Apple M1 Microarchitecture Research by Dougall Johnson

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

SRSHL (vector, 4H)

Test 1: uops

Code:

  srshl v0.4h, v0.4h, v1.4h
  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
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722036825482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100002473116112630100030383038303830383038
100430372396125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  srshl v0.4h, v0.4h, v1.4h
  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)03081e3a3f4e51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000612954825101001001000010010000500427731303001830037300372827272874010100200100082002001630037300371110201100991001001000010000011171701600296470100001003003830038300383003830038
10204300372250005362954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250002322954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010010000071011611296340100001003003830038300383003830038
10204300372250009352954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010010000071011611296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010030300071011611296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200101722002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037224000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010010000071011611296340100001003003830038300383003830038

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773133001803003730037282873287671001020101622020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722503395295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010121000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372240156295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001030640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  srshl v0.4h, v1.4h, v0.4h
  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)0307090b18191e1f3f4e51inst 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)9fa1a6a8a9acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224100000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037224000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000010000071021622296340100001003003830038300383003830038
1020430037224000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037224000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037224000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308181e1f3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000612954825100361010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010003640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010010640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010010640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037224000176612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  srshl v0.4h, v8.4h, v9.4h
  srshl v1.4h, v8.4h, v9.4h
  srshl v2.4h, v8.4h, v9.4h
  srshl v3.4h, v8.4h, v9.4h
  srshl v4.4h, v8.4h, v9.4h
  srshl v5.4h, v8.4h, v9.4h
  srshl v6.4h, v8.4h, v9.4h
  srshl v7.4h, v8.4h, v9.4h
  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)0307080b1e1f3f51inst 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)9fa1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420048150000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000030511031622200360800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000511021622200360800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000100511021622200360800001002004020040200402004020040
8020420039150001183881462580100100800001008010650064000012002020039200399973399978022520080000200160000200392003911802011009910010080000100209430511021622200360800001002004020040200402004020040
8020420039150000008325801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511021622200360800001002004020040200402004020040
8020420039150000008325801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000030511021622200360800001002004020040200402004020040
80204200391500001204125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000030511021622200360800001002004020040200402004020040
80204200391500001504125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000001511021622200360800001002004020040200402004020040
802042003915000000169258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000005110216232003624800001002004020040200402004020040
80204200391500004806225801001218000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000511021622200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030809191e1f3f51inst 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)9faccfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500000040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050201316242003680000102004020040200402004020040
800242003915000000342258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050200416342003680000102004020040200402004020040
800242003915000000126258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050200216242003680000102004020040200402004020040
80024200891500000040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050200416422003680000102004020040200402004020040
8002420039150000017640258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050200216242003680000102004020040200402004020040
800242003915000000402580010108000010800005064000020020200902014210006310019800102080000201600002003920039118002110910108000010050560536262003680000102004020040200402014220040
8002420039151113132264806438001011800001080104656416482006220039200399996310019800102080000201600002003920039118002110910108000010050200216242003680000102004020040200402004020040
80024200391500000040258001010800001080000506400002002020039200399996310019800102080000201600002003920039218002110910108000010050200216422003680000102004020040200402004020040
80024200391500000040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050200216242003680000102004020040200402004020040
800242003915000000201258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050200416422003680000102004020040200402004020040