Apple Microarchitecture Research by Dougall Johnson

M1/A14 P-core (Firestorm): Overview | Base Instructions | SIMD and FP Instructions
M1/A14 E-core (Icestorm):  Overview | Base Instructions | SIMD and FP Instructions

UCVTF (scalar, fixed-point, H from X)

Test 1: uops

Code:

  ucvtf h0, x0, #3
  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 2.000

Issues: 2.000

Integer unit issues: 0.000

Load/store unit issues: 1.000

SIMD/FP unit issues: 1.000

retire uop (01)cycle (02)033f51schedule uop (52)schedule simd uop (54)schedule ldst uop (55)dispatch simd uop (57)dispatch ldst uop (58)simd uops in schedulers (5a)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map ldst uop (7d)map simd uop (7e)map ldst uop inputs (80)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst simd alu (9a)ld unit uop (a6)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? ldst retires (ed)? simd retires (ee)f5f6f7f8fd
20043763361252000100010001000100014075229330357376376723109200010001000100010003763761110011000100000731161137310001000377379377377378
20043762361252000100010001000100014075228201357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
20043762361252000100010001000100014075228201357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
20043773364252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000731161237310001000377377377377377
20043762361252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
20043763361252000100010001000100014075228201357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
20043843361252000100010001000100014197228200357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
20043763361252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
20043762361252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000731161137310001000377379377377377
20043763361252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000732162337310001000377377377377377

Test 2: Latency 1->2 roundtrip

Code:

  ucvtf h0, x0, #3
  fmov x0, d0
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 13.0032

retire uop (01)cycle (02)03mmu table walk data (08)09l2 tlb miss data (0b)18191e1f3a3f4f51schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb access (a0)l1d tlb miss (a1)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acc2cfd0d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
3020413003297400000000130017119450254010010100200001000010020000100005006214497148027091130013130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131012162212951910000100001000010100130033130033130033130102130033
3020413003297400000000130017119410254010010100200001000010020000100005006214497148027091130013130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131012162212951910000100001000010100130033130033130056130057130033
3020413003297400000000130017119413254010010100200001000010020000100005006214497148027091130013130032130032125466312624030100200100002000020010000200001300331300411120201100991001010010000100001000000000131013162212951910000100001000010100130033130033130033130069130033
3020413003297300000000130017119448254010010100200001000010020000100005006214497148027091130013130042130037125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131012163212951910000100001000010100130033130033130049130079130033
3020413003297400000300130017119441254010010100200001000010020000100005006214497148027091130013130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131012162212951910000100001000010100130116130033130033130084130033
3020413003297401000000130017119433254010010100200001000010020000100005006214497148027091130013130032130032125466312624230100200100002000020010000200001300321300321120201100991001010010000100001000000000131012265412951910000100001000010100130033130033130033130083130033
3020413003297400000000130017119411254010010100200001000010020000100005006214497148027091130013130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131012162212951910000100001000010100130033130034130094130063130033
3020413003297400000000130017119408254010010100200001000010020000100005006214497148027091130013130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131012162212951910000100001000010100130071130033130033130079130033
3020413003297400000000130017119408254010010100200001000010020000100005006214497148027091130013130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131012162212952010000100001000010100130033130033130033130089130033
3020413003297400000000130017119427254010010100200001000010020000100005006214497148027091130013130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131012162212951910000100001000010100130033130033130033130072130033

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0032

retire uop (01)cycle (02)03mmu table walk data (08)l2 tlb miss data (0b)18191e1f3f4f51schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)5f60696b6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb access (a0)ld unit uop (a6)l1d cache writeback (a8)a9acc2branch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
30024130035974000000130017119408254001010010200001000610200001000050621449714800528001300320130032130032125489312626230010201000020000201000020000130041130032112002110910100101000010010000900000012701161112951910000100001000010010130033130033130033130033130033
30024130032974000000130017119408254001010010200001000010200001000050621449714800528001300130130032130032125500312626230010201000020000201000020000130032130032112002110910100101000010010000000000012701161112951910000100001000010010130033130033130033130033130033
30024130032974000000130017119408254001010010200001000010200001000050621449714800528001300130130032130032125489312626230010201000020000201000020000130032130032112002110910100101000010010000000000012701161112951910000100001000010010130033130033130033130033130033
30024130032974000000130017119408254001010010200001000010200001000050621449714800528001300130130032130068125489312626230010201000020000201000020000130032130032112002110910100101000010010000000000012701161112952010000100001000010010130033130033130033130033130033
300241300329740000540130017119408254001010010200001000010200001000050621449714800528001300130130032130032125489312626230010201000020000201000020000130032130032112002110910100101000010010000000000012701161112951910000100001000010010130037130033130033130033130033
30024130032974000000130017119408254001010010200031000010200001000050621449714800528011300130130032130032125489312626230010201000020000201000020000130032130032112002110910100101000010010000000000012701161112951910000100001000010010130033130033130033130033130033
30024130032974000000130017119408254001010010200001000010200001000050621449714800528001300130130032130032125489312626230010201000020000201000020000130032130032112002110910100101000010010000000000012700161112951910000100001000010010130033130033130033130033130033
30024130032974000100130017119408254001010010200001000010200001000050621449714800528011300130130032130032125489312626230010201000020000201000020000130032130032112002110910100101000010010000000000012701161212951910000100001000010010130033130033130033130033130033
30024130032974000030130017119408254001010010200001000010200001000050621449714800528001300130130032130032125489812626230010201000020000201000020000130032130032112002110910100101000010010002000000012702161112951910000100001000010010130033130033130033130033130033
30024130032973003000130017119408254001010010200001000010200001000050621449714800528001300130130032130032125489312626230010201000020000201000020000130032130032112002110910100101000010010000000210012701161112958210000100001000010010130033130033130033130033130033

