Apple M1 Microarchitecture Research by Dougall Johnson

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

FMUL (scalar, S)

Test 1: uops

Code:

  fmul 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)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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004403730061340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908140184037403732583389510001000200040374037111001100020073116113473100040384038403840384038
1004403730061340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403731061340725100010001000531908040184037403732583389510001000200040374037111001100010373116113473100040384038403840384038
1004403730061340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908040184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403731061340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908040184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
10044037300613407251000100010005319081401840374037325833895100010002000403740371110011000007873116113473100040384038403840384038

Test 2: Latency 1->2

Code:

  fmul 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003729906139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730066139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003729906139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003729906139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0318191e1f3a3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000006403163339473010000104003840038400384003840038
100244003730086106570407697393261771006717100361611184975718076140123404564046438162423894111291201145522225804046540463101100211091010100001022132308472341124439833410000104046140464405004049640225
100244046630395118879217316393251981006919100541211332565719472140333404624051238170403893811354241143222229584046140467101100211091010100001020032643072751014539799010000104003840038400384003840038
100244003730000000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000006403163339473010000104003840038400384003840038
100244003730000000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000006403163339547010000104003840038400384003840038
100244003730000000663940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000006403164339473010000104003840038400384003840038
100244003730000000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000006403163339473010000104003840038400384003840038
100244003729900000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000006403163339473010000104003840038400384003840038
100244003731000900613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000006403163339473010000104003840038400384003840038
100244003729900000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000006403163339473010000104003840038400384003840038

Test 3: Latency 1->3

Code:

  fmul 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)03080b18191e1f3f4e51inst 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)6061696b6d6edispatch 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)9fa0a6a8a9acbranch mispredict (cb)cdcfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000000008443940725101001001000010010000500570690802400180400374003738108033874510100200100002002000040037400371110201100991001001000010000000007102211611394790100001004003840038400384003840038
1020440037300000000613940725101001001000010010000500570690800400180400374003738108033874510100200100002002000040037400371110201100991001001000010000000007100011611394790100001004003840038400384003840038
1020440037300000000914394071001010010010000100100005005707928104001804003740037381080338745101002001000020020330400844003711102011009910010010000100200113007102011611394790100001004003840038400384003840038
1020440037300000000613940725101001001000010010000500570690800400180400374003738108033874510100200100002002000040037400371110201100991001001000010000000007100011611394790100001004003840038400384003840038
1020440037300000000613940725101001001000010010000500570690802400180400374003738108033874510100200100002002000040037400371110201100991001001000010000000007100011611394790100001004003840038400384003840038
102044013330001003601033940725101001001000010010000500570690800400180400374003738108033874510100200100002002000040037400371110201100991001001000010000000007100011611394790100001004003840038400384003840038
1020440037300000000613940725101001001000010010000500570690800400180400374003738108033874510100200100002002000040037400371110201100991001001000010000000007100011611394790100001004003840038400384003840038
1020440037300000000613940725101001001000010010000500570690800400180400374003738108033874510100200100002002000040037400371110201100991001001000010000000007100011611394790100001004003840038400384003840038
1020440037300000000613940725101001001000010010000500570690800400180400374003738108033874510100200100002002000040037400371110201100991001001000010000000007100011611394790100001004003840038400384003840038
10204400373000000006139407251010010010000100100005005706908024001804003740037381080338745101002001000020020000400374003711102011009910010010000100000024007100011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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)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)9fa0a1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000006405165539473010000104003840038400384003840038
100244003729900000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000006404165539473010000104003840038400384003840038
100244003729900000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000006405164539473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000006404165539473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000006404164539473010000104003840038400384003840038
100244003729900000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000364606405165539473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000000006405165539473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000006404165439473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000006405165439473010000104003840038400384008540038
100244003729900000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000006405165439473010000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  fmul s0, s8, s9
  fmul s1, s8, s9
  fmul s2, s8, s9
  fmul s3, s8, s9
  fmul s4, s8, s9
  fmul s5, s8, s9
  fmul s6, s8, s9
  fmul 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)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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100000051103161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
80204200401509422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
80204200401510422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100000151101161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041

1000 unrolls and 10 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)5f6061696d6edispatch 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)cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004915000412580010108000010800005064000001020021200402004099963100208001020800002016000020040200401180021109101080000100000502003051600044200370080000102004120041200412004120041
8002420040150015412580010108000010800005064000001520021200402004099963100208001020800002016000020040200401180021109101080000100000502003031600034200370080000102004120041200412004120041
800242004015000412580010108000010800005064000001520021200402004099963100208001020800002016000020040200401180021109101080000100000502053041600034200370080000102004120041201162004120041
8002420040150004125800101080000108000050640000010200212004020040999631002080010208000020160000200402004011800211091010800001001200502003071600034200370080000102004120041200412004120041
80024200401500041258001010800001080000506400000102002120040200409996310020800102080000201600002004020040118002110910108000010016500502000031600044200370080000102004120041200412004120041
800242004015000412580010108000010800005064000001020021200402004099963100208001020800002016000020040200401180021109101080000100000502050031600044200370080000102004120041200412004120041
80024200401500041258001010800001080000506400000152002120040200409996271002080010208000020160000200402004011800211091010800001001800502000071600034200370080000102004120041200412004120041
800242004015000412580010108000010800005064246811520021200402004099963100208001020800002016000020040200401180021109101080000100000502050071600074200370080000102004120041200412004120041
800242004015000412580010108000010800005064000000520021200402004099963100208001020800002016000020040200401180021109101080000100001502003061600064200370080000102004120041200412004120041
800242004015000472580010108000010800005064000000520021200402004099963100208001020800002016000020040200401180021109101080000100300502280041600043200370080000102004120041200412004120041