Apple M1 Microarchitecture Research by Dougall Johnson

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

CMEQ (zero, 4S)

Test 1: uops

Code:

  cmeq v0.4s, v0.4s, #0
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073316221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371596116862510001000100026452112018203720371571318951000100010002037203711100110005073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216231786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmeq v0.4s, v0.4s, #0
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)033f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371508219686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371506119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371506119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715014719686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371498219686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715014919686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371506119641251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371506119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371506119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371508419686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000001471968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402163219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402163219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201018020100002003720037111002110910101000010000000006402163219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402163219786010000102003820038200382003820038
100242003715000000006121968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000000001701968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402163219786010000102003820038200382003820038
100242003715000000001491968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402163219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmeq v0.4s, v8.4s, #0
  cmeq v1.4s, v8.4s, #0
  cmeq v2.4s, v8.4s, #0
  cmeq v3.4s, v8.4s, #0
  cmeq v4.4s, v8.4s, #0
  cmeq v5.4s, v8.4s, #0
  cmeq v6.4s, v8.4s, #0
  cmeq v7.4s, v8.4s, #0
  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)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)9fa0acc5branch mispredict (cb)cdcfd6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150073258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100031115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118161020035800001002003920039200392003920039
8020420038150052258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118161020035800001002003920090201112003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118161020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118161020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160120035800001002003920039200392003920039
80204200381500138258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e3f51inst 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)9fa8cfd5d6d9daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010050202016701042003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001005020816601462003580000102003920039200392003920039
800242003815500392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100502091680592003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001005020916604122003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010050209161005132003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001005020916601352003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001005020916601092003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100502091660942003580000102003920039200392003920039
80024200381500039258001010800001080108506400001200192003820038999631001880010208000020800002003820038118002110910108000010050205166013122003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001005020936806132003580000102003920039200392003920039