Apple M1 Microarchitecture Research by Dougall Johnson

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

UQRSHRN (4S)

Test 1: uops

Code:

  uqrshrn v0.4h, v0.4s, #3
  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)0318191e1f3f4e51inst 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)a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230000612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372300360612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037230000612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037230000612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037220000612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372300240612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037230000612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037230000612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037220000612547251000100010003981601301830373037241432895100010001000303730371110011000000973116112629100030383038303830383038
100430372200001562547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqrshrn v0.4h, v0.4s, #3
  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)0309191e1f3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006306129547251010010010000100100005004277160030018300373003728264022287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716013001830037300372826403287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
10204300372240000612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
10204300372250090612954725101001001000010010000500427716013001830037300372826403287451010020010000200100003003730037211020110099100100100001000007101162229633100001003003830038300383003830038
102043003722500480612954725101001001000010010000500427716013001830037300372826703287451010020010000200101663003730037111020110099100100100001000007102162229633100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
10204300372240000612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
102043003722500270612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000001800612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064041622296290010000103003830038300383003830038
10024300372250000027900612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
1002430037225000003000612954725100101010000101000050427716013001830037300852828632876710010201000020100003003730037111002110910101000010000090064021622296290010000103003830038300383003830038
100243003722500000900612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300372250000042900612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300372250000047700612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
100243003722500000420007262954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
100243003722500000331760612954725100101010000101000050427716013001830037300372828632876710010201016120100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300372250000029100612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103036930322301333032330324
100243036822811168936528139792949315610068141003214110507642866241302703036930324283132928880110632211146241097730131303738110021109101010000102212194030078827222298813010000103036830134303593032130366

Test 3: throughput

Count: 8

Code:

  uqrshrn v0.4h, v8.4s, #3
  uqrshrn v1.4h, v8.4s, #3
  uqrshrn v2.4h, v8.4s, #3
  uqrshrn v3.4h, v8.4s, #3
  uqrshrn v4.4h, v8.4s, #3
  uqrshrn v5.4h, v8.4s, #3
  uqrshrn v6.4h, v8.4s, #3
  uqrshrn v7.4h, v8.4s, #3
  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)0318191e1f3f51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420098150003300302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118116020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391560000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000031115118016020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391490000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500030302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3f51inst 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)9fa1a6a7a8a9acc5cdcfd0d5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500000027040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001160112003680000102004020040200402004020040
8002420039150000000040258001010800001080000506400001020020200392003999963100198001020801402080000200392003911800211091010800001000000000502001160112003680000102004020040200402004020040
8002420039150000009040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001160112003680000102004020040200402004020040
80024200391500000000338258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001160112003680000102004020040200402004020040
80024200391500004030040258001010800001080000506400001020020200392003999963100198001020800002080000201112009911800211091010800001000000000502001160112003680000102004020040200402004020040
8002420039150000000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001160112003680000102004020040200402004020040
8002420039150000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001160112003680000102004020040200402004020040
80024200391500000030040258001010800001080000506400001020021200392003999963100198012420800002080000200392003911800211091010800001000000000502001160112003680000102004020040200402004020040
8002420039150000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001160112003680000102004020040200402004020040
80024200391550000045040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502001160112003680000102004020040200402004020040