Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTN (vector, 2D)

Test 1: uops

Code:

  frintn 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)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372301032547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372301032547251000100010003981603018303730372414328951000100010003037303711100110001277073116112629100030383038303830383038
100430372401032547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintn 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)0318191e3f4e51inst 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)9fa6a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723200045029547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723200060829547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723300017429547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100010007101161129633100001003003830038300383003830038
102043003723300016629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723300044829547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723210015629547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723200051929547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723300045929547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723200010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723200016729547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038

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)9fa1a8acbranch mispredict (cb)cficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037232061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006400216222962910000103003830038300383003830038
1002430037233061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006400216222962910000103003830038300383003830038
1002430037233061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006400216222962910000103003830038300383003830038
1002430037233061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006610216222962910000103003830038300383003830038
1002430037233061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006400216222969910000103003830038300383003830038
1002430037233061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001001306400216222962910000103003830038300383003830038
1002430037233061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000316400216222962910000103003830038300383003830038
1002430037233061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006400232232962910000103018130038300383008830038
10024300372331261295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001002006400216222962910000103003830038300383003830038
1002430037232061295472510010101000010102965042771600300543003730037282863287671001020100002010000300373013211100211091010100001003306400253222962910000103003830133300383003830179

Test 3: throughput

Count: 8

Code:

  frintn v0.2d, v8.2d
  frintn v1.2d, v8.2d
  frintn v2.2d, v8.2d
  frintn v3.2d, v8.2d
  frintn v4.2d, v8.2d
  frintn v5.2d, v8.2d
  frintn v6.2d, v8.2d
  frintn 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)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)9facc5c8branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061155273025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000101151181620036800001002004020040200402004020040
80204200391551850525801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000101151181620036800001002004020040200402004020040
80204200391555043025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000101151181620036800001002004020040200402004020040
802042003915603025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000101151181620036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000101151181620036800001002004020040200402004020040
802042003915603025801881008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000101151181620036800001002004020040200402004020040
8020420039155243025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000101151181620036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000101151181620036800001002004020040200402004020040
8020420039156183025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000101151181620036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000101151181620036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915500003630402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000030502011611200360080000102004020040200402004020040
80024200391550000540402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502011611200360080000102004020040200402004020040
80024200391550000180402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502011611200360080000102004020040200402004020040
80024200391550000510402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502011611200360080000102004020040200402004020040
80024200391560000480402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100001030502011611200360080000102004020040200402004020040
80024200391550000270402580010108000010800005064000012002020039200399996310072800102080000208000020039200391180021109101080000100000000502011611200360080000102004020040200402004020040
800242003915500003305152580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502011611200360080000102004020040200402004020040
80024200391550000900402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502011611200360080000102004020040200402004020040
8002420039155000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502011611200360080000102004020040200402004020040
8002420039156000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502011611200360080000102004020040200402004020040