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

FJCVTZS

Test 1: uops

Code:

  fjcvtzs w0, d0
  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 2.000

Issues: 3.000

Integer unit issues: 1.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 2.000

retire uop (01)cycle (02)031e3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch simd uop (57)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map simd uop (7e)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst int alu (97)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
2004104180462530001000200020001800011022104110417453774200020002000104110411110011000007311611103810001000100010421042104210421042
2004104183462530001000200020001800011022104110417453774200020002000104110411110011000007311611103810001000100010421042104210421042
2004104180462530001000200020001800011022104110417453774200020002000104110411110011000007311611103810001000100010421042104210421042
2004104180882530001000200020001800011022104110417453774200020002000104110411110011000007311611103810001000100010421042104210421042
2004104180462530001000200020001800011022104110417453774200020002000104110411110011000007311611103810001000100010421042104210421042
2004104180462530001000200020001800011022104110417453774200020002000104110411110011000007311611103810001000100010421042104210421042
2004104180462530001000200020001800011022104110417453774200020002000104110411110011000037311611103810001000100010421042104210421042
2004104180672530001000200020001800011022104110417453774200020002000104110411110011000007311611103810001000100010421042104210421042
2004104180462530001000200020001800011022104110417453774200020002000104110411110011000007311611103810001000100010421042104210421042
2004104180462530001000200020001800011022104110417453774200020002000104110411110011000007311611103810001000100010421042104210421042

Test 2: Latency 1->2 roundtrip

Code:

  fjcvtzs w0, d0
  fmov d0, x0
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 13.0038

retire uop (01)cycle (02)03mmu table walk instruction (07)mmu table walk data (08)18191e1f3f4e51schedule 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)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acc2branch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd0d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
3020413003897400000013002312950425401001010020000100001002000010000500528887193220980130013013003813003812568671262413010020010002200062001000220006130038130040112020110099100101001000010001000000000111131701161112960110000100001000010100130039130039130039130039130039
3020413003897400000013002312950425401001010020000100001002000010000500528887193220980130013013008513004012568661262413010020010002200062001000220006130038130038112020110099100101001000010001000000000111131801160112960010000100001000010100130039130039130039130039130039
3020413003897400000013002312950425401001010020000100001002000010000500528887193220980130013013003813003812567931262463010020010000200002001000020000130038130038112020110099100101001000010001000000000000131012162212959010000100001000010100130039130039130039130039130039
3020413003897400000013002312950425401001010020000100001002000010000500528887193220980130013013003813003812567931262553010020010000200002001000020000130038130041112020110099100101001000010001000000000000131012162212959010000100001000010100130039130039130039130039130039
3020413003897400000013002312950425401001010020000100001002000010000500528887193220980130013013003813003812567931262463010020010000200002001000020000130038130038112020110099100101001000010001000000000000131012162212959010000100001000010100130039130039130039130039130039
3020413003897400000013002312950425401001010020000100001002000010000500528887193220980130013013003813003812567931262463010020010000200002001000020000130040130038112020110099100101001000010001000000000000131012162212959010000100001000010100130039130039130039130039130039
3020413003897400000013002312950425401001010020000100001002000010000500528887193220980130013013003813003812567931262463010020010000200002001000020000130077130039112020110099100101001000010001000000000000131012162312959010000100001000010100130039130039130039130039130039
3020413003897400000013002312950425401001010020000100001002000010000500528887193220980130013013003813003812567931262463010020010000200002001000020000130040130038112020110099100101001000010001000000000000131012162212959010000100001000010100130039130039130039130077130039
3020413003897400000013002312950425401001010020000100001002000010000500528887193220980130013013003813003812567931262463010020010000200002001000020000130379130038112020110099100101001000010001000000000000131012172312959010000100001000010100130039130039130039130039130039
3020413003897400000013002312950425401001010020000100001002000010000500528887193220980130013013003813003812567931262463010020010000200002001000020000130052130038112020110099100101001000010001000000000000131012162212959010000100001000010100130039130039130039130039130039

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0038

retire uop (01)cycle (02)03l2 tlb miss data (0b)18191e3a3f4e51schedule 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)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)st unit uop (a7)l1d cache writeback (a8)a9acc2branch 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
30024130038974000001300231295042540010100102000010000102000010000505287724932209813001313003813003812570131262683001020100002000020100002000013003813003811200211091010010100001010000030000012701161112959010000100001000010010130039130039130039130039130040
30024130083974000001300231295042540010100102000010000102000010000505287724932209813001313003813003812570131262683001020100002000020100002000013003813003811200211091010010100001010000070000012701161112959010000100001000010010130039130039130039130039130039
30024130038974000001300231295042540010100102000010000102000010000505287724932209813001313003813003812570131262683001020100002000020100002000013003813003811200211091010010100001010000000000012701161112959010000100001000010010130039130039130039130088130039
30024130038974000901300231295042540010100102000010000102000010000505287724932209813001313003813003812570131262683001020100002000020100002000013003813003811200211091010010100001010000000000012701161112959010000100001000010010130039130039130039130039130039
30024130038974000001300231295042540010100102000010000102000010000505287724932209813001313003813003812570131262683001020100472000020100002000013003813003811200211091010010100001010000020001012701161112959010000100001000010010130039130039130039130039130040
30024130038974000001300231295042540010100102000010000102000010000505287724932209813001313003813003812570131262683001020100002000020100002000013003813003811200211091010010100001010000000000012701161112959010000100001000010010130039130039130039130039130039
3002413003897400070201300231295052540010100102000010000102000010000505287724932209813001313003813003812570131262683012520100002000020100002000013003813003811200211091010010100001010000010040012701161112959010000100001000010010130039130039130039130039130039
30024130038974000001300231295042540010100102000010000102000010000505287724932209813001313003813003812570131262683001020100002000020100002000013003813003811200211091010010100001010000000000012701162112959010000100001000010010130039130039130039130039130058
30024130038974055011300231295082540010100112001610010112044410211555297334932927213001313054613020812570631262683001020100002000020100002000013004013003811200211091010010100001010000030000012701161112959010000100001000010010130039130039130039130039130039
30024130038974000001300231295042540010100102000010000102000010000505287724932209813001313003813003812570131262683001020100002000020100002000013003813003811200211091010010100001010000000000012701161112959010000100001000010010130039130039130039130039130039

