Apple M1 Microarchitecture Research by Dougall Johnson

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

UABDL (vector, 8H)

Test 1: uops

Code:

  uabdl v0.8h, v0.8b, v1.8b
  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)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)a8cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)f5f6f7f8fd
10043037232406125482510001000100039831313018303730372415328951000100020003037303711100110000731161126300100030383038303830383038
10043037232106125482510001000100039831313018303730372415328951000100020003037303711100110000731161126300100030383038303830383038
10043037230041025482510001000100039831313018303730842415329071000100020003037303711100110000731161126300100030383038303830383038
10043037220061254825100010001000398313130183037303724153289510001000200030373037111001100007311611263011100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000731161126300100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000731161126300100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000731161126300100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100020003037303711100110000731161126300100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000731161126300100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100020003037303711100110000731161126300100030383038303830383038

Test 2: Latency 1->2

Code:

  uabdl v0.8h, v0.8b, v1.8b
  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)030b1e3f4e51inst 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)9fa9c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129548251010010010000100100005004277313130018300373003728272628741101002001000820020016300373003711102011009910010010000100011171701600296460100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728272728741101002001000820020016300373003711102011009910010010000100011171801600296470100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728272628741101002001000820020016300373003711102011009910010010000100011171701600296470100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728272628741101002001000820020016300373003711102011009910010010000100011171701600296460100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250044129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

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)9fa8branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010010640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000106000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640224222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010100640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uabdl v0.8h, v1.8b, 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)030918191e1f3f4e51inst 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)9fa6a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110202100991001001000010000007101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000002512954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383008630038
1020430037225000006312954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03091e1f3a3f4e51inst 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)9fa0a1a6a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000060640216222963010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500002902954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000661316332963010000103003830038300383003830038
100243003722500002312954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037211002110910101000010000000640216222970110000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uabdl v0.8h, v8.8b, v9.8b
  uabdl v1.8h, v8.8b, v9.8b
  uabdl v2.8h, v8.8b, v9.8b
  uabdl v3.8h, v8.8b, v9.8b
  uabdl v4.8h, v8.8b, v9.8b
  uabdl v5.8h, v8.8b, v9.8b
  uabdl v6.8h, v8.8b, v9.8b
  uabdl v7.8h, v8.8b, v9.8b
  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)03091e3f51inst 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)9fa8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150094125801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100000051102161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100003051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040201032004020040
8020420039150004125801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020093
8020420039150004125801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
80204200391500034725801001008000010080000500640000020020200392003999730399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e1f3f51inst 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)9fa1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050206163520036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050205165320036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050205163520036080000102004020040200402004020040
800242003915000029704025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050203163520036080000102004020040200402004020040
80024200391500001804025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050203163520036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050203163520036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050205163520036080000102004020040200402004020040
8002420039150000604025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050204165520036080000102004020040200402004020040
800242003915000000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000150050205343520036080000102004020040200402009220040
800242003915000101044025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050205165520036180000102004020101200402004020040