Apple M1 Microarchitecture Research by Dougall Johnson

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

SHL (vector, 4S)

Test 1: uops

Code:

  shl v0.4s, v0.4s, #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)0307080a18191e3a3f4e51inst 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715101000213416862510001000100026452120182037203715713189510001000100020372037111001100000377416441786100020382038203820382038
100420371510100027116862510001000100026452120182037203715713189510001000100020372037111001100000077416441816100020742038208520852086
100420371510111132227316862510121000100026561920182037207315766190710001163100020852073111001100000077416441786100020382038203820382038
100420371610100027116862510001000100026452120182084203715713191411521000100020372037111001100000099537541816100020382038203820382038
1004203716101000211316862510001000100026452120182037203715713189510001000100020372037111001100000077416441786100020382038203820382038
100420371610100027116862510001000100026452120182037203715713189510001000100020372037111001100001077416441786100020382038203820382038
100420371610100027116862510001000100026452120182037203715713189510001000100020372037111001100000077416441786100020382038203820382038
100420371510100027116862510001000100026452120182037203715713189510001000100020372037111001100000077416441786100020382038203820382038
100420371510100027116862510001000100026452120182037203715713189510001000100020372037111001100000077416441786100020382038203820382038
100420371610100027116862510001000100026452120182037203715713189510001000100020372037111001100000077516441786100020382038203820382038

Test 2: Latency 1->2

Code:

  shl v0.4s, v0.4s, #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)030b18191e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000360611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000030611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000300611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150040210611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006403162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000816402162219786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100001626402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000156402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000126402162219786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001004006402162219786010000102003820038200382003820038
100242003715000224196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001001006402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844322187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001001066402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  shl v0.4s, v8.4s, #3
  shl v1.4s, v8.4s, #3
  shl v2.4s, v8.4s, #3
  shl v3.4s, v8.4s, #3
  shl v4.4s, v8.4s, #3
  shl v5.4s, v8.4s, #3
  shl v6.4s, v8.4s, #3
  shl v7.4s, v8.4s, #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)031e3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151182161220035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010001511151181161220035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151182162220035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161220035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001002011151182162220035800001002003920039200392003920039
8020420038150071258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100013511151182162220035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001001311151181162220035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010031211151182161220035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010009011151182162220035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151182162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100050200716352003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100050200316352003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001038050200316352003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001080502003163132003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100050200616352003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000101650200616532003580000102003920039200392003920039
8002420038150393925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100050200316652003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100050200616532003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019320038200389996310018800102080000208000020038200381180021109101080000101350200516532003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100050200416772003580000102003920039200392003920039