Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT64X (vector, 2D)

Test 1: uops

Code:

  frint64x v0.2d, 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)0308090b1e3f4e51inst 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)a0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303725000089254725100010001150398160030183037303724173289510001161100030373085211001100011000073116112629100030853038303830383085
10043073321100686254744100010081000399512030543084303724157292511501168116131333120311001100000203320111145112727100031363086308530853085
1004308425000061254743100010001150398160030543133308424141029191150116811213085313221100110000200364073116112629100030383038303830383038
100430372400006125472510001000100039816013018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
100430372300006125472510001000100039816003018303730372414328951000100010003037303711100110000001073116112629100030383038303830383038
1004303724000061254725100010001000398160030183037303724143289510001000100030373037111001100000003073116112629100030383038303830383038
100430372400008225472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
100430372400006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
100430372400006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
100430372300006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint64x v0.2d, 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)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723200003006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296330100001003003830038300383003830038
102043003723200000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000300071011611296330100001003003830038300383003830038
102043003724200000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296330100001003003830038300383003830038
1020430037233000018006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296520100001003003830038300383003830038
1020430037233000000010829547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373013421102011009910010010000100242004306000073213311297022100001003008530085300863013330133
1020430132233102226417606129538441012211410008104101506444279864130054301313013228269132876310428206103312021033330132301323110201100991001001000010024210219450000850191312993028100001003041930407304203040830371
1020430367235008792461606082294542121024614910088149110507374290527130378303683050228300482892511802218116642361181330419305149110201100991001001000010022200032695000942197213002931100001003051830562303253056130597
102043051923711111013449940712829502233102431521008815311650763429203213041430563305632831057289341103223611821220116523056730565121102011009910010010000100000000278930009443127122995837100001003046830326304723045430508

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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224210892954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010700640216222962910000103003830038300383003830038
100243003722512612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722515612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722521612954725100101010000101015050427716003001830037300372828632884210010201000020100003003730037111002110910101000010000640249222962910000103003830038300383003830038
100243003722533612954725100101010008101000050427716003001830037300372828632876710010201032920100003003730037111002110910101000010059640216222962910000103003830038300383003830038
100243003722527612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640217222962910000103003830038300383003830038
1002430037225363412954725100101010000101000050427716003001830037300372828662876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225181032954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010010640216222962910000103003830038300383003830038
10024300372253612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint64x v0.2d, v8.2d
  frint64x v1.2d, v8.2d
  frint64x v2.2d, v8.2d
  frint64x v3.2d, v8.2d
  frint64x v4.2d, v8.2d
  frint64x v5.2d, v8.2d
  frint64x v6.2d, v8.2d
  frint64x v7.2d, 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)03191e3f51inst 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 int load (95)inst integer (97)inst neon or fp (9a)9fa1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591550051258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910001008000010000311151180160020036800001002004020040200402004020040
802042003915600642680116100800161008002850064019612002020039200399977699908012020080032200800322003920039118020110099100010080000100016011151181160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910001008000010004311151180160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910001008000010000011151180160020036800001002004020040200402004020040
80204200391560030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910001008000010000011151180160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910001008000010000011151180160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910001008000010001011151180160020036800001002004020040200402004020040
80204200391550072258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910001008000010000011151180160020036800001002004020040200402004020040
8020420039166030630258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910001008000010000011151180160020036800001002004020040200402004020040
80204200391560030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910001008000010000011151180160020036800001002004020040200402004020040

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)6061696b6d6edispatch 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)9fa1a8acb5c2cfd0d2d5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501550402580010108000010800005064000000200200200392003999963100198001020800002080000200392003911800211091010800001000000502000161608132003680000102004020040200402004020040
8002420039155023025800101080000108000050640812002002002003920039999631001980010208000020800002003920039118002110910108000010015000502000131601382003680000102004020040200402004020040
800242003915604025800101080000108000050640000002002002003920039999631001980010208000020800002003920039118002110910108000010010005020001316012122003680000102004020040200402004020040
8002420039155040258001010800001080000506400000020020020039200399996310019800102080000208000020039200391180021109101080000100330005020001016012112003680000102004020040200402004020040
800242003915504025800101080000108000050640000002002002003920039999631001980010208000020800002003920039118002110910108000010000005020008160862003680000102004020040200402004020040
800242003916104025800101080000108000050640000002002002003920039999631001980010208000020800002003920039118002110910108000010000005020008160792003680000102004020040200402004020040
80024200391550402580010108000010800005064000000200200200392003999963100198001020800002080000200392003911800211091010800001000000502000101608112003680000102004020040200402004020040
800242003915504025800101080000108000050640000002002002003920039999631001980010208000020800002003920039118002110910108000010000005020007160572003680000102004020040200402004020040
80024200391550402580010108000010800005064000000200200200392003999963100198001020800002080000200392003911800211091010800001000000502000111608112003680000102004020040200402004020040
8002420039155040258001010800001080000506400000020020020039200399996310019800102080000208000020039200391180021109101080000100200050200011160692003680000102004020040200402004020040