Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDLV (vector, 4H)

Test 1: uops

Code:

  uaddlv s0, v0.4h
  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)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
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073316112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000200030373037111001100002173116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000200030373037111001100001573116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000200030373037111001100003373116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110002973116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uaddlv s0, v0.4h
  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)9fa6a8a9acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020610168200200003003730037111020110099100100100001002420071021622296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000100071021622296330100001003003830038300383003830038
102043003722545853295474310100100100001001000055142771601300183003730037282643287451025820210000200200003008430085111020110099100100100001000003071021622296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250126295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000103071021622296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)696d6edispatch 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)9fa0a1a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000024429547251001010100001110000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830086
10024300372250000038106129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229701010000103003830038300383003830038
1002430037224000003906129547251001010100001010000504277160300183003730037283013287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000001506129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000046506129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000001806129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000002706129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000180612954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000144006402162229629010000103003830038300383003830038
10024300372250000030606129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000100006402162229629010000103003830038300383003830038
1002430037225000004506129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uaddlv s0, v8.4h
  uaddlv s1, v8.4h
  uaddlv s2, v8.4h
  uaddlv s3, v8.4h
  uaddlv s4, v8.4h
  uaddlv s5, v8.4h
  uaddlv s6, v8.4h
  uaddlv s7, v8.4h
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

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)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)9facc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815005052580108100800081008002050064013220020020039200399977699908012020080032200160064200392003911802011009910010080000100011151181160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020020039200399977699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020020039200399977699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
8020420039150243302580108100800081008002050064013220020020039200399977699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020020039200399977699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
802042003915018302580108100800081008002050064013220020020039200399977699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
802042003915005052580108100800081008002050064013220020020039200399977699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
802042003915002222580108100800081008002050064013220020020039200399977699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
802042003915042302580108100800081008002050064013220020020039200399977699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020020039200399977699908012020080032200160064200392003911802011009910010080000100011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03091e3f51inst 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)696d6edispatch 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
80024200511500040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010005020616742003680000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010005020316552003680000102004020040200402004020040
8002420039150004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001001235020616352003680000102004020040200402004020040
800242003915002140258010910800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010005020316352003680000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010005020616652003680000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010005020516532003680000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010005020516352003680000102004020040200402004020040
8002420039150007052580010108000010800005064000020020200392003910012310019800102080000201600002003920039118002110910108000010005020616352003680000102004020040200402004020040
800242003915011240258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010005020316532003680000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010005020516462003680000102004020040200402004020040