Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTX (vector, 4S)

Test 1: uops

Code:

  frintx v0.4s, 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)03081e3f4e51inst 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372301261254725100010001000398160130183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
100430372201261254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300727254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000373116112664100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000116330373037111001100001073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724173289510001000100030373037111001100000073116112629100030383038303830383038
100430372202461254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintx v0.4s, 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)0308091e1f3a3f4e51inst 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)9fa6a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500900010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001037101161129633100001003003830038300383003830038
102043003722500510010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500240010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001037101161129633100001003003830038300383003830038
102043003722500540014729547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001007101161129633100001003003830038300383003830038
102043003722500420010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000037101271129633100001003003830038300383003830038
102043003722500240075129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001007101161129633100001003003830038300383003830038
102043003722500120010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001007101161129633100001003003830038300383003830038
102043003722400270010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001028207392251129633100001003003830038300383003830038
102043003722511930132171429547251010010010000100100005004277160130018300883003728264728763102612021000020410164300843008511102011009910010010000100101228337101161129633100001003003830038300383003830038
10204300372250000016629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001037101161129633100001003003830038300383003830038

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)696b6d6edispatch 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224000030612954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722400000010402954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000030612954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716030018030037300372828832876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000003462954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500001950612954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716030018330037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372240000270612954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintx v0.4s, v8.4s
  frintx v1.4s, v8.4s
  frintx v2.4s, v8.4s
  frintx v3.4s, v8.4s
  frintx v4.4s, v8.4s
  frintx v5.4s, v8.4s
  frintx v6.4s, v8.4s
  frintx v7.4s, 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)030b181e3f51inst 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)9fa0a1a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005015000277225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010002000111511821633200360800001002004020040200402004020040
80204200391500037225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000030111511831634200360800001002004020040200402004020040
802042003915000127225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000130111511831633200360800001002004020040200402004020040
80204200391500037225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000130111511831633200360800001002004020040200402004020040
802042003915000157225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000130111511841634200360800001002004020040200402004020040
802042003915000127225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000130111511841633200360800001002004020040200402004020040
802042003915000127225801081008000810080020500640132120020201392003999776999080120200800322008003220039200391180201100991001008000010000000111511841643200360800001002004020040200402004020040
802042003915000127225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000130111511841634200360800001002004020040200402004020040
802042003915000127225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000130111511831645200360800001002004020040200402004020040
802042003915000123025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000130111511841643200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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
800242003915048241258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005024201615122003680000102004020040200402004020040
80024200391500241258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005024151615162003680000102004020040200402004020040
80024200391500241258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005024171614162003680000102004020040200402004020040
80024200391566241258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005024161616162003680000102004020040200402004020040
80024200391503241258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005024131610172003680000102004020040200402004020040
800242003915002412580010108000010800005064000012002020039200391001431001980010208000020800002003920039118002110910108000010005024131616182003680000102004020040200992004020040
8002420039150332412580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050248169172003680000102004020040200402004020040
80024200391500241258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005024141616142003680000102004020040200402004020040
80024200391500241258001010800001080000566400001200202003920039999631001980010208000020800002003920039118002110910108000010005024161616162003680000102004020040200402004020040
80024200391500241258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005024151614162003680000102004020040200402004020040