Apple M1 Microarchitecture Research by Dougall Johnson

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

FMULX (scalar, S)

Test 1: uops

Code:

  fmulx s0, s0, s1
  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
10044037309613407251000100010005319084018403740373258338951000100020004037403711100110000073216113473100040384038403840384038
10044037310613407251000100010005319084018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
10044037300613407251000100010005319084018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
10044037300613407251000100010005319084018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
10044037300613407251000100010005319084018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
10044037300613407251000100010005319084018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373112613407251000100010005319084018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
10044037300613407251000100010005319084018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190840184037403732583389510001000200040374037111001100003073116113473100040384038403840384038
10044037310613407251000100010005319084018403740373258338951000100020004037403711100110000073116113473100040384038403840384038

Test 2: Latency 1->2

Code:

  fmulx s0, s0, s1
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

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)9facc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394791100001004008240038400384003840038
10204400373000613940725101001001000010010000500570690814001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
10204400372990613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
10204400372990613940725101001001000010010000500570690814001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
10204400372990613940725101001001000010010000500570690814001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
10204400372990613940725101001001000010010000500570690814001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030b18191e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373001000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010006405166639473010000104003840038400384003840038
1002440037300000046723940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010006406164639473010000104003840038400384003840038
10024400372990000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010006406165639473010000104003840038400384003840038
10024400372990006613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010006406166639549010000104003840038400384003840038
10024400373000010613939825100101010000101000050570690814005340085400373813033878610010201000020203244003740037211002110910101000010006406166539473010000104003840038400384003840038
100244003729900001033940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010106406166539473010000104003840038400384003840038
10024400773000000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010166406166539473110000104003840038400384003840038
10024400372990000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010036406165639473010000104003840038400384003840038
10024400373000000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010006404166639473010000104003840038400384003840038
100244003730000045613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010006405166639473010000104003840038400384003840038

Test 3: Latency 1->3

Code:

  fmulx s0, s1, s0
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037299000000006139407251010010010000100100005005706908040018400374003738115638741101002001000820020016400374003711102011009910010010000100000006011171801600394890100001004003840038400384003840038
1020440037300000000006139407251010010010000100100005005706908140018400374003738115638741101002001000820020016400374003711102011009910010010000100000000011171801600394900100001004003840038400384003840038
1020440037300000000006139407251010010010000100100005005706908140018400374003738115738739101252001000820020016400374003711102011009910010010000100000000011171701600394900100001004003840038400384003840038
1020440037300000000006139407251010010010000100100005005706908140018400374003738115738740101002001000820020016400374003711102011009910010010000100000000011171701600394890100001004003840038400384003840038
1020440037299000000006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000000000071011611394790100001004003840038400384003840038
1020440037299000000006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000000000071011611394790100001004003840038400384003840038
1020440037300000000006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100000000000071011611394790100001004003840038400384003840038
1020440037300000000006139407251010010010000100100005005706908140018400374003738108338745101002001000020420000400374003711102011009910010010000100000000000071011611394790100001004003840038400384003840038
1020440037300000000006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000000000071011611394790100001004003840038400384003840038
1020440037300000000006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100000000000071211611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03080b3f4e51inst 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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100363100640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100001640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
10024400372990072639407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100364500640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100900640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000103000640216223947310000104003840038400384003840038
1002440037299006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100300640216223947310000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  fmulx s0, s8, s9
  fmulx s1, s8, s9
  fmulx s2, s8, s9
  fmulx s3, s8, s9
  fmulx s4, s8, s9
  fmulx s5, s8, s9
  fmulx s6, s8, s9
  fmulx s7, s8, s9
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051102161120037800001002004120041200412004120041
8020420040150042525801001008000010080000500640000200210201482004099733999880100200800002001600002004020040118020110099100100800001000351101161120037800001002004120041200412004120041
802042004015104225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051101161120037800001002004120041200412004120041
8020420040150244225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051101161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000020021320040200409973399988010020080000200160000200402004011802011009910010080000100181551101161120037800001002004120041200412004120041
802042004015064225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051101161120037800001002004120041200412004120041
8020420040150186325801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051101161120037800001002004120041200412004120041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)5f60696d6edispatch 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)9fa0a6a8accfd5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500041258001010800001080000506400001020021200402004099963100208001020800002016000020040200401180021109101080000100006502071607520037080000102004120041200412004120041
80024200401500041258001010800001080000506400000120021200402004099963100208001020800002016000020040200401180021109101080000100000502051605320037080000102004120041200412004120041
80024200401500041258001010800001080000506400000120021200402004099963100208001020800002016000020040200401180021109101080000100003502061605520037080000102004120041200412004120041
8002420040150003262580010108000010800005064000000200212004020040999631002080010208000020160000200402004011800211091010800001000048502051606420037080000102004120041200412004120041
800242004015000412580010108000010800005064000011200212004020040999631002080010208000020160000200402004011800211091010800001000018502051605320037080000102004120041200412004120041
80024200401500041258001010800001080000506400000020021200402004099963100208001020800002016000020040200401180021109101080000100000502031603520037080000102004120041200412004120041
80024200401500041258001010800001080000506400000020021200402004099963100208001020800002016000020040200401180021109101080000100000502031603520037080000102004120041200412004120041
80024200401500041258001010800001080000506400001120021200402004099963100208001020800002016000020040200401180021109101080000100000502031603520037080000102004120041200412004120041
80024200401500041258001010800001080000506400000020021200402004099963100208001020800002016000020040200401180021109101080000100000502051606420037080000102004120041200412004120041
80024200401500041258001010800001080000506400000120021200402004099963100208001020800002016000020040200401180021109101080000100000502051606320037080000102004120041200412004120041