Test 3: throughput

Count: 8

Code:

  ucvtf h0, x8, #3
  ucvtf h1, x8, #3
  ucvtf h2, x8, #3
  ucvtf h3, x8, #3
  ucvtf h4, x8, #3
  ucvtf h5, x8, #3
  ucvtf h6, x8, #3
  ucvtf h7, x8, #3
  mov x8, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3339

retire uop (01)cycle (02)03091e3f4f51schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)60696b6d6emap stall dispatch (70)simd prf full (72)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fld unit uop (a6)l1d cache writeback (a8)acbranch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
16020426711207002669402516010010080000800001008002080014500116895118841630266900267092670966320666581601352008002480024200800208002026717267091180201100991001008000010080000001115117016002670680000800001002671026710267102671026710
1602042670920701226694025160100100800008000010080020800165001168951188416302669002670926709663206665816013520080020800202008002480020267172671411802011009910010080000100800000121115117016002670680000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118810160266900267092670966320666581601352008002080020200800248002026795267161180201100991001008000010080000031115117016002670680000800001002671026710267102671026710
16020426711207002669402516010010080000800001008002080015500116895118841630266900267092670966320666581601352008002080024200800208002426709267091180201100991001008000010080000001115117016002670680000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841630266900267092670966320666581601352008002480216200800208002026709267711180201100991001008000010080000001115117016002671080000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841630266900267092671166320666581601352008002080020200800208002026709267131180201100991001008000010080000001115117016002671080000800001002671426714267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841630266900267092670966320666581601352008002080012200800208002026716267091180201100991001008000010080000001115117016002670680000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841630266900267092670966320666621601352008002080020200800208002426709267091180201100991001008000010080000001115117016002670680000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841630266900267092670966320666581601352008002480024200800208002026709267091180201100991001008000010080000001115117016002670680000800001002671026710267102671026710
1602042670920700266940251601001008000080000100800208001550011689511884163026690026711267096632066658160135200804008002020080020800202670926709118020110099100100800001008000009541115117016002670680000800001002671026710267102671026710

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.3339

retire uop (01)cycle (02)031e1f3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)5f6061696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fld unit uop (a6)l1d cache writeback (a8)a9acbranch cond mispred nonspec (c5)cdcfd0d2d5map dispatch bubble (d6)ddfetch restart (de)e0? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
16002426710200002669425160010108000080000108000080000501168880188403201026690267092671266533668916001020800008000020800008000026709267181180021109101080000108000000000502015051642267068000080000102671026710267102671026710
1600242670920000266942516001010800008000010800008000050116888018840320002669026709267096653366891600102080000800002080000800002670926709118002110910108000010800000000050203041624267068000080000102671026710267102671026710
1600242670920000266942516001010800008000010800008000050116888018840320002669026709267096653366891600102080000800002080000800002671226718118002110910108000010800000000050203021642267068000080000102671026710267102671026710
1600242670920000266942516001010800008000010800008000050116888018840320002669026709267096653366891600102080000800002080000800002721926718118002110910108000010800000000050200041624267068000080000102671326710267112671026717
1600242670921500266942516001010800008000010800008000050116888018840320002669026709267096653366891600102080000800002080000800002670926709118002110910108000010800000000050200041642267068000080000102671026710267102671026710
1600242670920000266942516001010800008000010800008000050116888018840320002669026709267096653366891600102080000800002080000800002670926709118002110910108000010800000000050200041642267068000080000102671026710267102671026710
1600242670920000266942516001010800008000010800008000050116888018840320002669026709267096653366891600102080000800002080000800002670926709118002110910108000010800000000050200041644267068000080000102671026710267102671026710
1600242670919900266942516001010800008000010800008000050116888018840320002669026709267096653366891600102080000800002080000800002671126709118002110910108000010800000000050200041624267068000080000102671026710267102671026710
1600242670920000266942516001010800008000010800008000050116888018840320002669026709267096653366891600102080000800002080000803782670926709118002110910108000010800000000050200041644267068000080000102671026710267102671026710
1600242670920000266942516001010800008000010800008000050116888018840320102669026709267096653366891600102080000800002080000800002671026720118002110910108000010800000000050200021624267068000080000102671026710267102671026710