Apple M1 Microarchitecture Research by Dougall Johnson

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

CMHI (register, 8B)

Test 1: uops

Code:

  cmhi v0.8b, v0.8b, v1.8b
  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)03081e3f4e51inst 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
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073216111787100020382038203820382038
10042037150061168725100010001000264680201820372037157231895100010002000203720371110011000013273116111787100020382038203820382038
1004203715012611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715021611687251000100010002646802018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506611687251000100010002646802018203720371572318951000100020002037203711100110002073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmhi v0.8b, v0.8b, v1.8b
  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)0318191e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038
10204200371500001326119687251010010010000100100005002847680020018200372003718422271874510100200100002002000020037200371110201100991001001000010000371011611197910100001002003820038200382003820038
102042003715000001031968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000010391968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001371011611197910100001002003820038200382003820038
102042003714900003151968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000001451968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038
10204200371500000821968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000371011611197910100001002003820038200382003820038

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)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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000479196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100640316331978510000102003820038200382003820038
1002420037150013261196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100640316331978510000102003820038200382003820038
100242003715000191196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100640316331978510000102003820038200382003820038
100242003715000340196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100640316331978510000102003820038200382003820038
100242003715000617196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100640316331978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100640316331978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmhi v0.8b, v1.8b, v0.8b
  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)03080b1f3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102161119791100001002003820038200382003820038
102042003714900061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000500196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007402161119791100001002003820038200382003820038
1020420037150000103196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500010861196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000107101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fa7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000770196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038
10024200371500061196872510022101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmhi v0.8b, v8.8b, v9.8b
  cmhi v1.8b, v8.8b, v9.8b
  cmhi v2.8b, v8.8b, v9.8b
  cmhi v3.8b, v8.8b, v9.8b
  cmhi v4.8b, v8.8b, v9.8b
  cmhi v5.8b, v8.8b, v9.8b
  cmhi v6.8b, v8.8b, v9.8b
  cmhi v7.8b, v8.8b, v9.8b
  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)033f51inst 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)9fa8cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051103162220035800001002003920039200392003920039
802042003815040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051102162320035800001002003920039200392003920039
802042003815040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003814982258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038518020110099100100800001000051102162220035800001002003920039200392003920039
8020420038150705258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815040258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001001051102162220035800001002003920039200392003920039
802042003815040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038418020110099100100800001000051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b191e3f51inst 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)5f60696d6edispatch 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)9fc5branch mispredict (cb)cfd2d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020071600057200350080000102003920039200392003920039
800242003815000573925800101080000108000050640000002001920038200389996310018800102080000201602642003820038118002110910108000010005020051600077200350080000102003920039200392003920039
800242003815000076725800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020071600077200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020071600075200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020071600077200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020071600075200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020071600077200350080000102003920039200392003920039
800242003815000017625800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005037051600057200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000002001920038200389994310018800102080000201600002003820038118002110910108000010005020071600075200350580000102003920039200392003920039
80024200381500003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020051600057200350080000102003920039200392003920039