Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGT (register, 4S)

Test 1: uops

Code:

  cmgt v0.4s, v0.4s, v1.4s
  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)696d6edispatch 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
10042037150821687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160821687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037153821687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150821687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmgt v0.4s, v0.4s, v1.4s
  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)0308090b1e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720085184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000536196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000661196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b1e3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500007261968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100015640216221978510000102003820038200382003820038
1002420037150100611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100057640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000726196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010013640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150002161196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmgt v0.4s, v1.4s, v0.4s
  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)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)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)9fa1a8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100009007102161119791100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100003007101161119791100001002003820085200382003820038
1020420037150000000023519687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000163007101161119791100001002003820038200382003820038
10204200371500000900611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000003300611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000042007101161119791100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000081007101161119791100001002003820038200382003820038
102042003715000000004411968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100003007101161119791100001002003820038200382003820038
10204200371510012000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101162119791100001002003820038200382013420038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420085150100317196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020326200372008421100211091010100001000640216221978510000102003820038200382003820038
1002420037150001561196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100123640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmgt v0.4s, v8.4s, v9.4s
  cmgt v1.4s, v8.4s, v9.4s
  cmgt v2.4s, v8.4s, v9.4s
  cmgt v3.4s, v8.4s, v9.4s
  cmgt v4.4s, v8.4s, v9.4s
  cmgt v5.4s, v8.4s, v9.4s
  cmgt v6.4s, v8.4s, v9.4s
  cmgt v7.4s, v8.4s, v9.4s
  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)03191e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000351103161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019201152003899733999680100200800002001600002003820038118020110099100100800001000651101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000951101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000616640000120019200382003899733999680100200800002001600002003820038118020110099100100800001002051341161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001004051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3a3f51inst 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)6061696d6edispatch 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)9fa0a1a6a7a8a9acc2cfd0icache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000000039258001010800001080000506400001720019200382003899963100188001020800002016000020038200381180021109101080000100000000050206021644200350080000102003920039200392003920039
8002420038150000060039258001010800001080000506400001620019200382003899963100188001020800002016000020038200381180021109101080000100000000050206051644200350080000102003920039200392003920039
80024200381500000120039258001010800001080000506400001620019200382003899963100188001020800002016000020038200381180021109101080000100000000050206051655200350080000102003920039200392003920039
8002420038150000000039258001010800001080000506400001620019200382003899963100188001020800002016000020038200381180021109101080000100000000050206051655200350080000102003920039200392003920039
8002420038150000000039258001010800001080000506400001520019200382003899963100188001020800002016000020038200381180021109101080000100000000050205031644200350080000102003920039200392003920039
8002420038150000000039258001010800001080000506400001520019200382003899963100188001020800002016000020038200381180021109101080000100000000050205041644200350080000102003920039200392003920039
80024200381500000240039258001010800001080000506400001520019200382003899963100188001020800002016000020038200381180021109101080000100000000050205041633200350080000102003920039200392003920039
80024200381490000120039258001010800001080096506400001520019200382003899963100188001020800002016000020038200381180021109101080000100000000050205031643200350080000102003920039200392003920039
8002420038150000000039258001010800001080000506400001520019200382003899963100188001020800002016000020038200381180021109101080000100000000050205041644200350080000102003920039200392003920039
800242003815000000002292580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000003900050205041634200350080000102003920039200392003920039