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, 16B)

Test 1: uops

Code:

  cmhs 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)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)a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000100073216221787100020382038203820382038
10042037159611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037160611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000015773216221787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037153611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000050073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmhs 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)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)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)9fa0a8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500661196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000278071011611197910100001002003820038200382003820038
10204200371500010231968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000000710116111979124100001002003820038200382003820038
102042008415000576196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100200071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420217150061196872510010101000010100005028476800200182003720037184443187861001020100002020000200372003711100211091010100001003640216221978510000102003820038200382003820038
10024200371500251196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182008420037184443187671001020100002020000200372003711100211091010100001010640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150661196872510010101000010100005028476801200182003720037184443187671001020100002020000200842003711100211091010100001020640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmhs 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)031e3a3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000166196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001001071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001001371011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000371011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080a0b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000100006402162219785010000102008520038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200842003718448318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000000010319687491001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000100006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmhs v0.16b, v8.16b, v9.16b
  cmhs v1.16b, v8.16b, v9.16b
  cmhs v2.16b, v8.16b, v9.16b
  cmhs v3.16b, v8.16b, v9.16b
  cmhs v4.16b, v8.16b, v9.16b
  cmhs v5.16b, v8.16b, v9.16b
  cmhs v6.16b, v8.16b, v9.16b
  cmhs 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)030b1e3f51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915000402580100100800001008000050064000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000051103162220035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382008999730399968010020080000200160000200382003811802011009910010080000100000051102162220035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000051103162220035800001002003920039200392003920039
8020420038150002562580100100800001008000050064000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000051102162220035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000051102162220035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000051102162220035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382003899730399968010020080288200160000200382003811802011009910010080000100000051102162220035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000151102162220035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000051102162320035800001002003920039200392003920039
802042003815000612580100100800001008000050064000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308191e1f3a3f51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471500000039258001010800001080000506400001200190200382003899960310018800102080000201600002003820038118002110910108000010000502010167102003580000102003920039200392003920039
8002420038150000001042580010108000010800005064000012001902003820038999603100188001220800002016000020038200381180021109101080000100005020111612112003580000102003920039200392003920039
80024200381500000039258001010800001080000506400001200190200382003899960310018800122080392201600002003820038118002110910108000010000502091614122003580000102003920039200392003920039
80024200381500000039258001010800001080000506400001200190200382003899960310018800102080000201600002003820038118002110910108000010000502071612112003580000102003920039200392003920039
8002420038150000003925800101080000108000050640000120019020038200389996031001880012208000020160000200382003811800211091010800001000050206167112003580000102003920039200392003920039
8002420038150000880392580010108000010800005064000012001902003820038999603100188001220800002016019620038200381180021109101080000100005020121612112003580000102003920039200392003920039
800242003815000900392580010108000010800005064000002001902003820038999603100188001220800002016000020038200381180021109101080000100005020101611102003580000102003920039200392003920039
80024200381500012008125800101080000108000050640000120019020038200389996031001880010208000020160000200382003811800211091010800001001050206169102003580000102003920039200392003920039
800242003815000000392580010108000010800005664077012001902003820038999603100188001020800002016000020038200381180021109101080000100005020131611112003580000102003920039200392003920039
800242003815000000622580010108000010800005064000012001902003820038999603100188001020800002016000020038200381180021109101080000100005020101611112003580000102003920039200392003920039