Apple M1 Microarchitecture Research by Dougall Johnson

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

CMLT (zero, 4S)

Test 1: uops

Code:

  cmlt v0.4s, v0.4s, #0
  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
1004203715015616862510001000100026452102018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000373116111853100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmlt v0.4s, v0.4s, #0
  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)03070a1e3f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715011061196862510100100100001001000050028475210200182003720037184286187411010020010008200100082003720037111020110099100100100001000011171811611198040100001002003820038200382003820038
102042003715011061196862510100100100001001000050028475211200182003720037184286187411010020010008200100082003720037111020110099100100100001000011171711611198050100001002003820038200382003820038
102042003715011061196862510100100100001001000050028475210200182003720037184286187411010020010008200100082003720037111020110099100100100001000011171711611198040100001002003820038200382003820038
102042003715011061196862510100100100001001000050028475210200182003720037184287187401010020010008200100082003720037111020110099100100100001000010071021622197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
1020420037149000189196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
1020420037150000251196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
1020420037150003061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071021622197910100001002003820038200382003820075

1000 unrolls and 10 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)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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000611968625100101010012101000060284752120018200372003718443318767100102010168201000020037200371110021109101010000100203949640516341978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640416431978610000102003820038200382003820038
1002420037150001241968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000104002063640316341978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100009640416441978610000102003820038200382003820038
100242003715000103196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000183640316441978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120065200372003718443318767100102010000201000020037200371110021109101010000100006640316441978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006640416341978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640416431978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000018640416441978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640316341978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmlt v0.4s, v8.4s, #0
  cmlt v1.4s, v8.4s, #0
  cmlt v2.4s, v8.4s, #0
  cmlt v3.4s, v8.4s, #0
  cmlt v4.4s, v8.4s, #0
  cmlt v5.4s, v8.4s, #0
  cmlt v6.4s, v8.4s, #0
  cmlt v7.4s, v8.4s, #0
  movi v8.16b, 9

(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)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)9facc5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039
8020420038150012292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039
80204200381490029258010810080008100800205006401321200192003820038997706998980120200800322008003220113201011180201100991001008000010012611151181620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039
80204200381500322625801081008000810080020500640132020019200382003899770699898012020080032200800322003820038118020110099100100800001001511151181620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100611151181620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132020019200382003899770699898012020080032200800322003820038118020110099100100800001001511151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010014111151181620035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3a3f51inst 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)6061696d6edispatch 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)9fa0a1a6a8acc2cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000000000392580010108000010800005064000010200192003820038999631001880010208000020800002003820038118002110910108000010000000502000616562003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000502000616772003580000102003920039200392003920039
80024200381500000001200392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000502000516642003580000102003920039200392003920039
80024200381500000000006025800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000540502000416452003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000502000616562003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000502000516662003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000010200192003820038999631001880010208000020800002003820038118002110910108000010000000502000516552003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400000020023200382003899963100188001020800002080000200382003811800211091010800001000001410502000616552003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192008820038999631001880010208000020800002003820038118002110910108000010000000502000616662003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000502000516552003580000102003920039200392003920039