Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

UCVTF (vector, integer, 4S from 4S)

Test 1: uops

Code:

  ucvtf v0.4s, v0.4s
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
100430372406125472510001000100039816030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
100430372406125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372406125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372406125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  ucvtf v0.4s, v0.4s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080a1e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233020061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001007102162229633000100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633000100001003003830038300383003830038
10204300372330200749295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001007102162229633000100001003003830038300383003830038
10204300372330212061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633000100001003003830038300383003830038
1020430037233020061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633000100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633000100001003003830038300383003830038
10204300372330212061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633000100001003003830038300383003830038
1020430037232020061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633000100001003003830038300383003830038
1020430037233020061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633000100001003003830038300383003830038
1020430037232020061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633000100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030918191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a9acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300372110021109101010000100000000640216222962910000103003830038300383003830038
10024300372250000072629547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
10024300372250000074029547251001010100001010000504277160130054300373003728286328767100102010000201000030037300371110021109101010000100000020640216222962910000103003830038300383003830038
10024300372250222641126129547251001010100001010000504277160130018300373003728286328786103132210000201000030037300371110021109101010000100000400500640333222962910000103003830038300383007430038
10024300372241001682006129547251001010100001010000504277160030018301333013128286328767103112010000201000030037300371110021109101010000102020584500640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037224000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
10024300372250002706129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  ucvtf v0.4s, v8.4s
  ucvtf v1.4s, v8.4s
  ucvtf v2.4s, v8.4s
  ucvtf v3.4s, v8.4s
  ucvtf v4.4s, v8.4s
  ucvtf v5.4s, v8.4s
  ucvtf v6.4s, v8.4s
  ucvtf v7.4s, v8.4s
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)031e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8a9acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061155030258010810080008100802295006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100320011151182160200360800001002004020040200402004020040
8020420039155030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151180160200360800001002004020040200402004020040
8020420039156030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151180160200360800001002004020040200402004020040
8020420039155030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100050311151180160200360800001002004020040200402004020040
8020420039156030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160200360800001002004020040200402004020040
802042003915512302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000002711151181160200360800001002004020040200402004020040
8020420039156030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100020311151180160200360800001002004020040200402004020040
80204200391551230258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000311151180160200360800001002004020040200402004020040
8020420039155030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100050311151180160200360800001002004020040200402004020040
80204200391560302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000004811151180160200360800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)031e3a3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8a9acc5cfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391551032070525800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001020000050204160552003680000102004020040200402004020040
8002420039155004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000009050209160422003680000102004020040200402004020040
80024200391560098325800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000003050204160522003680000102004020040200402004020040
80024200391560040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000018050204160242003680000102004020040200402004020040
8002420039155004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000050205160522003680000102004020040200402004020040
80024200391550040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000087050204160522003680000102004020040200402004020040
80024200391550040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000096050203160452003680000102004020040200402004020040
80024200391550040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000081050204160352003680000102004020040200402004020040
80024200391550040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000078050204160422003680000102004020040200402004020040
8002420039155004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050205160442003680000102004020040200402004020040