Apple M1 Microarchitecture Research by Dougall Johnson

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

SQNEG (vector, 2D)

Test 1: uops

Code:

  sqneg v0.2d, v0.2d
  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)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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100073116112629100030383038303830863038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqneg v0.2d, 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): 3.0037

retire (01)cycle (02)03080b18191e3a3f4e51inst 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)9fa8cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372240000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250000906129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011613296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043007422611430025129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)9fa8branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006403162229629110000103003830038300383003830038
10024300372240000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372240000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250000612953825100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010016402162229629010000103003830038300383003830038
100243003722500007262954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500007262954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500007262954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500001562954725100101010000101014850427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqneg v0.2d, v8.2d
  sqneg v1.2d, v8.2d
  sqneg v2.2d, v8.2d
  sqneg v3.2d, v8.2d
  sqneg v4.2d, v8.2d
  sqneg v5.2d, v8.2d
  sqneg v6.2d, v8.2d
  sqneg v7.2d, v8.2d
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)033f51inst 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)9fa0a1a7a8acc2c5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001001115118016020036800001002004020040200402004020040
802042003915030818010810080008100800205006409442002020039200399977699908012020080032200800322003920103118020110099100100800001000000001115118016020036800001002004020040200402004020040
80204200391504801258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000211143021115135016020246800001002004020040200402009020040
8020420039150302580108100800081008002050064013220020200392003999861299908012020080032200800322003920039118020110099100100800001004001141301115173128020036800001002004020040200402004020040
802042003915030798021210080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040
802042003915051258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e1f3f51inst 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)9e9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800000100000502018168172003680000102004020040200402004020040
80024200391500000021225800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800000100000502061617152003680000102004020040200402004020040
800242003915000000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000010000050207161582003680000102004020040200402004020040
8002420039150000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800000100000502014161762003680000102004020040200402004020040
800242003915000000727258001010800801080000506400001200202003920039999631001980010208000020800002003920039118002110910108000001000005020141617172003680000102004020040200402004020040
8002420039150000002302580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000010000050206161772003680000102004020040200402004020040
8002420039150000001052580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000010000050208166172003680000102004020040200402004020040
8002420039150000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800000100000502014161782003680000102004020040200402004020040
80024200391500000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000001000005020161617172003680000102004020040200402004020040
8002420039150000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800000100000502012161762003680000102004020040200402004020040