234 lines · plain
1# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py2# RUN: llvm-mca -mtriple=amdgcn -mcpu=gfx900 --timeline --iterations=1 --timeline-max-cycles=0 < %s | FileCheck %s3 4s_load_dwordx2 s[2:3], s[0:1], 0x245s_load_dwordx2 s[0:1], s[0:1], 0x2c6s_waitcnt lgkmcnt(0)7v_mov_b32_e32 v0, s28v_mov_b32_e32 v1, s39flat_load_dword v2, v[0:1]10flat_load_dword v3, v[0:1] offset:811flat_load_dword v4, v[0:1] offset:1612flat_load_dword v5, v[0:1] offset:2413v_mov_b32_e32 v0, s014v_mov_b32_e32 v1, s115v_mov_b32_e32 v6, s616v_mov_b32_e32 v7, s717v_mov_b32_e32 v8, s818v_mov_b32_e32 v9, s919v_mov_b32_e32 v10, s1020v_mov_b32_e32 v11, s1121v_mov_b32_e32 v12, s1222v_mov_b32_e32 v13, s1323v_mov_b32_e32 v14, s1424v_mov_b32_e32 v15, s1525v_mov_b32_e32 v16, s1626v_mov_b32_e32 v17, s1727v_mov_b32_e32 v18, s1828v_mov_b32_e32 v19, s1929v_mov_b32_e32 v20, s2030v_mov_b32_e32 v21, s2131v_mov_b32_e32 v22, s2232v_mov_b32_e32 v23, s2333v_mov_b32_e32 v24, s2434v_mov_b32_e32 v25, s2535v_mov_b32_e32 v26, s2636v_mov_b32_e32 v27, s2737v_mov_b32_e32 v28, s2838v_mov_b32_e32 v29, s2939s_waitcnt vmcnt(0) lgkmcnt(0)40 41# CHECK: Iterations: 142# CHECK-NEXT: Instructions: 3643# CHECK-NEXT: Total Cycles: 9444# CHECK-NEXT: Total uOps: 3645 46# CHECK: Dispatch Width: 147# CHECK-NEXT: uOps Per Cycle: 0.3848# CHECK-NEXT: IPC: 0.3849# CHECK-NEXT: Block RThroughput: 36.050 51# CHECK: Instruction Info:52# CHECK-NEXT: [1]: #uOps53# CHECK-NEXT: [2]: Latency54# CHECK-NEXT: [3]: RThroughput55# CHECK-NEXT: [4]: MayLoad56# CHECK-NEXT: [5]: MayStore57# CHECK-NEXT: [6]: HasSideEffects (U)58 59# CHECK: [1] [2] [3] [4] [5] [6] Instructions:60# CHECK-NEXT: 1 5 1.00 * s_load_dwordx2 s[2:3], s[0:1], 0x2461# CHECK-NEXT: 1 5 1.00 * s_load_dwordx2 s[0:1], s[0:1], 0x2c62# CHECK-NEXT: 1 1 1.00 U s_waitcnt lgkmcnt(0)63# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v0, s264# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v1, s365# CHECK-NEXT: 1 80 1.00 * U flat_load_dword v2, v[0:1]66# CHECK-NEXT: 1 80 1.00 * U flat_load_dword v3, v[0:1] offset:867# CHECK-NEXT: 1 80 1.00 * U flat_load_dword v4, v[0:1] offset:1668# CHECK-NEXT: 1 80 1.00 * U flat_load_dword v5, v[0:1] offset:2469# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v0, s070# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v1, s171# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v6, s672# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v7, s773# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v8, s874# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v9, s975# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v10, s1076# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v11, s1177# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v12, s1278# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v13, s1379# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v14, s1480# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v15, s1581# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v16, s1682# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v17, s1783# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v18, s1884# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