Apple M1 Microarchitecture Research by Dougall Johnson

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

FMULX (by element, 2D)

Test 1: uops

Code:

  fmulx v0.2d, v0.2d, v1.d[1]
  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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10044037304561340725100010001000531908140184037403732583389510001000200040374037111001100001073116113473100040384038403840384038
1004403730061340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
10044037301561340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
10044037300124340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
10044037300216340725100010001000531908140184037403732583389510001000200040374037111001100020073116113473100040384038403840384038
100440373022261340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
10044037300103340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038

Test 2: Latency 1->2

Code:

  fmulx v0.2d, v0.2d, v1.d[1]
  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)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)9fa6accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037313006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908140018400374003738108338745101002001000020420000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
10204400372990019339407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
10204400373001074739407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
1020440037300006139407431010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908140018400374003738108338765101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038

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)9fa6a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100010640316223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100020640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000584640216223947310000104003840038400854003840038
1002440037300012639407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100033640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100010640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100030640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100030640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100013640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000526640216223947310000104003840086400384003840038

Test 3: Latency 1->3

Code:

  fmulx v0.2d, v1.2d, v0.d[1]
  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)9fa0a6a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000007102162239479100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000003007102162239479100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000004007102162239479100001004003840038400384003840038
1020440037299061394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000002007102162239479100001004003840038400384008740038
10204400373000536394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000000007102162239479100001004003840038400384003840038
1020440037299061394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000003007102162239479100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000003007102162239479100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000004007102162239479100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000000037102162239479100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000007102162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03091e3f4e51inst 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)9fa6a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300206139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010000064021622394733210000104003840038400384003840038
1002440037299006139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010000064021622394730010000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010000064021622394730010000104003840038400384003840038
1002440037299006139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010000064021622394730010000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400180400374003738130338767100102010000202000040037400371110021109101010000100230064021622394730010000104003840085400854008540038
1002440037300006139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010000064021622394730010000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010000064021622394730010000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010000064022422394730010000104003840038400384003840038
1002440037299006139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010000064021622394730010000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018040037400373813033876710010201000020200004003740037111002110910101000010000064021622394730010000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  fmulx v0.2d, v8.2d, v9.d[1]
  fmulx v1.2d, v8.2d, v9.d[1]
  fmulx v2.2d, v8.2d, v9.d[1]
  fmulx v3.2d, v8.2d, v9.d[1]
  fmulx v4.2d, v8.2d, v9.d[1]
  fmulx v5.2d, v8.2d, v9.d[1]
  fmulx v6.2d, v8.2d, v9.d[1]
  fmulx v7.2d, v8.2d, v9.d[1]
  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)030918191e3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591500000176258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051103163220037800001002004120041200412004120090
8020420040150000042258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000351103162320037800001002004120041200412004120041
8020420040150000042258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051102162320037800001002004120041200412004120041
8020420040150000042258010010080000100800005006400001200210200402004099733999880100200800002001600002004020040118020110099100100800001000051102162320037800001002004120041200412004120041
8020420040150000042258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051102162320037800001002004120041200412004120041
8020420040150000042258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051102162120037800001002004120041200412004120041
8020420040150000063258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051102162320037800001002004120041200412004120041
8020420040150000042258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051102163220037800001002004120041200412004120041
80204200401500000411258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051102163320037800001002004120041200412004120041
8020420040150000042258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000051103163220037800001002004120041200412004120041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e3a3f51inst 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)9fa9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420049150110248258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010000502419219162003780000102004120041200412004120041
80024200401501102482580010108000010800005064000020021200402004099963100208001020800002016000020040200401180021109101080000100005024171613162003780000102004120041200412004120041
80024200401501102482580010108000010800005064000020021200402004099963100208001020800002016000020040200401180021109101080000100005024171620172003780000102004120041200412004120041
80024200401501102482580010108000010800005064000020021200402004099963100208001020800002016000020040200401180021109101080000100005024151616172003780000102004120041200412004120041
80024200401501102482580010108000010800005064000020021200402004099963100208001020800002016000020040200401180021109101080000100005024141619162003780000102004120041200412004120041
80024200401501102482580010108000010800005064000020021200402004099963100208001020800002016000020040200401180021109101080000100005024161613142003780000102004120041200412004120041
8002420040150110248258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010000502491616172003780000102004120041200412004120041
80024200401501102582580010108000010800005064000020021200402004099963100208001020800002016000020040200401180021109101080000100005024141616162003780000102004120041200412004120041
80024200401501102692580010108000010800005064000020021200402004099963100208001020800002016000020040200401180021109101080000100305024161617162003780000102004120041200412004120041
80024200401501102482580010108000010800005064000020021200402004099963100208001020800002016000020040200401180021109101080000100005024161614182003780000102004120041200412004120041