Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTMS (vector, 4S)

Test 1: uops

Code:

  fcvtms 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)031e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112642100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtms 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)03181e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037233054204295472510100100100001001000057642771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372320061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372330066295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372320061295382510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001001307101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa0a8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003725300066061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
1002430037232004240612954762100281410016121030061427986403009030132301782829512288031031522104952210330301313013331100211091010100001020547020704241332962910000103003830038300383003830038
10024300372321212911121291295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001001000640216222962910000103003830038300383003830038
10024300372330000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003722400000346295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216512962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250000084295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtms v0.4s, v8.4s
  fcvtms v1.4s, v8.4s
  fcvtms v2.4s, v8.4s
  fcvtms v3.4s, v8.4s
  fcvtms v4.4s, v8.4s
  fcvtms v5.4s, v8.4s
  fcvtms v6.4s, v8.4s
  fcvtms 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)030b1e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391560072258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550930258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915610505618010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100101115118016020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391560030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550930258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040

1000 unrolls and 10 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)5f60696d6edispatch 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)9fa1a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420040155040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020316242003680000102004020040200402004020040
80024200391550610258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001023005038416522003680000102004020040200402004020040
8002420039155040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000305020316522003680000102004020040200402004020040
800242003915504025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100395305020316242003680000102004020040200402004020040
8002420039155061258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020516422003680000102004020040200402004020040
80024200391550402580010108000010800005064000001200202003920039999626100198001020800002080000200392003911800211091010800001000005020316542003680000102004020040200402004020040
80024200391550402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010016005020216252003680000102004020040200402004020040
8002420039155040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020416242003680000102004020040200402004020040
8002420039156040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020216422003680000102004020040200402004020040
80024200391550420258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020516422003680000102004020040200402004020040