Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMULL (scalar, S)

Test 1: uops

Code:

  sqdmull s0, h0, h1
  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
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723035525482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037231986125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372209925482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372308425482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372406125482510001000100039831303018303730372415328951000100020003037303711100110000373116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372308225482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqdmull s0, h0, h1
  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)03080b181e1f3f4e51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330101201032954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010001007353251129634100001003003830038300383003830090
1020430037241000750612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372330003005152954825101001221000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722400015352612954825101001001000812410000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372240002250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372240003300612954825101001001000010010000500427778113001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000180612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000270612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000240612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500030612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250061295482510010101000010100005042773130300183003730037282870328767100102010000202000030037300371110021109101010000102180640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010000640216232963010000103008530038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225606129548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828703287671001020100002020344300373003711100211091010100001001890640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000614277313030018300373003728287032876710010201000020200003003730037111002110910101000010800640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqdmull s0, h1, h0
  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)0318191e3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240015661295482510100100100001001000050042773130300183003730037282653287451010020010164204200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000726295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225001261295482510100100100001001000050042773130300183003730037282653287451010020010000200203323003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001002107101161129634100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

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)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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372255161295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010640316332963010000103003830038300383003830038
10024300372251561295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010640316332963010000103003830038300383003830038
10024300372331261295482510010101000010100005042773133005430037300372828732876710010201000020200003003730037111002110910101000010640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010640316332963010000103003830038300383003830038
10024300372251561295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010640316332963010000103003830038300383003830038
10024300372253361295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010640316332963010000103003830038300383003830038
10024300372252761295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010640316332963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqdmull s0, h8, h9
  sqdmull s1, h8, h9
  sqdmull s2, h8, h9
  sqdmull s3, h8, h9
  sqdmull s4, h8, h9
  sqdmull s5, h8, h9
  sqdmull s6, h8, h9
  sqdmull s7, h8, h9
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 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)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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150015025801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100051102161120036800001002004020040200402004020040
8020420039150023625801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
8020420039150067025801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915008325801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999737399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003914906425801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100451101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e3f51inst 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)6061696d6edispatch 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)9fa6a8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010000005020005164220036080000102004020040200402004020040
800242003915002164025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010014305020544162420036080000102004020040200402004020040
8002420039150000124025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000305020544164420036080000102004020040200402004020040
800242003915000094025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000005020544162420036080000102004020040200402004020040
8002420039150000184025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000005020542164420036380000102004020040200402004020040
80024200391500004324025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000005020544164320036180000102004020040200402004020040
8002420039150000953625800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000005020504164420036080000102004020040200402004020040
800242003915000034025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000005020544164320036080000102004020040200402004020040
800242003915000008225800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000005020544164220036080000102004020040200402004020040
800242003915000004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010000005020544164220036080000102004020040200402004020040