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, D from W)

Test 1: uops

Code:

  ucvtf d0, w0, #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)031e3f51schedule 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
200437630361252000100010001000100014075228201357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
200437930361252000100010001000100014075228530357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
200437620361252000100010001000100014115228200357376376723109200010001000100010003763761110011000100000731161137410001000377377377377377
200437630361252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
200437630361252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
200437630361252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
200437630361252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
200437630361252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377
200437630361252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000731161137310001000377377381377377
200437630361252000100010001000100014075228200357376376723109200010001000100010003763761110011000100000731161137310001000377377377377377

Test 2: Latency 1->2 roundtrip

Code:

  ucvtf d0, w0, #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)0309l2 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)60696b6d6emap 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
302041300329740000001300171194082540100101002000010000100200001000050062144971480270911300130130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131013163312952210000100001000010100130033130033130033130033130033
302041300329740000001300171194082540100101002000010000100200001000050062144971480270911300130130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131013162212951910000100001000010100130033130033130033130033130033
302041300329740000001300171194082540100101002000010000100200001000050062144971480270911300130130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131013163312951910000100001000010100130062130033130033130033130033
302041300329740000001300171194102540100101002000010000100200001000050062144971480270911300130130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131013163212951910000100001000010100130033130034130040130033130033
30204130032974000062101300171194082540100101002000010000100200001000050062144971480282111300130130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131013163312951910000100001000010100130033130033130033130033130033
302041300329740000001300171194082540100101002000010000100200001000050062144971480270911300130130032130032125466312624030100200100002000020210000200001300321300321120201100991001010010000100001000000000131013163312951910000100001000010100130033130033130033130033130033
3020413003297400009013001711940825401001010020000100001002000010000500621449714802709113001301300321300321254663126240301002001000020000200100002000013003213003211202011009910010100100001000010000000360131013162212951910000100001000010100130033130033130033130033130033
302041300329740000001300561194082540100101002000010000100200001000050062144971480270911300130130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131012162212951910000100001000010100130033130033130033130033130033
30204130032974000000130017119408254010010100200001000010020000100005006214497148027091130013013003213003212546631262403010020010064200002001000020000130032130032112020110099100101001000010000100000001770131012163312951910000100001000010100130033130033130033130033130099
302041300329740000001300171194082540100101002000010000100200001000050062144971480270911300130130032130032125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000000000131013162312951910000100001000010100130033130033130033130033130033

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0032

retire uop (01)cycle (02)0318191e1f3f4f51schedule 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)l1d tlb miss (a1)ld unit uop (a6)l1d cache writeback (a8)a9acc2branch cond mispred nonspec (c5)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)ea? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
3002413003210080000130017119408254001010010200001000010200001000050621449714800528111300130130032130067125551312626230010201000020000201000020000130032130032112002110910100101000010001000000000127031623129519100000100001000010010130033130033130033130033130033
3002413003210070000130017119408254001010010200001000010200001000050621449714800528001300130130032130032125494312626230010201000020000201000020000130032130032112002110910100101000010001000000300127031623129519100000100001000010010130033130035130033130033130036
3002413003210080000130017119409254001010010200001000010200001000050621449714800528001300190130036130087125491312626230180201000020000201000020000130032130032112002110910100101000010001000000000127031632129519100000100001000010010130033130033130033130033130033
3002413003210080000130017119408254001010010200001000010200001000050621500114800528001300130130032130082125489312626230010201000020000201000020000130032130032112002110910100101000010001000000000127021633129519100000100001000010010130033130033130033130033130033
3002413003210080000130017119408254001010010200001000010200001000050621459314801442001300130130032130116125489312626230010201000020000201000020000130032130032112002110910100101000010001000000000127031633129559100000100001000010010130033130033130033130033130099
30024130032100800270130017119408254001010010200001000010200001000050621449714800528001300130130032130032125585312626230010201000020000201000020000130032130032112002110910100101000010001000000000127031632129519100000100001000010010130033130033130033130033130038
30024130032100810001300171194082540010100102000010000102000010000506214497148005280013001301300321300321254902012630230010201000020000201000020000130032130032112002110910100101000010001000000000127031634129519100000100001000010010130033130033130033130033130036
3002413003210080000130017119408254001010010200001000010200001000050621449714800528001300130130032130032125492312626230010201000020000201000020000130032130032112002110910100101000010001000000000127031632129519100000100001000010010130033130033130033130033130033
3002413003210080000130017119408254001010010200001000010200001000050621449714800528001300130130032130109125489312626230010201000020000201000020000130032130032112002110910100101000010001000000000127031632129519100000100001000010010130033130033130033130033130033
3002413003210080000130017119408254001010010200001000010200001000050621449714800528001300130130032130032125512312626230010201006620000201000020000130106130036112002110910100101000010001000000000127021623129519100000100001000010010130033130033130033130033130033

