Apple M1 Microarchitecture Research by Dougall Johnson

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

ABS (vector, 2S)

Test 1: uops

Code:

  abs v0.2s, v0.2s
  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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722061254745100010001000398160130183037303724143289510001000100030373037111001100000073316112629100030383038303830383038
10043037220103254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037220156254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037237861254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000973116112629100030383038303830383038
1004303723084254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  abs v0.2s, v0.2s
  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)0318191e1f3f4e51inst 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)9fa0a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372251100612954743101001211000010010000500427716013005430133300842827032874510100200100002001000030037300371110201100991001001000010000307101161129633100001003003830038300383003830038
10204300372240000872954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000017101161129633100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
1020430037225004890612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372240000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
1020430037225007980668829547251010010010000100100005004277160130018300373003728264222874510100200100002001000030037300371110201100991001001000010020307101161129633100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010001283807101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e1f3a3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000166640216222962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222970110000103003830038300383003830038
100243003722512760061295472510010101000010100005042771600300183008530037282866287671001020101632010000300373003721100211091010100001020202743640216222962910000103003830038300383003830038
100243003722505370161295472510010101000812100005042785120300183003730037282863287671001020100002010000300373003711100211091010100001000013640216222962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
1002430037225030061295472510010101000010100005042771600300183003730037282863287671001020100002010166300373003711100211091010100001004009640216222966710000103003830038301343017930038
100243003722508610061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222969910000103003830038300383003830038
100243003722507620061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000023640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  abs v0.2s, v8.2s
  abs v1.2s, v8.2s
  abs v2.2s, v8.2s
  abs v3.2s, v8.2s
  abs v4.2s, v8.2s
  abs v5.2s, v8.2s
  abs v6.2s, v8.2s
  abs v7.2s, v8.2s
  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)03080b1e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150000505258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915001030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
8020420039150002430258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391500038151258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391500045930258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
8020420039150003030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)9fa8accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500061258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020716010102003680000102004020040200402004020040
80024200391506304025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502011160692003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020101609112003680000102004020040200402004020040
800242003915000402580010108000010800005064000012007020039200399996310019800102080000208000020039200391180021109101080000100050201216012102003680000102004020040200402004020040
8002420039150780402580010108000010800005064000012002020039200399996310019800102080000208041320039200391180021109101080000100050201016012122003680000102004020040200402004020040
80024200391506613240258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020101601272003680000102004020040200402004020040
8002420039150004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502091606122003680000102004020040200402004020040
80024200391501802302580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201216012102003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201116012112003680000102004020040200402004020040
8002420039150604025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502011160992003680000102004020040200402004020101