UnitS630# CHECK-NEXT: [7.1] - V1UnitS631# CHECK-NEXT: [8] - V1UnitV0632# CHECK-NEXT: [9] - V1UnitV1633# CHECK-NEXT: [10] - V1UnitV2634# CHECK-NEXT: [11] - V1UnitV3635 636# CHECK: Resource pressure per iteration:637# 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]638# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - 0.25 0.25 0.25 0.25639 640# CHECK: Resource pressure by instruction:641# 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:642# CHECK-NEXT: - - - - - - - 0.33 0.33 0.34 - - - - - - - - ld1 { v0.1d }, [sp]643# CHECK-NEXT: - - - - - - - - - - - - - - 0.25 0.25 0.25 0.25 add v0.2d, v0.2d, v0.2d644 645# CHECK: Timeline view:646# CHECK-NEXT: 01647# CHECK-NEXT: Index 0123456789648 649# CHECK: [0,0] DeeeeeeER .. ld1 { v0.1d }, [sp]650# CHECK-NEXT: [0,1] D======eeER. add v0.2d, v0.2d, v0.2d651# CHECK-NEXT: [1,0] DeeeeeeE--R. ld1 { v0.1d }, [sp]652# CHECK-NEXT: [1,1] D======eeER. add v0.2d, v0.2d, v0.2d653# CHECK-NEXT: [2,0] DeeeeeeE--R. ld1 { v0.1d }, [sp]654# CHECK-NEXT: [2,1] D======eeER. add v0.2d, v0.2d, v0.2d655# CHECK-NEXT: [3,0] D=eeeeeeE-R. ld1 { v0.1d }, [sp]656# CHECK-NEXT: [3,1] D=======eeER add v0.2d, v0.2d, v0.2d657 658# CHECK: Average Wait times (based on the timeline view):659# CHECK-NEXT: [0]: Executions660# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue661# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready662# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage663 664# CHECK: [0] [1] [2] [3]665# CHECK-NEXT: 0. 4 1.3 1.3 1.3 ld1 { v0.1d }, [sp]666# CHECK-NEXT: 1. 4 7.3 0.0 0.0 add v0.2d, v0.2d, v0.2d667# CHECK-NEXT: 4 4.3 0.6 0.6 <total>668 669# CHECK: [8] Code Region - ins670 671# CHECK: Iterations: 100672# CHECK-NEXT: Instructions: 200673# CHECK-NEXT: Total Cycles: 403674# CHECK-NEXT: Total uOps: 200675 676# CHECK: Dispatch Width: 8677# CHECK-NEXT: uOps Per Cycle: 0.50678# CHECK-NEXT: IPC: 0.50679# CHECK-NEXT: Block RThroughput: 0.5680 681# CHECK: Instruction Info:682# CHECK-NEXT: [1]: #uOps683# CHECK-NEXT: [2]: Latency684# CHECK-NEXT: [3]: RThroughput685# CHECK-NEXT: [4]: MayLoad686# CHECK-NEXT: [5]: MayStore687# CHECK-NEXT: [6]: HasSideEffects (U)688 689# CHECK: [1] [2] [3] [4] [5] [6] Instructions:690# CHECK-NEXT: 1 2 0.25 mov v0.b[0], v1.b[1]691# CHECK-NEXT: 1 2 0.25 add v0.16b, v0.16b, v0.16b692 693# CHECK: Resources:694# CHECK-NEXT: [0.0] - V1UnitB695# CHECK-NEXT: [0.1] - V1UnitB696# CHECK-NEXT: [1.0] - V1UnitD697# CHECK-NEXT: [1.1] - V1UnitD698# CHECK-NEXT: [2.0] - V1UnitFlg699# CHECK-NEXT: [2.1] - V1UnitFlg700# CHECK-NEXT: [2.2] - V1UnitFlg701# CHECK-NEXT: [3] - V1UnitL2702# CHECK-NEXT: [4.0] - V1UnitL01703# CHECK-NEXT: [4.1] - V1UnitL01704# CHECK-NEXT: [5] - V1UnitM0705# CHECK-NEXT: [6] - V1UnitM1706# CHECK-NEXT: [7.0] - V1UnitS707# CHECK-NEXT: [7.1] - V1UnitS708# CHECK-NEXT: [8] - V1UnitV0709# CHECK-NEXT: [9] - V1UnitV1710# CHECK-NEXT: [10] - V1UnitV2711# CHECK-NEXT: [11] - V1UnitV3712 713# CHECK: Resource pressure per iteration:714# 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]715# CHECK-NEXT: - - - - - - - - - - - - - - 0.50 0.50 0.50 0.50716 717# CHECK: Resource pressure by instruction:718# 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:719# CHECK-NEXT: - - - - - - - - - - - - - - - 0.50 - 0.50 mov v0.b[0], v1.b[1]720# CHECK-NEXT: - - - - - - - - - - - - - - 0.50 - 0.50 - add v0.16b, v0.16b, v0.16b721 722# CHECK: Timeline view:723# CHECK-NEXT: 012345678724# CHECK-NEXT: Index 0123456789725 726# CHECK: [0,0] DeeER. . . . mov v0.b[0], v1.b[1]727# CHECK-NEXT: [0,1] D==eeER . . . add v0.16b, v0.16b, v0.16b728# CHECK-NEXT: [1,0] D====eeER . . . mov v0.b[0], v1.b[1]729# CHECK-NEXT: [1,1] D======eeER . . add v0.16b, v0.16b, v0.16b730# CHECK-NEXT: [2,0] D========eeER . . mov v0.b[0], v1.b[1]731# CHECK-NEXT: [2,1] D==========eeER. . add v0.16b, v0.16b, v0.16b732# CHECK-NEXT: [3,0] D============eeER . mov v0.b[0], v1.b[1]733# CHECK-NEXT: [3,1] D==============eeER add v0.16b, v0.16b, v0.16b734 735# CHECK: Average Wait times (based on the timeline view):736# CHECK-NEXT: [0]: Executions737# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue738# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready739# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage740 741# CHECK: [0] [1] [2] [3]742# CHECK-NEXT: 0. 4 7.0 0.3 0.0 mov v0.b[0], v1.b[1]743# CHECK-NEXT: 1. 4 9.0 0.0 0.0 add v0.16b, v0.16b, v0.16b744# CHECK-NEXT: 4 8.0 0.1 0.0 <total>745 746# CHECK: [9] Code Region - lanewise-load747 748# CHECK: Iterations: 100749# CHECK-NEXT: Instructions: 200750# CHECK-NEXT: Total Cycles: 1003751# CHECK-NEXT: Total uOps: 300752 753# CHECK: Dispatch Width: 8754# CHECK-NEXT: uOps Per Cycle: 0.30755# CHECK-NEXT: IPC: 0.20756# CHECK-NEXT: Block RThroughput: 0.5757 758# CHECK: Instruction Info:759# CHECK-NEXT: [1]: #uOps760# CHECK-NEXT: [2]: Latency761# CHECK-NEXT: [3]: RThroughput762# CHECK-NEXT: [4]: MayLoad763# CHECK-NEXT: [5]: MayStore764# CHECK-NEXT: [6]: HasSideEffects (U)765 766# CHECK: [1] [2] [3] [4] [5] [6] Instructions:767# CHECK-NEXT: 2 8 0.33 * ld1 { v0.b }[0], [sp]768# CHECK-NEXT: 1 2 0.25 add v0.16b, v0.16b, v0.16b769 770# CHECK: Resources:771# CHECK-NEXT: [0.0] - V1UnitB772# CHECK-NEXT: [0.1] - V1UnitB773# CHECK-NEXT: [1.0] - V1UnitD774# CHECK-NEXT: [1.1] - V1UnitD775# CHECK-NEXT: [2.0] - V1UnitFlg776# CHECK-NEXT: [2.1] - V1UnitFlg777# CHECK-NEXT: [2.2] - V1UnitFlg778# CHECK-NEXT: [3] - V1UnitL2779# CHECK-NEXT: [4.0] - V1UnitL01780# CHECK-NEXT: [4.1] - V1UnitL01781# CHECK-NEXT: [5] - V1UnitM0782# CHECK-NEXT: [6] - V1UnitM1783# CHECK-NEXT: [7.0] - V1UnitS784# CHECK-NEXT: [7.1] - V1UnitS785# CHECK-NEXT: [8] - V1UnitV0786# CHECK-NEXT: [9] - V1UnitV1787# CHECK-NEXT: [10] - V1UnitV2788# CHECK-NEXT: [11] - V1UnitV3789 790# CHECK: Resource pressure per iteration:791# 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]792# CHECK-NEXT: - - - - - - - - 0.50 0.50 - - - - 0.50 0.50 0.50 0.50793 794# CHECK: Resource pressure by instruction:795# 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:796# CHECK-NEXT: - - - - - - - - 0.50 0.50 - - - - - 0.50 - 0.50 ld1 { v0.b }[0], [sp]797# CHECK-NEXT: - - - - - - - - - - - - - - 0.50 - 0.50 - add v0.16b, v0.16b, v0.16b798 799# CHECK: Timeline view:800# CHECK-NEXT: 0123456789 0123456789801# CHECK-NEXT: Index 0123456789 0123456789 012802 803# CHECK: [0,0] DeeeeeeeeER . . . . . . . ld1 { v0.b }[0], [sp]804# CHECK-NEXT: [0,1] D========eeER . . . . . . . add v0.16b, v0.16b, v0.16b805# CHECK-NEXT: [1,0] D==========eeeeeeeeER . . . . . ld1 { v0.b }[0], [sp]806# CHECK-NEXT: [1,1] D==================eeER . . . . . add v0.16b, v0.16b, v0.16b807# CHECK-NEXT: [2,0] D====================eeeeeeeeER . . . ld1 { v0.b }[0], [sp]808# CHECK-NEXT: [2,1] .D===========================eeER . . . add v0.16b, v0.16b, v0.16b809# CHECK-NEXT: [3,0] .D=============================eeeeeeeeER . ld1 { v0.b }[0], [sp]810# CHECK-NEXT: [3,1] .D=====================================eeER add v0.16b, v0.16b, v0.16b811 812# CHECK: Average Wait times (based on the timeline view):813# CHECK-NEXT: [0]: Executions814# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue815# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready816# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage817 818# CHECK: [0] [1] [2] [3]819# CHECK-NEXT: 0. 4 15.8 0.3 0.0 ld1 { v0.b }[0], [sp]820# CHECK-NEXT: 1. 4 23.5 0.0 0.0 add v0.16b, v0.16b, v0.16b821# CHECK-NEXT: 4 19.6 0.1 0.0 <total>822