Test 3: throughput

Count: 8

Code:

  ucvtf d0, w8, #3
  ucvtf d1, w8, #3
  ucvtf d2, w8, #3
  ucvtf d3, w8, #3
  ucvtf d4, w8, #3
  ucvtf d5, w8, #3
  ucvtf d6, w8, #3
  ucvtf d7, w8, #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)03l2 tlb miss instruction (0a)l2 tlb miss data (0b)1e3a3f4f51schedule 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)696d6emap 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)9fl1d tlb miss (a1)ld unit uop (a6)l1d cache writeback (a8)acbranch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)dde0? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
16020426712207000026694025160100100800008000010080020800155001168951188416326690267092670966320666581601352008002080020200800208002026709267091180201100991001008000010008000000111511701602670680000800001002671026710267102671026710
16020426709207000026694025160100100800008000010080020800155001168951188416326690267092671266320666581601352008002080020200800208002026709267091180201100991001008000010008000000111511701602670680000800001002671026710267102671426710
160204267092070012026694025160100100800008000010080020800155001168951188416326690267092670966320666581601352008002080020200800208002026709267131180201100991001008000010008000000111511711602670680000800001002671426710267102671426710
16020426709207000026694225160100100800008000010080020800155001168951188416326690267092670966320666581601352008002080020200800208002026709267091180201100991001008000010008000000111511701602670680000800001002671026712267102671026710
16020426713207000026694025160100100800008000010080020800155001168951188331826690267092670966320666581601352008002080020200800208002026709267091180201100991001008000010008000000111511701602670680000800001002671026710267102671026710
16020426709207000026698025160100100800008000010080020800155001168951188416326694267092670966320666581601352008002080020200800208002026709267091180201100991001008000010008000000111511701602670680000800001002671426710267102671026711
16020426709207000026694025160100100800008000010080020800155001170925188416326690267152670966320666581601352008002080020200800208002026709267091180201100991001008000010008000010111511701602670680000800001002671026710267102671026710
16020426713207000026694025160100100800008000010080020800155001168951188416326690267092670966320666581601352008002080020200800208002026709267131180201100991001008000010008000000111511701602670680000800001002671026710267102671026710
16020426709207000026694025160100100800008000010080020800155001168951188416326690267092670966320666581601352008002080020200800208002026709267131180201100991001008000010008000000111511701602670680000800001002671026710267102671026710
16020426709207100026694025160100100800008000010080020800155001168951188416326692267092670966320666581601352008002080020200800208002026709267091180201100991001008000010008000010111511701602670680000800001002671026710267102671026710

1000 unrolls and 10 iterations

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

retire uop (01)cycle (02)03mmu table walk data (08)l2 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)5f60696d6emap 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)9fa5ld unit uop (a6)l1d cache writeback (a8)a9acc2branch mispred nonspec (cb)cfd5map dispatch bubble (d6)daddfetch restart (de)e0? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
160024267112000000450026694325160010108000080000108000080000501168880188403200266902670926709681406066941600102080000800002080000800002670926709118002110910108000010080000000005020316042268708000080000102671026710267102671026710
1600242670920000006002669402516001010800008000010800008000050116888018840320026690267092670968090366911600102080000800002080000800002670926714118002110910108000010080000003005020216022267138000080000102671026710267172671326713
1600242671321900000002669402516001010800008000010800008000050116888018840320026859267172672766530366891600102080000800002080000800002670926713118002110910108000010080000000005020316022267068000080000102671026710267102671026710
1600242670920000000002669822516001010800008000010800008000050116888018930930026690267222671366900366891600102080000800002080000800002670926709118002110910108000010080000000005020216033267068000080000102671026710267102671026714
1600242670920000000002669402516001010800008000010800008000050116888018840320126690267202672166530366891600102080000800002080000800002670926709118002110910108000010080000000005020216022267068000080000102671026710267102671026710
1600242670920000000002669402516001010800008000010800008000050116888018840320026825267092687866550366891600102080000800002080000800002670926709118002110910108000010080000000005020216022267088000080000102671026710267102671026710
1600242670920000000002669402516001010800008000010800008000050116888018840320026690267122677266530366891600102080000800002080000800002670926709118002110910108000010080000000005020316032267068000080000102671026710267102671026710
1600242670920000000002669402516001010800008000010800008000050116888018840320026690267122671766530366891600102080000800002080000800002670926709118002110910108000010080000000005020216022267068000080000102671026710267102671026710
1600242670920000000002669402516001010800008000010800008000050116888018840320026690267612671166540366891600102080000800002080000800002670926709118002110910108000010080000000005020216032267068000080000102671026710267102671026710
1600242670920000000002669402516001010800008000010800008000050116888018840320026857267152670966530366891600102080000800002080000800002670926709118002110910108000010080000000005020316042267068000080000102671026710267102671026710