Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHL (vector, 16B)

Test 1: uops

Code:

  uqshl 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)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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100073216221787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100073216221787100020382038203820382038
1004203715336116872510001000100026468020182037203715723189510001000200020372037111001100073216221787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100073216221787100020382038203820382038
1004203715186116872510001000100026468020182037203715723189510001000200020372037111001100073216221787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100073216221787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100073216221787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100073216221787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100073216221787100020382038203820382038
1004203715014516872510001000100026468020182037203715723189510001000200020372037111001100073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl 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)03080b18191e1f3f4e51inst 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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000120611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002022720277202782023220228
1020420267151015469935225031964210110119136100601311076063228527721201622027620277184252218843108982141066221821334202282027961102011009910010010000100020079632808269221993132100001002022720275202772022720230
10204202741510166816440297919632137102141191007213410885694285409512019820321203241844328188321105022210993222220002032320180711020110099100100100001002002101332828365132002424100001002032620323203262032820325
102042032115211658192642959196211401021513010060134109126772847680120234202772032518444341883511045220108272102165020323203577110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071021611197910100001002003820038200382003820038
10204200371500000810611968725101001001000010410000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000015071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038

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)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
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640516651978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640616661978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640616771978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010400640716671978510000102003820038200382003820038
1002420037150240611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640716671978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640716761978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640716671978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640516771978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640616751978510000102003820038200382003820038
1002420037150150611968725100101010000101015250284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640716771978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uqshl 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)0307080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
10204200371500000000061196872510100104100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000008209071021622197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000230108071021622197910100001002003820038200382003820038
10204200371501000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000005400071021622197910100001002003820038200382003820038
10204200371500000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000018071021622197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000003071021622197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000003071021622197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021622197910100001002003820038200382003820038
102042003715000000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000111071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715002166119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767101622010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500025119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001006006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420083150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500034619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uqshl v0.16b, v8.16b, v9.16b
  uqshl v1.16b, v8.16b, v9.16b
  uqshl v2.16b, v8.16b, v9.16b
  uqshl v3.16b, v8.16b, v9.16b
  uqshl v4.16b, v8.16b, v9.16b
  uqshl v5.16b, v8.16b, v9.16b
  uqshl v6.16b, v8.16b, v9.16b
  uqshl 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010030351105164320035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200981180201100991001008000010026951103163420035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010019051104164420035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051104164420035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051103164320035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010034351104164320035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051104164420035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051104164320035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010030051104164320035800001002003920039200392003920039
80204200381509402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100402751104164420035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3a3f51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150000392580010108000010800005064000001200192003820038999631007380010208000020160000200382003811800211091010800001000005020216222003580000102003920039200392003920039
8002420038150000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000015020216222003580000102003920039200392003920039
8002420038150000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000005020216222003580000102003920039200392003920039
8002420038150000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000005020216222003580000102003920039200392003920039
8002420038150000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000005020216222003580000102003920039200392003920039
800242003815001203925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010003305020216222003580000102003920039200392003920039
80024200381500002292580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000605020216222003580000102003920039200392003920039
8002420038149000392580010108000010800005064000001200192003820038999631001880010208000020160000200382019011800211091010800001000005020216222003580000102003920039200392003920039
8002420038150000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001040005020216222003580000102003920039200392003920039
8002420038150000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000005020216222003580000102003920039200392003920039