Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTPS (scalar, S to S)

Test 1: uops

Code:

  fcvtps s0, s0
  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
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372308225472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372408425472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724013425472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110004673116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtps s0, s0
  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)03080b1e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010018071021611296330100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771600300183003730037282673287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037232000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372330000131295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372320000251295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006403162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037224000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037224000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtps s0, s8
  fcvtps s1, s8
  fcvtps s2, s8
  fcvtps s3, s8
  fcvtps s4, s8
  fcvtps s5, s8
  fcvtps s6, s8
  fcvtps s7, s8
  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)03080b18191e1f3f51inst 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)72scheduler 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)9fa0a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591560000003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511811600200360800001002004020040200402004020040
80204200391560000003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391550000003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000002000111511801600200360800001002004020040200402004020040
80204200391560000603025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000001000111511801600200360800001002004020040200402004020040
80204200391560000003025801081008000810080020500640132020020200392003999890699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391550000003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000002000111511801600200360800001002004020040200402004020040
802042003915500001205225801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391550000003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391550000003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
80204200391550000003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304081e3f51inst 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)60696b6d6edispatch 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)9fa8accdcfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015520082258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
8002420039155001261258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
800242003915600040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
800242003915600040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040