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, integer, H from X)

Test 1: uops

Code:

  ucvtf h0, x0
  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)033f4f51schedule 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)696d6emap 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)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? ldst retires (ed)? simd retires (ee)f5f6f7f8fd
2004376336102520001000100010001000140752282035737637672310920001000100010001000376376111001100010000731161137310001000377377377377377
2004376336102520001000100010001000140752282035737637672310920001000100010001000376376111001100010000731161137310001000377377377377377
2004376336102520001000100010001000140752282035737637672310920001000100010001000376379111001100010000731161137310001000377377377377377
2004376336102520001000100010001000140752282035737637672310920001000100010001000376376111001100010000731161137310001000377377377377377
2004376336102520001000100010001000140752282035737637672310920001000100010001000376376111001100010000731161137310001000377394377384377
2004376336102520001000100010001000140752282035737637672310920001000100010001000376376111001100010000731161137310001000377377377377377
2004376336102520001000100010001000140752282035737637672310920001000100010001000376376111001100010000731161137310001000377377377377377
2004376336102520001000100010001000140752282035737637672310920001000100010001000376376111001100010000731161137310001000377377377377377
2004376336102520001000100010001000140752282035737637672310920001000100010001000390378111001100010000731161137310001000377377377377377
2004376336102520001000100010001000140752282035737637672310920001000100010001000376376111001100010000731161137310001000377377377377377

Test 2: Latency 1->2 roundtrip

Code:

  ucvtf h0, x0
  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)03l1i tlb fill (04)mmu table walk instruction (07)mmu table walk data (08)1e3f4f51schedule 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)9fld unit uop (a6)l1d cache writeback (a8)accdcfd0d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
30204130032974000531130017119408254010010100200001000012520000100005006214497148027091130013013003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000000131012172212951810000100001000010100130033130033130033130033130033
302041300329740000130017119408254012510125200001000010020000100005006214497148027090130013013003213003212546631262393012520010000200002001000020000130032130032112020110099100101001000010010000000131014174412951810000100001000010100130033130033130033130033130033
302041300329740000130017119408254010010125200121000012420000100005006214497148027091130013013003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000000131012162212951910000100001000010100130033130033130033130033130102
302041300329740000130057119408254010010100200001000010020000100005006214497148027090130013013003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000001131012162212951910000100001000010100130033130033130033130033130117
302041300329740000130017119408254010010100200001000010020000100005006214497148030570130013013003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000000131012162212951910000100001000010100130033130033130033130033130033
302041300329740000130017119408254010010100200001000010020000100005006214497148027090130013013003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000000131012162212951910000100001000010100130033130033130033130033130033
302041300329740000130017119408254010010100200001000010020000100005006214497148027090130013013003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000000131012162212951910000100001000010100130033130033130033130033130033
30204130032974000013001711940825401001010020000100081252000010000626621455414803008113001301300321300321254663126240301002001000020000200100002000013003213003211202011009910010100100001001000012700131012162212951910000100001000010100130033130033130033130033130033
3020413003297400001300171194082540100101002000010000100200001000050062145931480270901300130130032130032125466312624030100200100002000020010000200001300351300321120201100991001010010000100100007690131214174412951810000100001000010100130033130033130033130033130033
302041300329740000130017119408254010010125200001000010020000100005006214497148027091130013013003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010010000000131012162212951910000100001000010100130033130033130033130033130033

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0032

retire uop (01)cycle (02)03191e3f4f51schedule 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)91inst branch cond (94)inst int alu (97)inst simd alu (9a)9fld unit uop (a6)l1d cache writeback (a8)acbranch cond mispred nonspec (c5)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
3002413003597404261300171194082540010100102000410000102000010000506215001148041500130013013003213003212548931262933001020100002000020100002000013003613003211200211094101001010000101000000012703161212951910000100001000010010130033130033130033130033130033
30024130032974001300171194082540010100102000010000102000010000506214497148005281130013013003213003212548931262623001020100002000020100002000013003213003211200211090101001010000101000000012703161212952010000100001000010010130074130033130061130035130033
30024130032974001300171194082540010100102000010000102000010000506214497148005281130013013003213003212548931262623001020100002000020100002000013003213003611200211090101001010000101000000012705163212951910000100001000010010130033130033130033130033130033
30024130032974001300171194083840010100102000010000102000010000506215003148005281130013013003213003212548931262623001020100002000020100002000013003213003211200211090101001010000101000000012702162212951910000100001000010010130033130033130033130033130033
30024130032974001300171194082540010100102000010000102000010000506214497148005281130013013003213003212553231262623001020100002000020100002000013003213003211200211090101001010000101000006012703162212951910000100001000010010130057130035130036130069130034
300241300329740151300171194082540010100102000010000102000010000506214497148005281130013013003213003212548931262623001020100002000020100002000013003213003311200221090101001010000101000000012702162212951910000100001000010010130033130033130033130033130033
300241300329740013001711940825400101001020000100001020000100005062144971480052811300140130032130032125568191262733001020100002000020100002000013003213003211200211090101001010000101000000012704162412951910000100001000010010130033130033130033130033130033
30024130032974001300171194082540010100102000010000102000010000506214497148005281130013013003213003212554931262623001020100002000020100002000013003213003211200211090101001010000101000000012702163412951910000100001000010010130033130033130033131038130035
300241300351166001300171194082540010100102000010000102000010000506214497148005281130013013003213003212548931262623001020100002000020100002000013003213003211200211090101001010000101000000012704162212957710000100001000010010130033130033130033130033130033
300241300329740331300171194082540010100102000010000102000010000506214497148005281130013013003213003212551131262623001020100002000020100002000013003213003211200211090101001010000101000000012704162312952310000100001000010010130033130033130033130033130033

