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, 16B)

Test 1: uops

Code:

  cmtst v0.16b, v0.16b, v1.16b
  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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716361168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmtst v0.16b, v0.16b, v1.16b
  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)0318191e1f3a3f4e51inst 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)9fa1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500066006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371510042006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680020018200372003718422318745101002001000020420000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150009006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100010071011611197910100001002003820038200382003820038
1020420037149000006119687251010010010000100100005002847680020018200372003718422318745102522001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680020018200372003718422318745101002001018020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e1f3f4e51inst 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)9fa8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150060611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500004411968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420085150000611968725100101010000101000050284768020018200372008418444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715001800611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150060611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500006421968725100101010000101000050284768020018200372003718448318767100102010169202000020037200731110021109101010000100000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmtst v0.16b, v1.16b, v0.16b
  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)0308090b191e1f3f4e5051inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000006119687025101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000061196872002125101001001000010010000500284768002001820085200371842231874510100200100002002000020037200371110201100991001001000010000003071011611197910100001002003820038200382003820038
1020420037150000090611968720021251010010010000100100005002848214020018200372003718422318745101002001000020020000200372003711102011009910010010000100000090071011611197910100001002003820085200852003820038
1020420037150000000631196870251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000370071011611197910100001002003820038200382003820038
10204200371500000006119687025101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000003071011611197910100001002003820038200382003820038
10204200371500000006119687025101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000019071011611197910100001002003820038200382003820038
102042003715000000061196870251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100020018071011611197910100001002003820038200382003820038
102042003715000000061196870251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000045071011611197910100001002003820038200382003820038
10204200371560000906119687025101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000061196870251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000012071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030408091e1f3f4e51inst 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)60696b6d6edispatch 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)9fa0a1a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715010000611968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100010006402162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100000306402162119823210000102003820038200382003820038
10024200371500004201086119687251001010100001010000502847680120018020037200371844403187671001020100002020000200372003711100211091010100001000610006402162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000906119687251001010100001010000502847680120018020037200371844403187671001020100002020000200372003711100211091010100001000290306402162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200372110021109101010000100000306402162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002001802003720037184440318767100102010000202000020037200371110021109101010000100010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmtst v0.16b, v8.16b, v9.16b
  cmtst v1.16b, v8.16b, v9.16b
  cmtst v2.16b, v8.16b, v9.16b
  cmtst v3.16b, v8.16b, v9.16b
  cmtst v4.16b, v8.16b, v9.16b
  cmtst v5.16b, v8.16b, v9.16b
  cmtst v6.16b, v8.16b, v9.16b
  cmtst v7.16b, v8.16b, v9.16b
  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)0307080b18191e1f3f51inst 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000003511021611200350800001002003920039200392003920039
8020420088150000000040258010010080000100800005006400000200192003820038999839996801002008000020016000020038200381180201100991001008000010000206511011611200350800001002003920039200892003920039
8020420038150000200040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000003511011611200350800001002003920039200392003920039
8020420038150000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000003511011611200350800001002003920039200392003920039
8020420038150000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000003511011611200350800001002003920039200392003920039
8020420038150000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000003511011611200350800001002003920039200392003920039
8020420038150000000040258010010080000100800005006400001200192003820038997339996801002008039120016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
80204200381500004000402580100100800001138000050064000012001920038200389973310103801002008000020016000020038200381180201100991001008000010000203511011611200350800001002003920039200392003920039
8020420038150111111628840548020210880095121800995376400001200192008820097997339996801002008000020016000020038200381180201100991001008000010020403512711611200350800001002003920039200392003920039
8020420038150000000040258010010080000100800005006400001200192003820139997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)696b6d6edispatch 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015000039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000050203160332003580000102003920039200392003920039
800242003815000039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000050205160432003580000102003920039200392003920039
800242003815000039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001030050204160532003580000102003920039200392003920039
800242003815000060258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000350203160442003580000102003920039200392003920039
800242003815000039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000050204160442003580000102003920039200392003920039
8002420038150000396080010118000010800005064000020019020038200389996310018800102080000201600002003820038118002110910108000010550650204160322019680000102003920039200392003920039
8002420038150000392580010108000010800005064000020019020038200389996310018800102080000201600002003820038118002110910108000010420650204160332003580000102003920039200392003920039
800242003815000039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001030050205160332003580000102003920039200392003920039
800242003815000039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001000050204160342003580000102003920039200392003920039
800242003815000039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001010050203160432003580000102003920039200392003920039