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, 2S)

Test 1: uops

Code:

  fcvtms v0.2s, v0.2s
  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)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
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100031273116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372309125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100006673116112629100030383038303830383038
1004303723010425472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110001373116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtms v0.2s, v0.2s
  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)030b191e3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037232000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372330001032954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372320003882954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010001071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010001071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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)6061696d6edispatch 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225400612954725100101010000101000050427716010300183003730037282863288051001020100002010000300373003711100211091010100001000640002162229629010000103003830038300383003830038
1002430131225000612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000640002162229629010000103003830038300383003830038
1002430037225000612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000640002162229629010000103003830038300383003830038
1002430037225000612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000640002162229629010000103003830038300383003830038
1002430037225000612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000640002162229629010000103003830038300383003830038
1002430037225000612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000640002162229629010000103003830038300383003830038
1002430037225000612954725100101010000101000050427716010300183003730037282863287671001022100002010000300373003711100211091010100001000640002162229629010000103003830038300383003830038
1002430037225000612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000640002162229629010000103003830038300383003830038
1002430037224000612954767100171010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000640002162229629010000103003830038300383003830038
1002430037225000612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000640002162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtms v0.2s, v8.2s
  fcvtms v1.2s, v8.2s
  fcvtms v2.2s, v8.2s
  fcvtms v3.2s, v8.2s
  fcvtms v4.2s, v8.2s
  fcvtms v5.2s, v8.2s
  fcvtms v6.2s, v8.2s
  fcvtms v7.2s, v8.2s
  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)031e1f3f51inst 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)9fa0a1a8acc5branch mispredict (cb)cdcfd6dcddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200501553000201258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181600020036800001002004020040200402004020040
802042003915612030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181600020036800001002004020040200402004020040
8020420039155387030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181600020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401321200202003920039997769990802252008003220080032200392003911802011009910010080000100000311151181600020036800001002004020040200402004020040
802042003915524030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181600020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181600020036800001002004020040200402004020040
8020420039156321030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181600020036800001002004020040200402004020040
802042003915548030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001011151181600020036800001002004020040200402004020040
8020420039155351030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181600020036800001002004020040200402004020040
802042003915572030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181600020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f4651inst 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)6061696d6edispatch 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)9fa8accfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915504002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000716632003680000102004020040200402004020040
800242003915504002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000316662003680000102004020040200402004020040
800242003915504002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000516532003680000102004020040200402004020040
800242003915504002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000316662003680000102004020040200402004020040
800242003915604002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010035020000516652003680000102004020040200402004020040
800242003915504002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000316452003680000102004020040200402004020040
80024200391550400258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502000025716532003680000102004020040200402004020040
800242003915504002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000316452003680000102004020040200402004020040
800242003915504002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000516532003680000102004020040200402004020040
800242003915504002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000516352003680000102004020040200402004020040