v19, s1985# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v20, s2086# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v21, s2187# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v22, s2288# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v23, s2389# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v24, s2490# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v25, s2591# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v26, s2692# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v27, s2793# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v28, s2894# CHECK-NEXT: 1 1 1.00 U v_mov_b32_e32 v29, s2995# CHECK-NEXT: 1 1 1.00 U s_waitcnt vmcnt(0) lgkmcnt(0)96 97# CHECK: Resources:98# CHECK-NEXT: [0] - HWBranch99# CHECK-NEXT: [1] - HWExport100# CHECK-NEXT: [2] - HWLGKM101# CHECK-NEXT: [3] - HWSALU102# CHECK-NEXT: [4] - HWVALU103# CHECK-NEXT: [5] - HWVMEM104# CHECK-NEXT: [6] - HWXDL105 106# CHECK: Resource pressure per iteration:107# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6]108# CHECK-NEXT: - - 2.00 2.00 28.00 4.00 -109 110# CHECK: Resource pressure by instruction:111# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] Instructions:112# CHECK-NEXT: - - 1.00 - - - - s_load_dwordx2 s[2:3], s[0:1], 0x24113# CHECK-NEXT: - - 1.00 - - - - s_load_dwordx2 s[0:1], s[0:1], 0x2c114# CHECK-NEXT: - - - 1.00 - - - s_waitcnt lgkmcnt(0)115# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v0, s2116# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v1, s3117# CHECK-NEXT: - - - - - 1.00 - flat_load_dword v2, v[0:1]118# CHECK-NEXT: - - - - - 1.00 - flat_load_dword v3, v[0:1] offset:8119# CHECK-NEXT: - - - - - 1.00 - flat_load_dword v4, v[0:1] offset:16120# CHECK-NEXT: - - - - - 1.00 - flat_load_dword v5, v[0:1] offset:24121# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v0, s0122# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v1, s1123# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v6, s6124# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v7, s7125# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v8, s8126# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v9, s9127# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v10, s10128# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v11, s11129# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v12, s12130# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v13, s13131# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v14, s14132# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v15, s15133# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v16, s16134# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v17, s17135# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v18, s18136# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v19, s19137# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v20, s20138# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v21, s21139# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v22, s22140# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v23, s23141# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v24, s24142# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v25, s25143# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v26, s26144# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v27, s27145# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v28, s28146# CHECK-NEXT: - - - - 1.00 - - v_mov_b32_e32 v29, s29147# CHECK-NEXT: - - - 1.00 - - - s_waitcnt vmcnt(0) lgkmcnt(0)148 149# CHECK: Timeline view:150# CHECK-NEXT: 0123456789 0123456789 0123456789 0123456789 0123151# CHECK-NEXT: Index 0123456789 0123456789 0123456789 0123456789 0123456789152 153# CHECK: [0,0] DeeeeE . . . . . . . . . . . . . . . . . . s_load_dwordx2 s[2:3], s[0:1], 0x24154# CHECK-NEXT: [0,1] .DeeeeE . . . . . . . . . . . . . . . . . . s_load_dwordx2 s[0:1], s[0:1], 0x2c155# CHECK-NEXT: [0,2] . .DE . . . . . . . . . . . . . . . . . . s_waitcnt lgkmcnt(0)156# CHECK-NEXT: [0,3] . . DE . . . . . . . . . . . . . . . . . . v_mov_b32_e32 v0, s2157# CHECK-NEXT: [0,4] . . DE. . . . . . . . . . . . . . . . . . v_mov_b32_e32 v1, s3158# CHECK-NEXT: [0,5] . . DeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeE. . flat_load_dword v2, v[0:1]159# CHECK-NEXT: [0,6] . . DeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeE . flat_load_dword v3, v[0:1] offset:8160# CHECK-NEXT: [0,7] . . .DeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeE . flat_load_dword v4, v[0:1] offset:16161# CHECK-NEXT: [0,8] . . . DeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeE. flat_load_dword v5, v[0:1] offset:24162# CHECK-NEXT: [0,9] . . . DE. . . . . . . . . . . . . . . . . v_mov_b32_e32 v0, s0163# CHECK-NEXT: [0,10] . . . DE . . . . . . . . . . . . . . . . v_mov_b32_e32 v1, s1164# CHECK-NEXT: [0,11] . . . DE . . . . . . . . . . . . . . . . v_mov_b32_e32 v6, s6165# CHECK-NEXT: [0,12] . . . .DE . . . . . . . . . . . . . . . . v_mov_b32_e32 v7, s7166# CHECK-NEXT: [0,13] . . . . DE . . . . . . . . . . . . . . . . v_mov_b32_e32 v8, s8167# CHECK-NEXT: [0,14] . . . . DE. . . . . . . . . . . . . . . . v_mov_b32_e32 v9, s9168# CHECK-NEXT: [0,15] . . . . DE . . . . . . . . . . . . . . . v_mov_b32_e32 v10, s10169# CHECK-NEXT: [0,16] . . . . DE . . . . . . . . . . . . . . . v_mov_b32_e32 v11, s11170# CHECK-NEXT: [0,17] . . . . .DE . . . . . . . . . . . . . . . v_mov_b32_e32 v12, s12171# CHECK-NEXT: [0,18] . . . . . DE . . . . . . . . . . . . . . . v_mov_b32_e32 v13, s13172# CHECK-NEXT: [0,19] . . . . . DE. . . . . . . . . . . . . . . v_mov_b32_e32 v14, s14173# CHECK-NEXT: [0,20] . . . . . DE . . . . . . . . . . . . . . v_mov_b32_e32 v15, s15174# CHECK-NEXT: [0,21] . . . . . DE . . . . . . . . . . . . . . v_mov_b32_e32 v16, s16175# CHECK-NEXT: [0,22] . . . . . .DE . . . . . . . . . . . . . . v_mov_b32_e32 v17, s17176# CHECK-NEXT: [0,23] . . . . . . DE . . . . . . . . . . . . . . v_mov_b32_e32 v18, s18177# CHECK-NEXT: [0,24] . . . . . . DE. . . . . . . . . . . . . . v_mov_b32_e32 v19, s19178# CHECK-NEXT: [0,25] . . . . . . DE . . . . . . . . . . . . . v_mov_b32_e32 v20, s20179# CHECK-NEXT: [0,26] . . . . . . DE . . . . . . . . . . . . . v_mov_b32_e32 v21, s21180# CHECK-NEXT: [0,27] . . . . . . .DE . . . . . . . . . . . . . v_mov_b32_e32 v22, s22181# CHECK-NEXT: [0,28] . . . . . . . DE . . . . . . . . . . . . . v_mov_b32_e32 v23, s23182# CHECK-NEXT: [0,29] . . . . . . . DE. . . . . . . . . . . . . v_mov_b32_e32 v24, s24183# CHECK-NEXT: [0,30] . . . . . . . DE . . . . . . . . . . . . v_mov_b32_e32 v25, s25184# CHECK-NEXT: [0,31] . . . . . . . DE . . . . . . . . . . . . v_mov_b32_e32 v26, s26185# CHECK-NEXT: [0,32] . . . . . . . .DE . . . . . . . . . . . . v_mov_b32_e32 v27, s27186# CHECK-NEXT: [0,33] . . . . . . . . DE . . . . . . . . . . . . v_mov_b32_e32 v28, s28187# CHECK-NEXT: [0,34] . . . . . . . . DE. . . . . . . . . . . . v_mov_b32_e32 v29, s29188# CHECK-NEXT: [0,35] . . . . . . . . . . . . . . . . . . . DE s_waitcnt vmcnt(0) lgkmcnt(0)189 190# CHECK: Average Wait times (based on the timeline view):191# CHECK-NEXT: [0]: Executions192# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue193# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready194# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage195 196# CHECK: [0] [1] [2] [3]197# CHECK-NEXT: 0. 1 0.0 0.0 0.0 s_load_dwordx2 s[2:3], s[0:1], 0x24198# CHECK-NEXT: 1. 1 0.0 0.0 0.0 s_load_dwordx2 s[0:1], s[0:1], 0x2c199# CHECK-NEXT: 2. 1 0.0 0.0 0.0 s_waitcnt lgkmcnt(0)200# CHECK-NEXT: 3. 1 0.0 0.0 0.0 v_mov_b32_e32 v0, s2201# CHECK-NEXT: 4. 1 0.0 0.0 0.0 v_mov_b32_e32 v1, s3202# CHECK-NEXT: 5. 1 0.0 0.0 0.0 flat_load_dword v2, v[0:1]203# CHECK-NEXT: 6. 1 0.0 0.0 0.0 flat_load_dword v3, v[0:1] offset:8204# CHECK-NEXT: 7. 1 0.0 0.0 0.0 flat_load_dword v4, v[0:1] offset:16205# CHECK-NEXT: 8. 1 0.0 0.0 0.0 flat_load_dword v5, v[0:1] offset:24206# CHECK-NEXT: 9. 1 0.0 0.0 0.0 v_mov_b32_e32 v0, s0207# CHECK-NEXT: 10. 1 0.0 0.0 0.0 v_mov_b32_e32 v1, s1208# CHECK-NEXT: 11. 1 0.0 0.0 0.0 v_mov_b32_e32 v6, s6209# CHECK-NEXT: 12. 1 0.0 0.0 0.0 v_mov_b32_e32 v7, s7210# CHECK-NEXT: 13. 1 0.0 0.0 0.0 v_mov_b32_e32 v8, s8211# CHECK-NEXT: 14. 1 0.0 0.0 0.0 v_mov_b32_e32 v9, s9212# CHECK-NEXT: 15. 1 0.0 0.0 0.0 v_mov_b32_e32 v10, s10213# CHECK-NEXT: 16. 1 0.0 0.0 0.0 v_mov_b32_e32 v11, s11214# CHECK-NEXT: 17. 1 0.0 0.0 0.0 v_mov_b32_e32 v12, s12215# CHECK-NEXT: 18. 1 0.0 0.0 0.0 v_mov_b32_e32 v13, s13216# CHECK-NEXT: 19. 1 0.0 0.0 0.0 v_mov_b32_e32 v14, s14217# CHECK-NEXT: 20. 1 0.0 0.0 0.0 v_mov_b32_e32 v15, s15218# CHECK-NEXT: 21. 1 0.0 0.0 0.0 v_mov_b32_e32 v16, s16219# CHECK-NEXT: 22. 1 0.0 0.0 0.0 v_mov_b32_e32 v17, s17220# CHECK-NEXT: 23. 1 0.0 0.0 0.0 v_mov_b32_e32 v18, s18221# CHECK-NEXT: 24. 1 0.0 0.0 0.0 v_mov_b32_e32 v19, s19222# CHECK-NEXT: 25. 1 0.0 0.0 0.0 v_mov_b32_e32 v20, s20223# CHECK-NEXT: 26. 1 0.0 0.0 0.0 v_mov_b32_e32 v21, s21224# CHECK-NEXT: 27. 1 0.0 0.0 0.0 v_mov_b32_e32 v22, s22225# CHECK-NEXT: 28. 1 0.0 0.0 0.0 v_mov_b32_e32 v23, s23226# CHECK-NEXT: 29. 1 0.0 0.0 0.0 v_mov_b32_e32 v24, s24227# CHECK-NEXT: 30. 1 0.0 0.0 0.0 v_mov_b32_e32 v25, s25228# CHECK-NEXT: 31. 1 0.0 0.0 0.0 v_mov_b32_e32 v26, s26229# CHECK-NEXT: 32. 1 0.0 0.0 0.0 v_mov_b32_e32 v27, s27230# CHECK-NEXT: 33. 1 0.0 0.0 0.0 v_mov_b32_e32 v28, s28231# CHECK-NEXT: 34. 1 0.0 0.0 0.0 v_mov_b32_e32 v29, s29232# CHECK-NEXT: 35. 1 0.0 0.0 0.0 s_waitcnt vmcnt(0) lgkmcnt(0)233# CHECK-NEXT: 1 0.0 0.0 0.0 <total>234