Apple M1 Microarchitecture Research by Dougall Johnson

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

ADDV (8B)

Test 1: uops

Code:

  addv b0, v0.8b
  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)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372230612547251000100010003981603018303730372414328951000100020003037303711100110000073216222629100030383038308630383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
10043037231410612547251000100010003981603018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372230612547251000100010003981603018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
1004303723150612547251000100010003981603018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  addv b0, v0.8b
  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)030b181e1f3f4e51inst 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)9fa0a8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000061295474510100100100001001000050042771600300183003730037282643287451027220210168200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225005370726295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225005100251295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500513061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183008430037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372250000103295474410100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000001071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9facc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250005250612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037211002110910101000010006402162229629010000103003830038300383003830038
10024300372250002370612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250008490612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  addv b0, v8.8b
  addv b1, v8.8b
  addv b2, v8.8b
  addv b3, v8.8b
  addv b4, v8.8b
  addv b5, v8.8b
  addv b6, v8.8b
  addv b7, v8.8b
  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)0307181e3a3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500000302580108100800081008002050064013202002002003920039997769990801202008003220016006420039200391180201100991001008000010000111511811600200360800001002009220040200402004020040
80204200391500000302580108100800081008002050064013202002002003920039997769990801202008003220016006420039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
80204200391500000952580108100800081008002050064013202002002003920039997769990801202008003220016006420039200391180201100991001008000010000111511801600200860800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002002003920039997769990801202008003220016006420039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002002003920039997769990801202008003220016006420039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002002003920039997769990801202008003220016006420039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
80204200391500000302580108100800081008002050064013212002002003920039997769990801202008003220016006420039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200200200392003999776999080120200800322001600642003920039118020110099100100800001000536111511801600200360800001002004020040200402004020040
80204200391500000302580108100800081008002050064013212002002003920039997769990801202008003220016006420039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039150003690302580108100800081008002050064013212002002003920039997769990801202008003220016006420039200391180201100991001008000010000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)9fa6a8accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050200416442003680000102004020040200402004020040
80024200391500361292580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050200416422003680000102004020040200402004020040
800242003915000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050200416422003680000102004020040200402004020040
800242003915006402580010108009710800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050200216242003680000102004020040200402004020040
800242003915000402580010108000010800005064075601200202003920039999631001980010208000020160000200392003911800211091010800001000050200216422003680000102004020040200402004020040
800242003915000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050200416422003680000102004020040200402004020040
800242003915000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050200216442003680000102004020040200402004020040
8002420039150004392580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050200216442003680000102004020040200402004020040
80024200391500040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100052550200416442003680000102004020040200402004020040
800242003915000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000050200216422003680000102004020040200402004020040