Test 3: throughput

Count: 8

Code:

  fjcvtzs w0, d8
  fjcvtzs w1, d8
  fjcvtzs w2, d8
  fjcvtzs w3, d8
  fjcvtzs w4, d8
  fjcvtzs w5, d8
  fjcvtzs w6, d8
  fjcvtzs w7, d8
  mov x8, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.0005

retire uop (01)cycle (02)03l2 tlb miss data (0b)191e1f3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696b6d6emap stall dispatch (70)flags prf full (73)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)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)9fl1d cache writeback (a8)acbranch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
160204800576000012034252401008010016000010016000450014400241800220800418004159976075999316010420016001620016001680041800411180201100991008010010000111511701600800388000080000801008009280042800428004280042
16020480041599000034252401008010016000010016000450014400241800220800418004159976075999416010420016001620016001680041800411180201100991008010010000111511701600800388000080000801008004280042800428004280042
16020480041600000034252402498012416000010016000450014400241800220800418004159976075999416010420016001620016001680041800411180201100991008010010000111511601600800388000080000801008004280042800428004280042
16020480041600000035252401008010016000010016000450014400241800220800418004159976075999316010420016001620016001680041800411180201100991008010010000111511701600800388000080000801008004280042800428004280042
160204800415990000699252401008010016000010016000450014400241800220800418004159976075999416010420016001620016001680041800411180201100991008010010000111511701600800388000080000801008004280042800428004280042
160204800416000000224252401008010016000010016000450014400241800220800418004159976075999416010420016001620016001680041800411180201100991008010010000111511601600800388000080000801008004280042800428004280042
16020480041599000034252401008010016000010016000450014400241800220800418004159976075999316010420016001620016001680041800411180201100991008010010060111511711600800388000080000801008004280042800428004280042
16020480041600000035252401008010016005210016000450014400240800220800418004159976075999316010420016001620016001680041800411180201100991008010010000111511701600800388000080000801008004280042800428004280042
16020480041599000034252401008010016000010016000450014400240800220800418004159976075999416010420016001620016001680041800411180201100991008010010000111511601600800388000080000801008004280042800428004280042
16020480041600000034252401008010016000010016000450014400241800220800418004159976075999416010420016001620016001680041800411180201100991008010010009111511701610800388000080000801008004280042800428004280042

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0005

retire uop (01)cycle (02)03mmu table walk data (08)18191e1f3a3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696b6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)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)9fl1d tlb miss (a1)l1d cache writeback (a8)acc2branch mispred nonspec (cb)cfd0d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
160024800415990000001042524001080010160000101600005014400000800220800418008959992360021160010201600002016000080041800411180021109108001010000005020041642800378000080000800108004280042800428004280042
16002480041599000000682524001080010160000101600005014400000800220800418004159992360021160010201600002016000080041800411180021109108001010000005020041624800378000080000800108004280042800428004280042
160024800415990000007412524001080010160000101600005014400000800220800418004159992360021160010201600002016000080041800411180021109108001010000005020021644800378000080000800108004280042800428004280042
160024800415990000006982524001080010160000101600005014400001800220800418004159992360021160010201600002016000080041800411180021109108001010000005020021624800378000080000800108004280042800428004280042
160024800415990000006052524001080010160000101600005014400000800220800418004159992360021160010201600002016000080041800411180021109108001010000005020041624800378000080000800108004280042800428004280042
160024800415990000001302524001080010160000101600005014400000800220800418004159992360021160010201600002016000080041800411180021109108001010000005020041642800378000080000800108004280042800428004280042
160024800415990000006472524001080010160000101600005014400000800220800418004159992360021160010201600002016000080041800411180021109108001010000005020041642800378000080000800108004280042800428004280042
160024800416000000004992524001080010160000101600005014400000800220800418004159992360021160010201600002016000080041800411180021109108001010000005020021624800378000080000800108004280042800428004280042
160024800416000000006682524001080010160000101600005014400000800220800418004159992360021160010201600002016000080041800411180021109108001010000005020041663800378000080000800108004280042800428004280042
1600248004160000000021402524001080010160150101600005014400000800220800418004159992360021160010201600002016000080041800411180021109108001010000005020021624800378000080000800108004280042800428004280042