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, 4S)

Test 1: uops

Code:

  uaddlv d0, v0.4s
  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
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723019425472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110009073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000200030373037111001100014073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000200030373037111001100003973116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uaddlv d0, v0.4s
  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)03090b191e3f4e51inst 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)9fa6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430084225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000302818007102162229633100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000003007102162229633100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000003007102162229633100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000003007102162229633100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183013230037282643287451010020010000200200003003730037111020110099100100100001000009007102162229633100001003003830038300383003830038
1020430037224000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000003007102162229633100001003013230038300383003830038
1020430037225000061295472510100100100001001000050042771601300543003730037282643287451010020010000200200003003730037111020110099100100100001000003007102162229633100001003003830038300383003830038
10204300372250000189295472510100100100001001000050042771601300183003730037282643287451010020010000208200003003730037111020110099100100100001005103007102162229633100001003003830038300383003830038
10204300372250000210295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000003007102162229633100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000006007102162229633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010200640216222962910000103003830038300383003830079
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010400640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100012640216222962910000103003830038300383008530038
100243003722506129547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000103600640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010003640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010003640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010003640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830085300383003830038
10024300372240822954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010100640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uaddlv d0, v8.4s
  uaddlv d1, v8.4s
  uaddlv d2, v8.4s
  uaddlv d3, v8.4s
  uaddlv d4, v8.4s
  uaddlv d5, v8.4s
  uaddlv d6, v8.4s
  uaddlv d7, v8.4s
  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)03191e1f3f51inst 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)9fa8a9acc2c5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001004000111511801620036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010056030111511801620036800001002009020040200402004020040
8020420039150000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001003060111511801620036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000000111511801620036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000060111511801620036800001002004020040200402004020040
80204200391501603025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010053000111511801620036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000030111511801620036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000000111511801620036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000000111511801620036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001003000111511801620036800001002004020040200402004020040

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)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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150040258001010800001080000506400000200202003920039999603100198001020800002016000020039200391180021109101080000100000502031632200360080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999603100198001020800002016000020039200391180021109101080000100000502031623200360080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999603100198001020800002016000020039200391180021109101080000100010502041633200360080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999603100198001020800002016000020039200391180021109101080000100000502031634200360080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999603100198001020800002016000020039200391180021109101080000100000502021632200360080000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996031001980010208000020160000200392003911800211091010800001000469502031632200360080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999673100198001020800002016000020039200391180021109101080000100020502031633200360080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999603100198001020800002016000020039200391180021109101080000100000502031632200360080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999603100198001020800002016000020039200391180021109101080000100000502021633200360080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999603100198001020800002016000020039200391180021109101080000100000502031652200360080000102004020040200402004020040