Apple M1 Microarchitecture Research by Dougall Johnson

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

CMTST (register, 2D)

Test 1: uops

Code:

  cmtst v0.2d, v0.2d, v1.2d
  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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715010316872510001000100026468020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
1004203715158616872510001000100026468020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100073216111787100020382038203820382038
100420371596116872510001000100026468020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
1004203715012416872510001000100026468020182037203715723189510001000200020372037111001100075216111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmtst v0.2d, v0.2d, v1.2d
  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)03081e3f4e51inst 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
10204200371500456119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500486119687251010010010000100100005002847680120018200372003718422318745107352001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150106119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500756119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037151006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500606119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715004776119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3f4e51inst 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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715018672619687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640316421978510000102003820038200382003820038
100242003715008219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150156119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150366119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371501836119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150126119687251001010100001010000502847680120018200372003718444318786100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371504386119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100030640216221978510000102003820038200382008620038
1002420037150336119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmtst v0.2d, v1.2d, v0.2d
  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)03081e3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100001027102161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010002437101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000107101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000057428476801200182003720037184223187621010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371490010111968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010005707101161119791100001002003820038200382003820038
102042003715000611968710110100100100001001000062728476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000707101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010005157101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e1f3f4e51inst 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)9fa0a8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010010006404163419785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010010006404164419785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010210006403164419785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006404244419785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006404164319785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006614164319785110000102003820038200382003820038
10024200371500006119687441001010100001010000502848963120018200372003718444318767100102010000202000020037200371110021109101010000100183006403167419785010000102003820038200382003820085
10024200371500897152821968725100221010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010050006404164419785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006404164319785010000102003820038200382003820038
1002420037150000611968725100221010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010003006404164419785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmtst v0.2d, v8.2d, v9.2d
  cmtst v1.2d, v8.2d, v9.2d
  cmtst v2.2d, v8.2d, v9.2d
  cmtst v3.2d, v8.2d, v9.2d
  cmtst v4.2d, v8.2d, v9.2d
  cmtst v5.2d, v8.2d, v9.2d
  cmtst v6.2d, v8.2d, v9.2d
  cmtst v7.2d, v8.2d, v9.2d
  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)031e3a3f51inst 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)9fa1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000124258010010080000100800975006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000005910051103162220035800001002003920039200392003920039
80204200381500031632580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051102162220035800001002003920039200392003920039
8020420038150007052580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100001000051102162220035800001002003920039200392003920039
802042003815000612580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051102162220035800001002014120039200392003920039
802042003815000822580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051102162220035800001002003920039200392003920039
802042003815000822580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051102162220035800001002003920039200392003920039
802042003815000612580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051102162220035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100400230051102162420035800001002003920039200392003920039
8020420038150001662580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051102162220035800001002003920039200392003920039
8020420038150001052580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa8a9accfd5d6dbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500018625800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020616069200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020716046200350080000102003920039200392003920039
80024200381503039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001001050205160513200350080000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050205160610200350080000102003920039200392003920039
8002420038150006025800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020616075200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020516066200350080000102003920039200392003920039
8002420038150008125800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020616069200350080000102003920039200392003920039
80024200381490039258001010800001080000506400001200192008820089999631001880010208000020160000200382003811800211091010800001000050205160511200350080000102003920039200392003920039
8002420038150005725800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020616058200350080000102003920039200392003920039
80024200381500010225800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100035020616059200351080000102003920039200392003920039