Apple Microarchitecture Research by Dougall Johnson

M1/A14 P-core (Firestorm): Overview | Base Instructions | SIMD and FP Instructions
M1/A14 E-core (Icestorm):  Overview | Base Instructions | SIMD and FP Instructions

SQSHRUN (H)

Test 1: uops

Code:

  sqshrun b0, h0, #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 uop (01)cycle (02)031e1f3f4e51schedule uop (52)schedule simd uop (54)dispatch simd uop (57)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map simd uop (7e)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst simd alu (9a)l1d tlb access (a0)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)f5f6f7f8fd
100430372300612547251000100010003981601301830373037241432895100010001000303730371110011000014073116112629100030383038303830383038
10043037220061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037220061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372200112254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372212061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372330612547251000100010003981601301830373037241432895100010001000303730371110011000019373116112629100030383038303830383038
10043037220061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037220061254725100010001000398160130183037303724143289510001000100030373037111001100000373116112701100030383038303830383038

Test 2: Latency 1->2

Code:

  sqshrun b0, h0, #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 uop (01)cycle (02)03mmu table walk instruction (07)mmu table walk data (08)1e3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)6061696b6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fld unit uop (a6)l1d cache writeback (a8)a9acc2cfd0d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
102043003722500061295472510100100100001001000050042771601530018030037300372826432874510100200100002041000030037300371110201100991001001000010005000710521622296330100001003003830038300383003830038
102043003722400061295472510100100100001001000050042798641530018030037300372826432874510100200100002001000030037300371110201100991001001000010000062710521622296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716015300180300373003728264328745101002001000020010000300373003711102011009910010010000100018000710521622296330100001003003830038300383003830038
1020430037224001261295472510100100100001001000050042771601530018030037300372826432874510100200100002001000030037300371110201100991001001000010000030710521622296330100001003003830038300383003830038
1020430037225000124295472510100100100001001000050042771601530018030037300372826432874510100200100002001000030037300371110201100991001001000010030000710521622296330100001003003830038300383003830038
1020430037225000726295472510100100100001001000050042798731530018030037300372826432874510100200100002001000030037300371110201100991001001000010000000710521622296330100001003003830038300383003830038
102043003722400061295472510100100100001001000050042771601530018030037300372826432874510100200100002001000030037300371110201100991001001000010000030710521622296330100001003003830038300383003830038
1020430037225001261295472510100100100001001000050042771601530018030037300372826432874510100200100002001000030037300371110201100991001001000010000030710521622296330100001003003830132300873003830038
1020430037225000612954725101001001000010010000500427716015300180300373003728264328745101002001000020010000300373003711102011009910010010000100030030710521622296330100001003003830038300383003830038
102043003722400061295472510100100100001001000050042771601530018030037300372826432874510100200100002001000030037300371110201100991001001000010000030710521622296330100001003013230038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire uop (01)cycle (02)03191e1f3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)acc2cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
10024300372250006129547251001010100001010000604277160130018300373003728286328767100102010000201000030037300371110021109101010000100039006403162229629010000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010008006402162229629010000103017930038300383003830038
1002430037224000612954762100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010002006402162229629010000103003830038300383003830038
100243003722500010329547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100007506402162229629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100007506402162229629010000103003830038300383003830038
10024300372250390612954725100101010024101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000606402162229629010000103003830038300383003830038
10024300372250001892954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000606403162229629010000103003830038300383003830038
10024300372250006129511251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006906402162229629010000103003830038300383003830038
10024300372250120612954725100101010000101000050427716013012630037300372828632876710010201000020100003003730037111002110910101000010004306402162229629010000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000017706402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqshrun b0, h8, #3
  sqshrun b1, h8, #3
  sqshrun b2, h8, #3
  sqshrun b3, h8, #3
  sqshrun b4, h8, #3
  sqshrun b5, h8, #3
  sqshrun b6, h8, #3
  sqshrun b7, h8, #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 uop (01)cycle (02)03191e3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb access (a0)l1d cache writeback (a8)acbranch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)fetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
802042004915000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000161115118116020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000101115118016020036800001002004020040200402004020040
80204200391500024125801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000121115118016020036800001002004020040200402004020040
802042003915100302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000101115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000101115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000061115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001002131115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire uop (01)cycle (02)031e3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d cache writeback (a8)accfd0d5map dispatch bubble (d6)dbddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
800242004015004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001010502004160242003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502002160252003680000102004020040200402004020040
800242003915004025801091080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001003502002160242003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502004160442003680000102004020040200402004020040
8002420039150013525800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502002160242003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502002160242003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001013504534160432003680000102004020040200402004020040
800242003915004025800101080000108030450640000120020200392003999963100198001020800002080000200392003911800211091010800001010502004160422003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001010502002160242003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502004160422003680000102004020040200402004020040