Apple M1 Microarchitecture Research by Dougall Johnson

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

UQADD (scalar, B)

Test 1: uops

Code:

  uqadd b0, b0, b1
  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)030818191e1f3f4e51inst 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)a0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723000006125482510001000100039831313018303730372415328951000100020003037303711100110000000000073116112630100030383038303830383038
1004303723000006125482510001000100039831313018303730372415328951000100020003037303711100110000000000073116112630100030383038303830383038
1004303722000006125482510001000100039831313018303730372415328951000100020003037303711100110000000000073116112630100030383038303830383038
1004303722000006125482510001000100039831313018303730372415328951000100020003037303711100110002001302768479140112689100030383038303830863038
100430372201013506125484510001000100039982013018307330372415629071000100023263037308411100110002000022753094116112647100030383086303830863038
1004303722010006125392510001000100039831313018303730372415328951000100020003037303711100110000000000073116112630100030383038303830383038
1004303723000006125482510001000100039831313018303730372415328951000100020003037303711100110000000000073116112646100030383038303830383038
1004303723000006125482510001000100039831313018303730372415328951000100020003037303711100110000000000073116112630100030383038303830383038
1004303724000008225482510001000100039831313018303730372415328951000100023263146308511100110000030100095145112694100030383038303830383038
10043084241001320117253925100010081089398313130183037303724157291510001168200030373037111001100000001200094116112665100030843131312030383122

Test 2: Latency 1->2

Code:

  uqadd b0, b0, b1
  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)030b191e1f3f4e51inst 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)9fa0a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500001762954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000028457101161129634100001003003830038300383003830038
1020430133225110104612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000037101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372240000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003008630086300383003830038
10204300372240000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037224002101032954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000028287101161129634100001003003830038300383003830038

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250105295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225961295482510010101000011100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqadd b0, b1, b0
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722406129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071021611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722406129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003008630038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080b18191e1f3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006404164629630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006405165429630010000103003830038300383003830038
100243003722500000002012954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006406165629630010000103003830038300383003830038
1002430037225000000084712954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006405166629630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006406165429630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006406165629630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006406165529630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006406165529630010000103003830038300383003830038
10024300372250000060612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000306406165629630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006404166629630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqadd b0, b8, b9
  uqadd b1, b8, b9
  uqadd b2, b8, b9
  uqadd b3, b8, b9
  uqadd b4, b8, b9
  uqadd b5, b8, b9
  uqadd b6, b8, b9
  uqadd b7, b8, b9
  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)0318191e1f3f51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021611200360800001002004020040200402004020040
8020420039150000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
8020420039150000083258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
8020420039150000041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200413180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500000167258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391500000146258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
8020420039150000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
8020420039150000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
8020420039150000083258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200366800001002004020040200402004020040
8020420039150000041448021310080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000511025511200840800001002009220103200942011420040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)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)9fa6accfd2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500040258001010800001080000506400002002020039200399996031001980010208000020160000200392003911800211091010800001000502000131614162003680000102004020040200402004020040
80024200391506040258001010800001080000506400002002020039200399996031001980010208000020160000200392003911800211091010800001000502000131612122003680000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996031001980010208000020160000200392003911800211091010800001000502000101617132003680000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996031001980010208000020160000200392003911800211091010800001000502000161613132003680000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996031001980010208000020160000200392003911800211091010800001000502000161612122003680000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996031001980010208000020160000200392003911800211091010800001000502000121616132003680000102004020040200402004020040
800242003915000705258001010800001080000506400002002020039200399996031001980010208000020160000200392003911800211091010800001000502000131612102003680000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996031001980010208000020160000200392003911800211091010800001000502000171615162003680000102004020040200402004020040
8002420039150010863258001010800001080000506400002002020039200399996031001980010208000020160000200392003911800211091010800001000502000101616162003680000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996031001980010208000020160000200392003911800211091010800001000502000151612102003680000102004020040200402004020040