Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDLV (vector, 8B)

Test 1: uops

Code:

  uaddlv h0, v0.8b
  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
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372396125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303721100110000073116112629100030383038303830383038
1004303723156125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110000373116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037220354254725100010001000398160130183037303724143289510001000200030373037111001100001273116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uaddlv h0, v0.8b
  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)03080b191e1f3a3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000263295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722400000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001002000071011611296330100001003003830038300383003830038
10204300372240000003837295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225000000103295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000020071011613296330100001003003830038300383003830038
1020430037224000000275295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011612296330100001003003830038300383003830038
102043003722500002640822954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010000000710116112963325100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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
100243003722400000000128295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001040000006402162229629010000103003830038300383003830038
100243003722500000600103295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722400000000166295472510010101000010101505042771601300183003730037282863287861016120100002020000300373003711100211091010100001000000006402162329665010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722400000000612954725100101010000101000050427716013001830037300372828619287671001020100002020000300373003711100211091010100001000000006402162329629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001002000006402162229629010000103003830038300383003830038
100243003722500000000103295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001040000006402162329629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uaddlv h0, v8.8b
  uaddlv h1, v8.8b
  uaddlv h2, v8.8b
  uaddlv h3, v8.8b
  uaddlv h4, v8.8b
  uaddlv h5, v8.8b
  uaddlv h6, v8.8b
  uaddlv h7, v8.8b
  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)9fa0a8a9acc2c5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150072258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000000111511816020036800001002004020040200402004020040
80204200391500220258010810080008100801205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010001200111511816020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000000111511816020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000000111511816020036800001002004020040200402004020040
80204200391500139258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000000111511816020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000000111511816020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000000111511816020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000000111511816020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000000111511816020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000000111511816020036800001002004020040200402004020040

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)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)9fa8acc2cfd2d5d6dadbddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500862580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502011416406420036080000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502005164041120036080000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502001316006320036080000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502001216008520036080000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200516007620036080000102004020040200402004020040
8002420039150082258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200616009520036080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050200416103520036080000102004020040200402004020040
80024200391500128258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200916005420036080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020061600121020036080000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050200616005420036080000102004020040200402004020040