Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTNU (vector, 8H)

Test 1: uops

Code:

  fcvtnu v0.8h, v0.8h
  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)03191e3f4e51inst 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
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303723008225472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230216125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303723036125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtnu v0.8h, v0.8h
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723308929547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100037101161129633100001003003830229300383003830038
1020430037233094329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723206129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037233126129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037232017329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037233053629547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100337101161129633100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723336129547251010010010000100100005004277160030018300373003728264328745102522001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723206129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

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)6061696d6edispatch 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723306129547251001010100001010000504277160103001830037300372828632876710010201000020100003003730037111002110910101000010006400216222962910000103003830038300383003830038
100243003723306129547251001010100001010000504277160003001830037300372828632876710010201000020100003003730037111002110910101000010006400216222962910000103003830038300383003830038
100243003723306129547251001010100001010000504277160003001830037300372828632876710010201000020100003003730037111002110910101000010006680216222962910000103003830038300383003830038
100243003723306129547251001010100001010000504277160103001830037300372828632876710010201000020100003003730037111002110910101000010006400216222962910000103003830038300383003830038
100243003722506629547251001010100001010000504277160103001830037300372828632876710010201000020100003003730037111002110910101000010006400216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160103001830037300372828632876710010201000020100003003730037111002110910101000010006400216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160103001830037300372828632876710010201000020100003003730037111002110910101000010006400216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160103001830037300372828632876710010201000020100003003730037111002110910101000010006400216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160103001830037300372828632876710010201000020100003003730037111002110910101000010006400216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160103001830037300372828632876710010201000020100003003730037111002110910101000010006400216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtnu v0.8h, v8.8h
  fcvtnu v1.8h, v8.8h
  fcvtnu v2.8h, v8.8h
  fcvtnu v3.8h, v8.8h
  fcvtnu v4.8h, v8.8h
  fcvtnu v5.8h, v8.8h
  fcvtnu v6.8h, v8.8h
  fcvtnu v7.8h, v8.8h
  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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039155000932580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550002352580108100800081008002050064013202002020039201009977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000311151180160020036800001002004020040200402004020040
8020420039160000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039156000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
80204200391560306952580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180166020036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 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)5e696d6edispatch 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401550001025258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020416112003680000102004020040200402004020040
80024200391550120298258001010800001080000506400000200202009920039999631001980010208000020800002003920039118002110910108000010000105038139112003680000102010120040200402004020040
8002420039155000105258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
8002420039155000624258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000035020116212003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020216222003680000102004020040200402004020040
80024200391550132881569428010910802901080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010022005020116112003680000102004020040200402004020040
8002420039155000263258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
8002420039156000124258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000105020116112003680000102004020040200402004020040
800242003915500084258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020216122003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020116222003680000102004020040200402004020040