Test 3: throughput

Count: 8

Code:

  ucvtf h0, x8
  ucvtf h1, x8
  ucvtf h2, x8
  ucvtf h3, x8
  ucvtf h4, x8
  ucvtf h5, x8
  ucvtf h6, x8
  ucvtf h7, x8
  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)031e1f3f4f51schedule 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)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 access (a0)a5ld unit uop (a6)l1d cache writeback (a8)a9acbranch 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
16020426711207002669402516010010080000800001008002080015500116895118841631266902670926709663206665816013520080020800202008002080020267602677111802011009910010080000100008000000011151172160026706080000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841630266902670926709663206665816013520080020800202008002480020267862673311802011009910010080000100008000000011151170160026706080000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841630266902670926709663206665816013520080020800202008002080020268122671811802011009910010080000100008000000011151170160026706080000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080014500116895118789150266902670926709663206665816013520080020800202008002080024268162671411802011009910010080000100008000000011151171160026706080000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841630266902670926709663206665816013520080020800202008002080020267092670911802011009910010080000100008000000011151171160026708080000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841631266902670926709663206665816013520080020800202008002080024268182671511802011009910010080000100008000000011151170160026729080000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841630266902671126709663206665816013420080020800202008002080020267812670911802011009910010080000100008000000011151170160026706080000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841630266902670926709663206665816013520080020800202008002480020268532672111802011009910010080000100008000000011151170160026706080000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841630266902670926709663206665816013520080020800202008002080020268562671511802011009910010080000100008000000011151170160026706080000800001002671026710267102671026710
16020426709207002669402516010010080000800001008002080015500116895118841631266902670926709663206665816013520080020800202008002480020267222683011802011009910010080000100008000000011151170160026706080000800001002671026710267102671026710

1000 unrolls and 10 iterations

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

retire uop (01)cycle (02)03l2 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)60696d6emap 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 access (a0)l1d tlb miss (a1)a5ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acc2branch mispred nonspec (cb)cfd5map dispatch bubble (d6)d9dbddfetch restart (de)e0? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
16002426709207000002669402516001010800008000010800008000050116888018840320266902670926709665303668916001020800008000020800008000026709267091180021109101080000100008000000000050204160544267188000080000102671026710267102671026710
16002426709207000002669402516001010800008000010800008000050116888018840320266902670926709665303668916001020800008000020800008000026709267091180021109101080000100008000000000050204160533267068000080000102671026710267102671026710
16002426709207000002669402516001010800008000010800008000050116888018840320266902670926709665303668916001020800008000020800008000026709267091180021109101080000100008000001000050204160534267068000080000102671026710267102671026710
160024267092060069247042754122516001010800008013010800008000050116888018840320266942671026709679881149724616146522818938057020815188075928200273791018002110910108000010201448130300444552050204160544268458000080000102671026714267142671026710
160024267092071050616272114993021615721080910801301080558814245011908241942530026690267092670966530366891600102080000800002080189800002670926709118002110910108000010202548013300469902050643160533267068000080000102671026710267102671028209
1600242671421701154088274774322641602701280650809101080743814245012131701899180026690267162671966530366891600102080000800002080000800002670926709118002110910108000010000801321108780050204160545267068000080000102671026710267102676426710
160024267122070006026694025160010108000080000108000080000501168880188325602669826715267186659036695160010208000080000208000080000267092670911800211091010800001000080000000000502051610034267068000080000102671526719267162671026710
16002426713215000002669722516001010800008000010800008000050116888018840320266902670926709665303668916001020800008000020800008000026709267091180021109101080000100008000000090050204160044267068000080000102671026710267102671026710
16002426709207000002669402516001010800008000010800268020550118232718926521266942672026709665303668916001020800008000020800008000026709269861180021109101080000100008000000060150204160044267068000080000102671426710267102671026710
16002426709207000002669402516001010800008000010800008000050116888018840320266902671426709665303669016001020800008000020800008000026709267091180021109101080000100008000000000050203160053267068000080000102671026714267102671026710