Apple M1 Microarchitecture Research by Dougall Johnson

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

URSHL (vector, 16B)

Test 1: uops

Code:

  urshl v0.16b, v0.16b, v1.16b
  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)0308090b18191e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300000061254825100010001000398313301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300000061254825100010001000398313301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300000061254825100010001000398313301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300000061254825100010001000398313301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300000061254825100010001000398313301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300000061254825100010001000398313301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300000061254825100010001000398313301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372200000061254825100010001000398313301830373037241532895100010002000303730371110011000013073116112630100030383038303830383038
1004303722000000612548251000100010003983133018303730372415328951000100020003037303711100110000133073116112630100030383038303830383038
100430372300000061254825100010001000398313301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  urshl v0.16b, v0.16b, v1.16b
  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)030b181e3a3f4e51inst 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)9fa0a1a6a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372240000822954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500007262954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500007262954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500001562954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b191e1f3f4e51inst 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)9fa0a1a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000006129548251001010100001010000504277313130018300373003728304032876710010201000020200003008530083111002110910101000010000600640216222977410000103003830038300383003830038
10024300372251001206129548251001010100001010000504277313130018300373003728287332876710010201000020200003003730037111002110910101000010000300640216222963010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010001900640216222963010000103003830038300383003830038
1002430037224002006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000600640216222963010000103003830038300383003830038
1002430037225003006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000001640216222963010000103003830038300383003830038
10024300372250000010329548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010001900640216222963010000103003830038300383003830038
1002430037225000276886129548251001010100001010000504277313130126300373003728287032876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000121766129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500015010329548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000000640216222966610000103003830038300383003830038

Test 3: Latency 1->3

Code:

  urshl v0.16b, v1.16b, v0.16b
  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)033f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722582295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225145295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225124295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037224451295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003008530038300383003830038
1020430037225535295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225166295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037224167295482510100100100001001014850042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225281295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225449295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000307101161129634100001003003830038300383003830038
1020430037225474295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506302954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001020640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300842250612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722501032954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  urshl v0.16b, v8.16b, v9.16b
  urshl v1.16b, v8.16b, v9.16b
  urshl v2.16b, v8.16b, v9.16b
  urshl v3.16b, v8.16b, v9.16b
  urshl v4.16b, v8.16b, v9.16b
  urshl v5.16b, v8.16b, v9.16b
  urshl v6.16b, v8.16b, v9.16b
  urshl v7.16b, v8.16b, v9.16b
  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)03181e1f3f51inst 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)9fa0a8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000010425801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000051102161120036800001002004020040200402004020040
802042003915000043625801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
8020420039150000108258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010001430051101161120036800001002004020040200402004020040
80204200391500008525801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
802042003915000012725801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
80204200391500004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
802042003915000048525801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
80204200391500006425801001008000010080000500640000120020200392003999733999780216200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
802042003915000010625801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
80204200391500004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa8a9accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000402580010108000010800005064000012002002003920039999631001980010208000020160000200392003911800211091010800001000050200116112003680000102004020040200402004020040
8002420039150001072580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000050200116112003680000102004020040200402004020040
8002420039150001052580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000050200116112003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000050200116112003680000102004020040200402004020040
8002420039150003142580010108000010800005064000012002032003920039999631001980010208000020160000200392003911800211091010800001040650200116112003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000050200116112003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000350200116112003680000102004020040200402004020087
800242003915000612580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000050200116112003680000102004020040200402004020040
80024200391500078925800101080000108000050640000120020020039200399996310019800102080000201600002003920039118002110910108000010560050200116112003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000050200116112003680000102004020040200402004020040