Apple M1 Microarchitecture Research by Dougall Johnson

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

URSHR (vector, 4H)

Test 1: uops

Code:

  urshr v0.4h, v0.4h, #3
  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
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116212629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372336125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723026525472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000373116212629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  urshr v0.4h, v0.4h, #3
  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)03191e3f4e51inst 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
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000281871021622296330100001003003830038300383003830038
1020430037225306129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000371021622296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000187295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000000006402163229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716013001830037300372828602628767100102010000201000030037300371110021109101010000100000000006403162229629010000103003830038300383003830038
10024300372250000000124295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000000006402163229629010000103008430038300383008530038
1002430037225000000061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000003006402162229629010000103003830038300383003830038
1002430037225000200061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000000006402162329667010000103003830086300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000000006402162329629010000103003830038300383003830038
10024300372250000000166295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000003006402163229629010000103003830038300383003830038
10024300372250000000195295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000103006402163229629010000103003830038300383003830038
100243003722500000001032954725100101010000101000050427716013001830084300842828603288041046220100002010161300853021531100211091010100001062301219450207675725629880410000103037130363304073037130367
100243036522710779306161457829484176100281310056111105060428679813027330367304152831203128884110642210228241113830370303228110021109101010000100000000006402165329883410000103036630419303723037030369

Test 3: throughput

Count: 8

Code:

  urshr v0.4h, v8.4h, #3
  urshr v1.4h, v8.4h, #3
  urshr v2.4h, v8.4h, #3
  urshr v3.4h, v8.4h, #3
  urshr v4.4h, v8.4h, #3
  urshr v5.4h, v8.4h, #3
  urshr v6.4h, v8.4h, #3
  urshr v7.4h, v8.4h, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030b191e3f51inst 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)9fa0a1a6a8acc2c5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150000302580108100800081008002050064013202002002003920039997769990801202008014320080032200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002002003920039997769990801202008003220080032200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002002003920039997769990801202008003220080032200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002032003920039997769990801202008003220080032200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
8020420039150000742580108100800081008002050064013202002002003920039997769990801202008003220080032200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002002003920039997769990804352008003220080032200392003911802011009910010080000100000000111511816220036800001002004020040200402004020040
802042003915000555302580108100800081008002050064013202002002003920039997769990801202008003220080032200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
8020420039150000302580108100800081008012050064013202002002003920039997769990801202008003220080032200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002002003920039997769990801202008003220080032200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002002003920039997769990801202008003220080032200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020800002003920039118002110910108000010502020165112003680000102004020040200402004020040
80024200391500402580010108000010800005064000020020020039200399996310019800102080000208000020039200391180021109101080000105020916962003680000102004020040200402004020040
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020800002003920039118002110910108000010502011161042003680000102004020040200402004020040
80024200391500402580010108000010800005064000020020020039200399996310019800102080000208000020039200391180021109101080000105020101611102003680000102004020040200402004020040
800242003915001902580010108000010800005064000020020020039200399996310019800102080000208000020039200391180021109101080000105020516842003680000102011520142201002004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002080000200392003911800211091010800001050201116682003680000102004020040200402004020040
80024200391500502580010108000010800005064000020020020039200399996310019800102080000208000020039200391180021109101080000105020816882003680000102004020040200402004020040
80024200391500402580010108000010800005064000020020020039200399996310019800102080000208000020039200391180021109101080000105020716862003680000102004020040200402004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002080000200392003911800211091010800001050208167102003680000102004020040200402004020040
8002420039150340258001010800001080000506400002002002003920039999631001980010208000020800002003920039118002110910108000010502011167102003680000102004020040200402004020040