Apple M1 Microarchitecture Research by Dougall Johnson

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

SQXTUN (2D)

Test 1: uops

Code:

  sqxtun 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)03071e3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100040073116112629100030383038303830383038
100430372200612547251000100010003981601301830373037241332895100010001000303730371110011000180073116112629100030383038303830383038
100430372300612547251000100010003981601301830373037241432895100010001000303730371110011000230073116112629100030383038303830383038
1004303722015612547251000100010003981601301830373037241432895100010001000303730371110011000340073116112629100030383038303830383038
100430372200105254725100010001000398160030183037303724143289510001000100030373037111001100000073116122629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100050073116122629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112626100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037211001100010073116112629100030383038303830383086
10043037220082254725100010001000398160130183037303724143289510001000100030373037111001100010073116212629100030383038303830383038
100430372209163254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqxtun 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)03080b18191e3f4e51inst 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)9fa0a8acbranch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000100710011611296330100001003003830038300383003830038
10204300372250000961295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
10204300372250000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
102043003722500000251295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
10204300372250000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000781011611296330100001003003830038300383003830038
102043003722500000251295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
102043003722500000251295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
102043003722500000346295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038
102043003722500000631295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296331100001003003830038300383003830038
10204300372250000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037224000000441295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722400000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250001560061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000082295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162329629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqxtun v0.2s, v8.2d
  sqxtun v1.2s, v8.2d
  sqxtun v2.2s, v8.2d
  sqxtun v3.2s, v8.2d
  sqxtun v4.2s, v8.2d
  sqxtun v5.2s, v8.2d
  sqxtun v6.2s, v8.2d
  sqxtun 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)03070a0b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150110000013725801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511811611200360800001002004020040200402004020040
802042003915011000003025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111515321611200360800001002004020040200402004020040
8020420039150110003303025801081008000810080122500641008120020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511821611200360800001002004020040200402004020040
8020420039150110001203025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511811611200360800001002004020040200402004020040
802042003915011000003025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511811611200360800001002004020040200402004020040
8020420039150110002403025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511811611200360800001002004020040200402004020040
802042003915011000003025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111517011611200360800001002004020040200402004020040
802042003915011000003025802121008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511821611200360800001002004020040200402004020040
802042003915011000003025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511811611200360800001002004020040200402004020040
802042003915011000003025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000000000111511811611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391501404680010108000010801075064000012002020039200399996310019800102080000208000020041200921180021109101080000101050202216962003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050207161092003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201016962003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020816962003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502011161272003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050208168102003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001026502010169102003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201016862003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020816882003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020516682003680000102004020040200402004020040