Apple M1 Microarchitecture Research by Dougall Johnson

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

UQADD (vector, 8H)

Test 1: uops

Code:

  uqadd v0.8h, v0.8h, v1.8h
  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)033f4e51inst 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
100430372210325482510001000100039831313018303730372415328951000100020003037303711100110000073216112630100030383038303830383038
10043037238425482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831313018303730372415328951000100020003037303711100110000073116112659100030383038303830383038
10043037236125482510001000100039831313018303730372415328951000100020003037303711100110000073116112689100030383038303830383038
10043037226125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037226125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqadd v0.8h, v0.8h, v1.8h
  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)0307080b18191e1f3f4e51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000002707712954825101001001000010010000500427731313009030037300372826532874410267200100002002000030037300371110201100991001001000010000243371011611296340100001003003830038300383003830038
10204300372250000000274295482510100125100001001000050042773130300183003730037282653287441010020010000200200003003730037111020110099100100100001000000071021711296340100001003003830038300383003830038
102043003722500000120103295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011621296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874410100200100002002000030037300371110201100991001001000010000003710116112963425100001003003830038300383003830038
1020430037225000000061295482510100125100001001000050042773130300183003730037282653287441010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037224000000061295482510100100100001001044750042773130300183003730037282653287441010020010000200203483003730037111020110099100100100001002000071011611296340100001003003830038300383003830038
1020430037225000000061295482510125125100001251000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282653287441010020010000200200003003730037111020110099100100100001000000078311611296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282653287441012520010000200200003003730037111020110099100100100001000000071011611297040100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282653287441010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e1f3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037224000840295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630110000103003830038300383003830038
1002430037224000103295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010200006402162229630010000103003830038300383003830038
10024300372250543061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000306402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373018028287328767100102010000202000030037300371110021109101010000100001126402162229630010000103003830038300383003830038
1002430037225000346295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630210000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqadd v0.8h, v1.8h, 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722521661295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372256061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372253361295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
1020430037225661295482510100100100001001000050042773130300183003730037282653287451010020010180200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372254861295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
1020430037224961295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102161229634100001003003830038300383003830038
10204300372253961295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372243361295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
1020430037225661295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
1020430037225961295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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
100243003722504261295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225015631295482510010101000010100005042773130300183008330037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225023761295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722503061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001003640216222963010000103003830038300383003830038
10024300372240301000295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225032761295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225032761295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225030661295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225033690295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722505761295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqadd v0.8h, v8.8h, v9.8h
  uqadd v1.8h, v8.8h, v9.8h
  uqadd v2.8h, v8.8h, v9.8h
  uqadd v3.8h, v8.8h, v9.8h
  uqadd v4.8h, v8.8h, v9.8h
  uqadd v5.8h, v8.8h, v9.8h
  uqadd v6.8h, v8.8h, v9.8h
  uqadd v7.8h, v8.8h, v9.8h
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03081e3f51inst 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
80204200601500604125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102161120036800001002004020040200402004020040
80204200391500844125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915003642125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102161120036800001002004020040200402004020040
80204200391500124125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
80204200391500023125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051271161120036800001002004020040200402004020040
8020420039150094125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304091e3f51inst 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)9fa8c2cdcfitlb miss (d4)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915011089258001010800001080000506400001200202003920049999631001980010208000020160000200392003911800211091010800001001050211171617172003680000102004020040200402004020040
800242003915011089258001010800001080000506400001200202003920050999631001980010208000020160000200392003911800211091010800001000050211181617162003680000102004020040200402004020040
80024200391501108925800101080000108000050640000020020200392005099963100198001020800002016000020039200391180021109101080000100005021191618112003680000102004020040200402004020040
800242003915011150754258001010800001080000506400001200202003920050999631001980010208000020160000200392003911800211091010800001000050200181618172003680000102004020040200402004020040
80024200391500029440258001010800001080000506400000200202003920050999631001980010208000020160000200392003911800211091010800001000050200171611182003680000102004020040200402004020040
8002420039150002440258001010800001080000506400001200202003920050999631001980010208000020160000200392003911800211091010800001000050200111618112003680000102004020040200402004020040
800242003915000040258001010800981080000506400001200202003920066999631001980010208000020160000200392003911800211091010800001000050200181616182003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920050999631001980010208000020160000200392003911800211091010800001000150200171617182003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920050999631001980010208000020160000200392003911800211091010800001000050200181616172003680000102004020040200402004020040
8002520039150001840258001010800001080000506400001200202003920050999631001980010208000020160000200392003911800211091010800001000050200111618112003680000102004020040200402004020040