Apple M1 Microarchitecture Research by Dougall Johnson

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

ADDV (16B)

Test 1: uops

Code:

  addv b0, v0.16b
  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
10043037222106125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037226606125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723606125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110001073116112629100030383038303830383038
10043037231206125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230022925472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  addv b0, v0.16b
  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)031e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129547251010010010000100100005004277160030018030037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160030018030037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722406129547251010010010000100100005004277160030018030037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018030084300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722406129547251010010010000100100005004277160130018030037300372826482874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018030037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018030037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018030037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722406129547251010010010000100100005004277160130018030037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722406129547251010010010000100100005004277160030018030037300852826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129547251001010100001010000504277160030018300843003728286328767100102010000202000030037300371110021109101010000100000640316222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100000640216122962910000103003830038300383003830038
1002430037225072629547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100100640216222962910000103003830038300383003830038
1002430037225377529547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100028780661216222962910000103003830038300383003830038
1002430037225053629547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225010329547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100130640216222962910000103003830038300383003830069
100243003722506129547251001010100001010000604277160030054300373003728290328767100102010000202000030037300372110021109101010000100004640232242962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  addv b0, v8.16b
  addv b1, v8.16b
  addv b2, v8.16b
  addv b3, v8.16b
  addv b4, v8.16b
  addv b5, v8.16b
  addv b6, v8.16b
  addv b7, v8.16b
  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)0308090b18191e1f3f51inst 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)9fa0a1a6a8acc5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420125151011121561163025801081008000810080020500640132020020200392003999776100168012020080032200160064201162010611802011009910010080000100022001115118116220036800001002004020040200402004020040
802042003915000000150302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
802042003915000000006952580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040
80204200391500000000302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000001115118016020036800001002004020040200402004020040

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)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)9fa8accfd0d5d6d9dbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500402580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001003502006160075200360080000102004020040200402004020040
80024200391500402580010108000010800005064000012002002003920039999631001980010208000020160000200392003911800211091010800001000502007160075200360080000102004020040200402004020040
80024200391500402580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001006502007160057200360080000102004020040200402004020040
80024200391500402580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000502007160075200360080000102004020040200402004020040
800242003915004025800101080000108000050640000120020020039200399996310019800102080000201600002003920039118002110910108000010012502007160057200360080000102004020040200402004020040
80024200391500402580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000502005160075200360080000102004020040200402004020040
80024200391500402580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000502005160057200360080000102004020040200402004020040
8002420039150040258001010800001080000506400000200200200392003999963100198001020800002016000020039200391180021109101080000100111502005160075200360080000102004020040200402004020040
800242003915004025800101080000108000050640000020020020039200399996310019800102080000201600002003920039118002110910108000010005020071620572003620080000102004020040200402004020040
80024200391500402580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000502005160057200360080000102004020040200402004020040