Apple M1 Microarchitecture Research by Dougall Johnson

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

ADDV (8H)

Test 1: uops

Code:

  addv h0, v0.8h
  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)0308090b18191e1f3a3f4e51inst 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)a0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372200000000612547251000100010003981600301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
1004303723000000002232547251000100010003981600301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
100430372200000600612547251000100010003981600301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
100430372200000000612547251000100010003981600301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
100430372300000000612547251000100010003981600301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
100430372200000600612547251000100010003981600301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
100430372300000300612547251000100010003981600301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
100430372300000000612547251000100010003981600301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
100430372300000000612547251000100010003981600301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
100430372200000000612547251000100010003981600301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  addv h0, v0.8h
  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)030809191e3a3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240000014929547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250000056329547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000008429547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000008229547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160030018300373003728264328745101002001018220020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250000012429547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372240000061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000517101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277363130018300373003728264328745101002001000020020000300373003711102011009910010010000100037101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3a3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250014529547251001010100001010000504277160130018030037300372828632876710010201000020200003003730037111002110910101000010000640716232962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020200003003730037111002110910101000010000640216232962910000103003830038300383003830038
10024300372250059329547251001010100001010000504277160130018030037300372828632876710010201000020200003003730037111002110910101000010100640216232962910000103003830038300383003830038
1002430037225006129547251001010100071010000504277160130018030037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010148504277160130018030037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020200003003730037111002110910101000010190640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020200003003730037111002110910101000010000640216232962910000103003830038300383003830038
10024300372250017029547251001010100001010000504278512130018030037300372828632876710010201000020200003003730037111002110910101000010000640216232962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020200003003730037111002110910101000010000640216232962910000103003830038300383003830038
1002430037225606129547251001010100001010000504277160130018030037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  addv h0, v8.8h
  addv h1, v8.8h
  addv h2, v8.8h
  addv h3, v8.8h
  addv h4, v8.8h
  addv h5, v8.8h
  addv h6, v8.8h
  addv h7, v8.8h
  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)033f51inst 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)696d6edispatch 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)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915072258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100001115118116020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915072258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915081258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204201381503025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010019401115118016020036800001002004020040200402004020040
802042003915072258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200160064200392003911802011009910010080000100001115118016120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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)9fa8acc5cfd2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150001032580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502000216000112003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502000116000112003680000102004020040200402004020040
800242009315000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502000116000112003680000102004020040200402004020040
800242003915006822580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502000116010112003680000102004020040200402004020040
8002420039150002512580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502000116010112003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010100502001116020112003680000102004020040200402004020040
8002420091150104182580010108000010800005064000012006820039200399996310019800102080000201600002003920039118002110910108000010000502000116010112003680000102004020040200402004020040
800242003915000822580010108000010800005064016412002020039200399996310019800102080000201600002003920039118002110910108000010000502000116000112003680000102004020040200402004020040
800242003915000822580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010130502000116000112003680000102004020040200402004020040
8002420039150001052580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502000116010112003680000102004020040200402024920040