Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMEQ (scalar, zero, S)

Test 1: uops

Code:

  fcmeq s0, s0, #0
  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)03070a1e3a3f4e51inst 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
100420371511026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
100420371511026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
100420371511026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
100420371511028916862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
100420371511028916862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
100420371511026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
100420371611026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
100420371511026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
100420371511026816862510001000100026452112018203720371571318951000100010002037203711100110000077416441786100020382038203820382038
100420371511026816862510001000100026452102018203720371571318951000100010002037203711100110000077416441786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmeq s0, s0, #0
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371509061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150001083196862510100100100001001000050028475211200652003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150198061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150010861196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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
10024200371500000150611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010020000006402165219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010200000006402162219786010000102003820038200382003820038
100242003715000001801021968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500020240611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000150821968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000330611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163219786010000102003820038200382003820038
10024200371500000120611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102013320038200382003820038
10024200371500000001031968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmeq s0, s8, #0
  fcmeq s1, s8, #0
  fcmeq s2, s8, #0
  fcmeq s3, s8, #0
  fcmeq s4, s8, #0
  fcmeq s5, s8, #0
  fcmeq s6, s8, #0
  fcmeq s7, s8, #0
  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)030818191e1f3a3f51inst 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)9fa6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500001800292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511821600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
802042003815000011100642680116100800161008002850064019602002820048200499976999868012820080038200800382004820049118020110099100100800001000000222512812311200450800001002004920050200502004920049
8020420048150000000642680116100800161008002850064019612002820048200489976999868012820080038200800382004820048118020110099100100800001000000222512812311200450800001002004920049200492005020049
8020420048150000000642780116100800161008002850064019602002820048200489976999868012820080038200800382004820048118020210099100100800001000000221512912311200450800001002005020050200502004920049

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)9fa8cfd0icache miss (d3)d5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001005020003161120035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020002161120035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020001161120035080000102003920039200392003920039
800242003815040239258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001005020001161120035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020002162220035080000102013820039200392003920039
800242003815030339258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001005020001161120035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020001161120035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020001161120035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020002161120035080000102003920039200392003920039
8002420038149381704258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020001161120035080000102003920039200392003920039