Apple M1 Microarchitecture Research by Dougall Johnson

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

FMUL (vector, 4H)

Test 1: uops

Code:

  fmul v0.4h, v0.4h, v1.4h
  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)a0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10044037300613407251000100010005319081401840374037325833895100010002000403740371110011000000373216223473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010002000403740371110011000000073216223473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010002000403740371110011000000073216223473100040384038403840384038
10044037300613407251000100010005319081401840374037325833895100010002000403740371110011000000073216223473100040384038403840384038
10044037303613407251000100010005319081401840374037325833895100010002000403740371110011000000073216223473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010002000403740371110011000000073216223473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010002000403740371110011000000073216223473100040384038403840384038
10044037310613407251000100010005319080401840374037325833895100010002000403740371110011000000073216223473100040384038403840384038
100440373012613407251000100010005319080401840374037325833895100010002000403740371110011000000073216223473100040384038403840384038
10044037309613407251000100010005319080401840374037325833895100010002000403740371110011000000073216223473100040384038408540384038

Test 2: Latency 1->2

Code:

  fmul v0.4h, v0.4h, v1.4h
  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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000613940725101001001000010010000500571249240018400374003738108338745101002001000020020000400374003711102011009910010010000100017363271011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690840018400374003738108338745102512001000020020000400374003711102011009910010010000100010971011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690840018400374003738108338745101002001000020020000400374003711102011009910010010000100010971011611394790100001004003840038400384003840038
1020440037300661394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010007971011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010007971011611394790100001004003840038400384003840038
1020440037299061394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010001671011611394790100001004003840038400384003840038
102044003729909153940725101001001000010010000500570690840018400374003738108338745101002001000020020000400374003711102011009910010010000100010971011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010000371011611394790100001004003840038400384003840038
1020440037299061394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010008971011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690840018400374003738108338745101002001000020020000400374003711102011009910010010000100058671011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03080a18191e1f3f4e51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440418303119910687046476393261211006719100541411332765720868040333404534049838168203895211347201080720228984046340451911002110910101000010220323348354883239873210000104055840553405584056140595
10024405563041011101329528613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010006126402162239473010000104003840038400384003840038
100244003729900000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000306402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000306402162239473010000104003840038400384003840038
1002440037300000036061394072510010101000010100005057069081400184008140037381303387671001020100002020000400374003711100211091010100001000306402162239473010000104003840038400384003840038
1002440037299000000536394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000206402162239473010000104003840038400384003840038
1002440037300000000613940710210010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000106402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000036402162239473010000104003840038400384003840038
100244003729900000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000106402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000166402162239473010000104003840038400384003840038

Test 3: Latency 1->3

Code:

  fmul v0.4h, v1.4h, 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): 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)60696b6d6edispatch 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
102044003730001493940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001003007101161139479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010024007101161139479100001004003840038400384003840038
102044003730006139407105101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000202200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000613940764101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244008330000823940765100341010000121014850570690814001840037400373813033876710010201000020200004003740037111002110910101000010100640216223947310000104003840038400384003840038
1002440037299012613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010030640216223947310000104003840038400384003840038
100244003730000613940725100101010000101014850570690814001840037400373813033876710158201000020200004003740037111002110910101000010130640216223947310000104003840038400384003840038
1002440037299015613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003729900613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840077400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010100640216223947310000104003840038400384003840038
100244008430000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300002453940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037299096713940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300005483940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  fmul v0.4h, v8.4h, v9.4h
  fmul v1.4h, v8.4h, v9.4h
  fmul v2.4h, v8.4h, v9.4h
  fmul v3.4h, v8.4h, v9.4h
  fmul v4.4h, v8.4h, v9.4h
  fmul v5.4h, v8.4h, v9.4h
  fmul v6.4h, v8.4h, v9.4h
  fmul v7.4h, v8.4h, v9.4h
  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)030b18191e1f3a3f51inst 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)9fa1a6a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500000004225801001008000010080000500640000120021200402004099733999880100200800002001600002004020040118020110099100100800001000030530051103161120037800001002004120041200412004120041
802042004015000000042258010010080000100800005006400001200212004020040997339998801002008000020016000020040200401180201100991001008000010000000051101161120037800001002004120041200412004120041
802042004015000000042258010010080000100800005006400000200212004020040997339998801002008013620016000020040200401180201100991001008000010000000051101161120037800001002004120041200412004120041
8020420040150000000947258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000000051101161120037800001002004120041200412004120041
80204200401500000008172580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100002303051101161120037800001002004120041200412004120096
802042004015000000042258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000000051101161120037800001002004120041200412004120041
8020420040150000000996258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000000051101161120037800001002004120041200412004120041
8020420040150000000842258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000000051101161120037800001002004120041200412004120041
8020420040150000000422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100002600051101161120037800001002004120041200412004120041
802042004015000000010132580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100002200051101161120037800001002004120041200412004120041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)60696b6d6edispatch 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)9fa8accdcfd5d6dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004915000094825800101080000108000050640000020021320040200409996310020800102080000201600002004020040118002110910108000010000502041600552003780000102004120041200412004120041
80024200401550004125800101080000108000050640000020021020040200409996310020801172080000201600002004020040118002110910108000010100502051600332003780000102004120041200412004120041
800242004015000019025800101080000108000050640000020021020040200409996310020800102080000201600002004020040118002110910108000010030502031600322003780000102004120041200412004120041
8002420040150000121325800101080000108000050640000120021020040200409996310020800102080000201600002004020040118002110910108000010000502021600232003780000102004120041200412004120041
80024200401500001065258001010800001080000506400001200210200402004099963100208001020800002016000020040200401180021109101080000100120502021600232003780000102004120041200412004120041
80024200401500004125800101080000108000050640000120021020040200409996310020800102080000201600002004020040118002110910108000010000502031600332003780000102004120041200412004120041
800242004015000016725800101080000108000050640000020021020040200409996310020800102080000201600002004020040118002110910108000010000502051600322003780000102004120041200412004120041
80024200401490004125800101080000108000050640000120021020040200409996310020800102080000201600002004020040118002110910108000010000502031600322003780000102004120041200412004120041
80024200401500006225800101080000108000050640000120021020040200409996310020800102080000201600002004020040118002110910108000010000502031600352003780000102004120041200412004120041
800242004015000010625800101080000108000050640000120021020040200409996310020800102080000201600002004020040118002110910108000010000502051600652003780000102004120041200412004120041