Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSUB (vector, 2D)

Test 1: uops

Code:

  sqsub v0.2d, v0.2d, v1.2d
  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
1004303723010325482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
100430372396125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303724216125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722246125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372366125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqsub v0.2d, v0.2d, v1.2d
  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)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
10204300372250126295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003013430135300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372240168295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020210000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200203603003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250170295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250156295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000026329548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722400000022929548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372240000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830085
1002430037225000681006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250001080012429548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372240000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000027896732429880310000103036930370303703037130369

Test 3: Latency 1->3

Code:

  sqsub v0.2d, v1.2d, v0.2d
  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)03080b18191e1f3f4e51inst 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)696b6d6edispatch 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)9fa1a6a8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224000000612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300372110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731330018030037300372826532874510100200101662002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731330018030037300372827932874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038

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)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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224016629548251001010100001010000504277313153001830037300372828732876710010201000020200003003730037111002110910101000010006405216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313153001830037300372828732876710010201000020200003003730037111002110910101000010006405216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313053001830037300372828732876710010201000020200003003730037111002110910101000010006405216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313103001830037300372828732876710010201000020200003003730037111002110910101000010006405216222963010000103003830038300383003830038
100243003722508929548251001010100001010000504277313153001830037300372828732876710010201000020200003003730037111002110910101000010006405216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313053001830037300372828732876710010201000020200003003730037111002110910101000010006405216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313103001830037300372828732876710010201000020200003003730037111002110910101000010006400216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313103001830037300852828732876710010201000020200003003730037111002110910101000010006400216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313103001830037300372828732878610010201000020200003003730037111002110910101000010006405216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313053001830037300372828732876710010201000020200003003730037111002110910101000010006400216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqsub v0.2d, v8.2d, v9.2d
  sqsub v1.2d, v8.2d, v9.2d
  sqsub v2.2d, v8.2d, v9.2d
  sqsub v3.2d, v8.2d, v9.2d
  sqsub v4.2d, v8.2d, v9.2d
  sqsub v5.2d, v8.2d, v9.2d
  sqsub v6.2d, v8.2d, v9.2d
  sqsub v7.2d, v8.2d, v9.2d
  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)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)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)9fa0a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000511031622200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000511021622200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000511021622200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000511021622200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000511021632200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000511021622200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000511021622200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000511021622200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000511021622200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000511021622200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)9fa0a1a6a8accficache miss (d3)d5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502002167232003680000102004020040200402004020040
800242003915000193258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502003166342003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502003166452003680000102004020040200402004020040
800242003915000149258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502002166432003680000102004020040200402004020040
8002420039150020740258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502002167332003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502002167532003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202008920039999631001980010208000020160000200392003911800211091010800001000000502002167432003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502004167442003680000102004020040200402004020040
800242003915000248258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502003167542003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502002167342003680000102004020040200402004020040