Apple M1 Microarchitecture Research by Dougall Johnson

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

USHLL (4S)

Test 1: uops

Code:

  ushll v0.4s, v0.4h, #3
  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)gpr retires (ef)f5f6f7f8fd
10042037151261168625100010001000264521020182037203715713189510001000100020372037111001100000731161117861000020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100000731161117861000020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100013731161117861000020382038203820382038
100420372006116862510001000100026452102018203720371571318951000100010002037203711100110001073116111786100022520382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100000731161117861000020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100000731161117861000020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100000731161117861000020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000731161117861000020382038203820382038
10042037150164168625100010001000264521020182037203715713189510001000100020372037111001100003731161117861000020382038203820382038
1004203716065168625100010001000264521020182037203715713189510001000100020372037111001100000731161117861000020382038203820382038

Test 2: Latency 1->2

Code:

  ushll v0.4s, v0.4h, #3
  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)030b1e3f4e51inst 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)9fa1a7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550246119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
1020420037155036119675251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
1020420037156006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
1020420037155006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100001007102162219791100001002003820038200382003820038
1020420037156006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
1020420037156006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715503846119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
1020420037155006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
10204200371550061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000004207102162219791100001002003820038200382003820038
1020420037156006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038

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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100252003715018611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640416331978610000102003820038200382003820038
100242003715681611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
1002420037150195821968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640319331978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
100242003715012611968644100231010012101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
100242003715027611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
10024200371550611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  ushll v0.4s, v8.4h, #3
  ushll v1.4s, v8.4h, #3
  ushll v2.4s, v8.4h, #3
  ushll v3.4s, v8.4h, #3
  ushll v4.4s, v8.4h, #3
  ushll v5.4s, v8.4h, #3
  ushll v6.4s, v8.4h, #3
  ushll v7.4s, v8.4h, #3
  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)030b18191e1f3f51inst 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)9fa0a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200381550000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
80204200381550000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
80204200381550000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
80204200381550000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815500000219258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
80204200381550000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000030111511801600200350800001002003920039200392003920039
80204200381550000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003927029200492004920049
80204200381550000029258010810080107100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200912009920039
80204200381550000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
80204200381550000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a18191e1f3f51inst 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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051155000027081258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020141611102003580000102003920039200392003920039
800242003815500000081258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020121612132003580000102003920039200392003920039
8002420038155000012039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020101611122003580000102003920039200392003920039
8002420038155000000101125800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000502012161172003580000102003920039200392003920039
80024200381550000303925800101080000108000050641528120019200382003899963100188001020800002080000200382003811800211091010800001000000502014169102003580000102003920039200392003920039
8002420038155000012039258001010800001080000506407601200192003820038999631001880010208000020800002003820038118002110910108000010000005020121612122003580000102003920039200392003920039
800242003815500000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020121612112003580000102003920039200392003920039
80024200381560020210104258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020121611122003580000102003920039200392003920039
800242003815500000060258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020121614132003580000102003920039200392003920039
800242003815500000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000305020131612132003580000102003920039200392003920039