Apple M1 Microarchitecture Research by Dougall Johnson

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

CMHS (register, 4H)

Test 1: uops

Code:

  cmhs v0.4h, v0.4h, v1.4h
  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
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715010316872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmhs v0.4h, v0.4h, v1.4h
  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)0308090b181e3f4e51inst 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)9fa6a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000030611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
10204200371500010061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000270407102162219791100001002008620085200852008620086
102042008415000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372008611102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768020054200372003718422318745101002001000020020000200372003711102011009910010010000100010007102162219791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219849100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100030017102162219791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371504506119687251001010100001010000502847680020054200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150008219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150606119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000298619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006405564320038310000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820083
1002420037179006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371492706119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmhs v0.4h, v1.4h, v0.4h
  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)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000001506119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071021611197910100001002003820038200382003820038
102042003715000001206119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000025206119687251010010010000100100005002847680200182008420037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005162847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000012419687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000001506119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000034619687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000030264611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500000270611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000030611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000060611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500000120611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmhs v0.4h, v8.4h, v9.4h
  cmhs v1.4h, v8.4h, v9.4h
  cmhs v2.4h, v8.4h, v9.4h
  cmhs v3.4h, v8.4h, v9.4h
  cmhs v4.4h, v8.4h, v9.4h
  cmhs v5.4h, v8.4h, v9.4h
  cmhs v6.4h, v8.4h, v9.4h
  cmhs v7.4h, v8.4h, v9.4h
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015094025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051103162220035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815094025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
8020420038150304025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815034025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
8020420038150070525801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030407090f1e3f51inst 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)9fa8accfd2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481491210039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502000271626262003580000102003920039200392003920039
80024200381500200039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001013502000261625272003580000102003920039200392003920039
80024200381500100639258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502000211623112003580000102003920039200392003920039
8002420038150020018514258001010800001080000506400001201802003820038999631001880010208000020160000200382003811800211091010800001000502000211626162003580000102003920039200392003920039
800242003815001001539258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502000291627272003580000102003920039200392003920039
80024200381500300039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502000151628202003580000102003920039200392003920039
800242003815001001839258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502000281617282003580000102003920039200392003920039
80024200381500300039258001010800001080000506400001200192003820038999631001880010208000020160000200382003821800211091010800001000502000271627272003580000102003920039200392003920039
80024200381500200039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502000281624252003580000102003920039200392003920039
80024200381500300039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000502000271627272003580000102003920039200392003920039