Apple M1 Microarchitecture Research by Dougall Johnson

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

FADD (vector, 8H)

Test 1: uops

Code:

  fadd 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)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
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372396125482510001000100039831330183037303724153289510001000200030373037111001100001273216222630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230822548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  fadd 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)03071e3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372250061295482510111100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500103295482510100103100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001002007102162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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)9fa0a1a6a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500060061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250005250061295482510010101000010100005042773130300183003730037282870328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722400042900943295482510010101000010100005042773131300183003730037282870328767100102010162202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250003900061295482510010101000010100005042773130300183003730037282870328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250003180061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250004860061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500048900816295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500040500194295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250004560061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fadd 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225510612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225240612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225429612954825101001001000010010000500427731303001830037300842826932874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225453612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225399612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225459612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225522612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225441612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225333612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372255250612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372243990612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372255220612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372254140612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372254170612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100640316332963010000103003830038300383003830038
100243003722539306312954825100101010000101000050427731330018300373003728287328767101622010000202000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372254110612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372253870612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372253750612954825100101010000101000050427731330018300373003728287328767100102010000202000030084300371110021109101010000100640316332963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fadd v0.8h, v8.8h, v9.8h
  fadd v1.8h, v8.8h, v9.8h
  fadd v2.8h, v8.8h, v9.8h
  fadd v3.8h, v8.8h, v9.8h
  fadd v4.8h, v8.8h, v9.8h
  fadd v5.8h, v8.8h, v9.8h
  fadd v6.8h, v8.8h, v9.8h
  fadd 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)03191e3f51inst 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)9fa1a7a8branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491500454125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000100051102161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
8020520049150004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000050051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
8020420039150234125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020210099100100800001000000051101161120036800001002004020040200402004020040
80204200391500023125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
80204200391500334125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161220036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b181e1f3f51inst 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)9fa0a8accdcfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500060402580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001001005020004162220036080000102004020040200402004020040
800242003915000120402580010108000010800005064000005200202003920039999631001980010208000020160000200392003911800211091010800001000005020532163320036080000102004020040200402004020040
80024200391500018040258001010800001080000506400001520020200392003999963100198001020800002016000020039200391180021109101080000100051605020543162220036080000102004020040200402004020040
80024200771500100402580010108000012800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000005020502162220036080000102004020040200402004020040
80024200391500000402580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000005020502162220036080000102004020040200402004020040
80024200391500000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020042162220036080000102004020040200402004020040
800242003915001390402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001020005020002162220036080000102004020040200402004020040
80024200391500000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020502162220036080000102004020040200402004020040
800242003915000002302580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020042162220036080000102004020040200402004020040
80024200391500000402580010108000010800005064000015200202003920039999631001980010208000020160000200392003911800211091010800001000005020042162220036080000102004020040200402004020040