Apple M1 Microarchitecture Research by Dougall Johnson

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

FRECPS (vector, 2D)

Test 1: uops

Code:

  frecps v0.2d, v0.2d, v1.2d
  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)031e1f3f4e51inst 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100440373000613407251000100010005319080401840374037325833895100010002000403740371110011000073116113473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010002000403740371110011000073116113473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010002000403740371110011000073116113473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010002000403740371110011000073116113473100040384038403840384038
100440373000843407251000100010005319080401840374037325833895100010002000403740371110011000073116113473100040384038403840384038
1004403730006134072510001000100053190804018403740373258338951000100020004037403711100110003773116113473100040384038403840384038
1004403730001843407251000100010005319080401840374037325833895100010002000403740371110011000073116113473100040384038403840384038
100440373000613407251000100010005319081401840374037325833895100010002000403740371110011000073116113473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010002000403740371110011000073116113473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010002000403740371110011000073116113473100040384038403840384038

Test 2: Latency 1->2

Code:

  frecps v0.2d, v0.2d, v1.2d
  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)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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300006139407251010010010000100100005005706908400184003740037381083387451010020010000200200004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908400184003740037381083387451010020010000200200004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908400184003740037381083387451010020010000200200004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908400184003740037381083387451010020010000200200004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037300106139407251010010010000100100005005706908400184003740037381083387451010020010000200200004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037299006139407251010010010000100100005005706908400184003740037381083387451010020010000200200004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037300006139407251010010010000100101475005706908400184003740037381083387451010020010000200200004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908400184003740037381083387451010020010000200200004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037299006139407251010010010000100100005005706908400184003740037381083387451010020010000200200004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
102044003729904266139407251010010010000100100005005706908400184003740037381083387451010020010000200200004003740037111020110099100100100001000007102162239479100001004003840038400384003840038

1000 unrolls and 10 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730096139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010006402162239473210000104003840038400384003840038
100244003730006139407251001010100001010000505706908140018040037400373813033876710010201016220200004003740037111002110910101000010006422162239473010000104003840038400384003840038
100244003730008439407251001010100001010000505706908140018040037400373813033876710012201000020200004003740037111002110910101000010006402162239473010000104003840038400384003840038
100244003729906139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010006402162239473010000104003840038400384003840038
100244003730006139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010006402162239473010000104003840038400384003840038
1002440037299061394072510010101000012100005057069080400180400374003738130338767100102010000202000040037400371110021109101010000104006402162239473010000104003840038400384003840038
100244003730006139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010006402162239473010000104003840038400384003840038
1002440037300126139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037211002110910101000010006402162239473010000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018040037400373813033876710010201000020200004003740037111002110910101000010006402162239473010000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018040037400373813033876710010201000020200004003740037111002110910101000010006403162239473010000104003840038400384003840038

Test 3: Latency 1->3

Code:

  frecps v0.2d, v1.2d, v0.2d
  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)0308090b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037299000000061394072510100100100001001000050057069081400180400374003738108338745101002001000020020000400374003711102011009910010010000100000000071011611394790100001004008540038400384003840038
102044003729900030210103394072510100100100001001000050057069080400180400844003738108338745101002041000020020000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400180400374003738108338763102672001000020020000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
10204400373000000000105394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
10204400373000000000145394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000000471011621394790100001004003840038400384003840038
102044003730010010162061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000100071011611394790100001004003840038400384003840038
10204400373000000000103394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000003071011611394790100001004003840038400384003840038
10204400373001000045061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000000071001611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038

1000 unrolls and 10 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037300025139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003729906139407251001010100001010000505706908040018400374003738130338786100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003729906139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037300010339407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003729906139407251001010100001010000505706908140018400374003738135338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  frecps v0.2d, v8.2d, v9.2d
  frecps v1.2d, v8.2d, v9.2d
  frecps v2.2d, v8.2d, v9.2d
  frecps v3.2d, v8.2d, v9.2d
  frecps v4.2d, v8.2d, v9.2d
  frecps v5.2d, v8.2d, v9.2d
  frecps v6.2d, v8.2d, v9.2d
  frecps v7.2d, v8.2d, v9.2d
  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)0309183f51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100051103161120037800001002004120041200412004120041
8020420040150001682580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100051101161120037800001002004120041200412004120041
802042004015000422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100051101163120037800001002004120041200412004120041
802042004015010422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100051101161120037800001002004120041200412004120041
802042004015000422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100051101161120037800001002004120041200412004120041
802042004015000422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100051101161120037800001002004120041200412004120041
802042004015000632580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100051101161120037800001002004120041200412004120041
802042004015000422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100051101161120037800001002004120041200412004120041
802042004015000422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100051101161120037800001002004120041200412004120041
802042004015000422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100051101161120037800001002004120041200412004120041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)9fa6a8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500063041258001010800001080000506400001020021200402004099963100208001020800002016000020040200401180021109101080000100144005020006163520037080000102004120041200412004120041
8002420040150001504125800101080000108000050640000102002120040200409996310020800102080000201600002004020040118002110910108000010000005020003163620037080000102004120041200412004120041
8002420040150001504125800101080000108000050640000102002120040200409996310020800102080000201600002004020040118002110910108000010000005020003163520037080000102004120041200412004120041
8002420040150006304125800101080000108000050640000102002120040200409996310020800102080000201600002009120040118002110910108000010000005020005165320037080000102004120041200412004120041
8002420040150005404125800101080000108000050640000102002120040200409996310020800102080000201600002004020040118002110910108000010000005020003165320037080000102004120041200412004120041
8002420040150006304125800101080000108000050640000102002120040200409996310020800102080000201600002004020040118002110910108000010020005020005165520037080000102004120041200412004120041
800242004015000008325800101080000108000050640000102002120040200409996310020800102080000201600002004020040118002110910108000010000005020003165520037080000102004120041200412004120041
800242004015000004125800101080000108000050640000102002120040200409996310020800102080000201600002004020040118002110910108000010000005020005165320037080000102004120041200412004120041
8002420040150007204125800101080000108000050640000102002120040200409996310020800102080000201600002004020040118002110910108000010000005020004163520037080000102004120041200412004120041
8002420040150000023125800101080000108000050640000102002120040200409996310020800102080000201600002004020040118002110910108000010000005020005165320037080000102004120041200412004120041