Apple M1 Microarchitecture Research by Dougall Johnson

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

CLS (vector, 8B)

Test 1: uops

Code:

  cls v0.8b, v0.8b
  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
1004203715016616862510001000100026452102018203720371571318951000100010002037203711100110000073316221786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073316331786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073316331786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073316331786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073316331786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073316331786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110001073416331786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073316331786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110000073316331786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110001073316331786100020382038203820382038

Test 2: Latency 1->2

Code:

  cls v0.8b, v0.8b
  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)03191e3f4e51inst 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)72scheduler 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
1020420037150006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521200182003720037184210318765101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820085
1020420037150006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475212001820037200371842102618745101002001000020010000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
1020420078150006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163319786010000102003820038200382003820038
100242003715000000001031968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000306403163319848010000102003820038200382003820085
100242003715000000001451968625100101010012101015250284752112001820084200841844331876710010201000020100002003720037111002110910101000010000010006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000010306403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006403163319786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cls v0.8b, v8.8b
  cls v1.8b, v8.8b
  cls v2.8b, v8.8b
  cls v3.8b, v8.8b
  cls v4.8b, v8.8b
  cls v5.8b, v8.8b
  cls v6.8b, v8.8b
  cls v7.8b, v8.8b
  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)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)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)9facc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591502202362580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000111512210169920035800001002003920039200392003920039
80204200381502202362580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000111512291612920035800001002003920039200392003920039
8020420038150220236258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151224164920035800001002003920039200392003920039
80204200381502202769258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151224164920035800001002003920039200392003920039
80204200381502202773258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151229169920035800001002003920039200392003920039
8020420038150220236258010810080008100800205006401321200192003820038997769989801202008003220080032200382003821802011009910010080000100011151229169920035800001002003920039200392003920039
80204200381502202362580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000111512291610920035800001002003920039200392003920039
80204200381502202362580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000111513891610920035800001002003920039200392003920039
8020420038150220236258010811480008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151229169920035800001002003920039200392003920039
8020420038150220236258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151229169920035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b0f18191e1f3f51inst 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)9fa0a1a6a8a9acc2cfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000200003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020090116112003580000102003920039200392003920039
800242003815000000008125800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020070116112003580000102003920039200392003920039
800242003815000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020070116112003580000102003920039200392003920039
800242003815000000003925800101080000108000050640000020019200382003899963100188001020800002080132200382003811800211091010800001000010005020080116112003580000102003920039200392003920039
800242003815000000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000305020070116112003580000102003920039200392003920039
800242003815000000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020091116112003580000102003920039200392003920039
800242003815000000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020070116112003580000102003920039200392003920039
800242003815000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020081116112003580000102003920039200392003920039
8002420038150000000033125800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020080116112003580000102003920039200392003920039
800242003815000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020080116112003580000102003920039200392003920039