Apple M1 Microarchitecture Research by Dougall Johnson

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

UQXTN (2D)

Test 1: uops

Code:

  uqxtn v0.2s, v0.2d
  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)0318191e1f3a3f4e51inst 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)a8cfd0d5d6ddinst fetch restart (de)dfe0? fp/simd (ee)f5f6f7f8fd
1004303723001500272254725100010001000398160130183037303724143289510001000100030373037111001100007902161132629100030383038303830383038
10043037230090372254725100010001000398160030183037303724143289510001000100030373037111001100007941161132629100030383038303830383038
10043037230000372254725100010001000398160130183037303724143289510001000100030373037111001100007941161132629100030383038303830383038
1004303722001803167254725100010001000398160030183037303724143289510001000100030373037111001100007941161132629100030383038303830383038
10043037220000372254725100010001000398160030183037303724143289510001000100030373037111001100007941161132629100030383038303830383038
10043037220000372254725100010001000398160030183037303724143289510001000100030373037111001100007941161132629100030383038303830383038
10043037220090372254725100010001000398160030183037303724143289510001000100030373037111001100007941161132629100030383038303830383038
10043037230000372254725100010001000398160130183037303724143289510001000100030373037111001100007941161132629100030383038303830383038
100430372300120372254725100010001000398160030183037303724143289510001000100030373037111001100007941161132629100030383038303830383038
10043037220000372254725100010001000398160030183037303724143289510001000100030373037111001100007941161132629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqxtn v0.2s, 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)03181e1f3a3f4e51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037259030082129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003725900006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003724100006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100200071011611296330100001003003830038300383003830038
102043003724200006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003724100006129547251010010010000100100005004277160030018300373003728264328747101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037232000049129547251010010010000100100005004277160130018300373003728264328745104182001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102053003723300006129547251010010010000100100005004277160030018300373003728264328745101002041000020010000300373003711102011009910010010000100000071011621296337100001003003830038300383003830038
102043003723300006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722900006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722900006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa0a1a6a7a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295472510010101000010100005042771600230018300373003728286328767100102010000201000030037300371110021109101010000100000000064003162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000000064002162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000000064022162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000000064002162229629010000103003830038300383003830038
100243003722400000061295472510010101000010100005042771601030018300373003728286328767100102010000201000030037300371110021109101010000100000006064002162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600030018300373003728286328767100102010000201000030037300371110021109101010000100000000064002162229629010000103003830038300383003830038
1002430037225010000726295472510010101000010100005042771600030018300373008528286328767100102010000201000030037300371110021109101010000100000000064002162229629010000103003830038300383003830038
1002430037225000000346295472510010101000010100005042771601030018300373003728286328767100102010000201000030037300371110021109101010000100000000064002162229629010000103003830038300383003830038
1002430037224000000726295472510010101000010100005042771601030018300373003728286328767100102010000201000030037300371110021109101010000100000000064002162229629010000103003830038300383003830038
10024300372250000005362954725100101010000101000050427716000300183003730037282861628786100102010000201000030037300371110021109101010000100000000064002162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uqxtn v0.2s, v8.2d
  uqxtn v1.2s, v8.2d
  uqxtn v2.2s, v8.2d
  uqxtn v3.2s, v8.2d
  uqxtn v4.2s, v8.2d
  uqxtn v5.2s, v8.2d
  uqxtn v6.2s, v8.2d
  uqxtn v7.2s, v8.2d
  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)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)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)cdcfd6dde0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915001562580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160200360800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160200360800001002004020040200402004020040
802042003915001142580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160200360800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160200360800001002004020090201462004020040
802042003915009382580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160200360800001002004020040200402004020040
80204200391500932580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160200360800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160200360800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160200360800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118161200360800001002004020040201492004020040
80204200391500302580108100800081008002050064019602002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304091e3a3f51inst 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)9fa8accfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150110016625800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502100011816000917200360080000102004020040200402004020040
800242003915011001422580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050210001181600011182003621780000102004020040200402004020040
800242003915011001352580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050210001171600011182003620080000102004020040200402004020040
80024200391501100115258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010035021031117161001920200360080000102004020040200402004020040
800242003915011011152580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050210311181600018182003641080000102004020040200402004020040
800242003915011001162580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050210001191600010182003620080000102004020040200402004020040
80024200391501100110258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005021000191600018102003621080000102004020040200402004020040
800242003915011301152580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050210001111600017142003620080000102004020040200402004020040
800242003915011001162580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050210001181600018172003641080000102004020040200402004020040
800242003915011002662580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050210001181600017182003621080000102004020040200402004020040