Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHL (immediate, scalar, D)

Test 1: uops

Code:

  uqshl d0, d0, #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)0308093f4e51inst 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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111784100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500103168625100010001000264521120182037203715713189510001000100020372037111001100001073116111786100020382038203820382038
100420371500156168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500407168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl d0, d0, #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)030b1e1f3a3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000245196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011621197910100001002003820038200382003820038
10204200371500000124196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011621197910100001002003820038200382003820038
10204200371500000170196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500000126196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187631010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500900575196862510100100100001001015250028475211200182003720037184213187451010020010000202100002003720037111020110099100100100001000371011621197910100001002003820038200382003820038
10204200371500000126196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001001071011621197910100001002003820038200382003820038
1020420037150012001031968625101001001000010010000500284752112001820037200371842131874510100208100002001000020037200371110201100991001001000010001571011611197910100001002003820038200382003820038
102042003715000001891968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000710116211979113100001002003820038200382003820038
1020420037150000084196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

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)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)9fa7a8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119686251001010100001010000502847521002001820037200371844331876710010201000020100002003720037111002110910101000010000064002162219786010000102003820038200382003820038
1002420037150008219686251001010100001010000502847521102001820037200371844331876710010201000020100002003720037111002110910101000010000064002162219786010000102003820038200382003820038
1002420037150006119686251001010100001010000502847521002001820037200371844331876710010201000020100002003720037111002110910101000010000064002162219786010000102003820038200382003820038
10024200371500010319686251001010100001010000502847521102001820037200371844331876710010201000020100002003720037111002110910101000010000064002162219786010000102003820038200382003820038
10024200371500083719686251001010100001010000502847521002001820037200371844331876710010201000020100002003720037111002110910101000010000064002162219786210000102003820038200382003820038
10024200371501012419686251001010100001010000502848785002001820037200371844331876710010201000020100002003720037111002110910101000010000064002162219786010000102003820038200382003820038
1002420037150068219686251001010100001010000502847521002001820037200371844331876710010201000020100002003720037111002110910101000010000064002162219786010000102003820038200382003820038
10024200371500047619686251001010100001010000502847521002001820037200371844331876710010201000020100002003720037111002110910101000010000064002162219786010000102003820038200382003820038
1002420037150098219686251001010100001010000502847521002001820037200371844331876710010201000020100002003720037111002110910101000010010064002162219786010000102003820038200382003820038
1002420037150006119686251001010100001010000502847521102001820037200371844331876710010201000020100002003720037111002110910101000010000064002162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uqshl d0, d8, #3
  uqshl d1, d8, #3
  uqshl d2, d8, #3
  uqshl d3, d8, #3
  uqshl d4, d8, #3
  uqshl d5, d8, #3
  uqshl d6, d8, #3
  uqshl d7, d8, #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)696d6edispatch 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)9fc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150012725801081008000810080020500640132200192003820038997706998980120200800322008003220038200381180201100991001008000010011151184162320035800001002003920039201412003920039
8020420038150066425801081008000810080020500640132200192003820038997706998980120200800322008013520038201102180201100991001008000010011151182163320035800001002003920039200392003920039
8020420038150014125801081008000810080020500640132200192003820038997706998980120200800322008003220086200381180201100991001008000010011151183163320035800001002003920039200392003920039
8020420038150019925801081008000810080020500640132200192003820038997706998980120200800322008003220038200381180201100991001008000010011151183163320035800001002003920039200392003920039
802042003815002925801081008000810080020500640132200192003820038997706998980120200800322008003220038200381180201100991001008000010011151183163320035800001002003920039200392003920039
802042003815002925801081008000810080020500640132200192003820038997706998980120200800322008003220038200381180201100991001008000010011151183162320035800001002003920039200392003920039
802042003815002925801081008000810080020500640132200192003820038997706998980120200800322008003220038200381180201100991001008000010011151183162320035800001002003920039200392003920039
802042003815002925801081008000810080020500640132200192003820038997706998980120200800322008003220038200381180201100991001008000010011151183162320035800001002003920039200392003920039
802042003815002925801081008000810080020500640132200192003820038997706998980120200800322008003220038200381180201100991001008000010011151183163320035800001002003920039200392003920039
8020420038150122925801081008000810080020500640132200192003820038997706998980120200800322008003220038200381180201100991001008000010011151183163220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a0b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000000039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201161112003580000102003920039200392003920039
800242003815000000000165258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201161112003580000102003920039200392003920039
8002420038150000000003925800101080000108000050640000200192003820038999631001880010208000020800002008720038118002110910108000010000000005020116512003580000102003920039200392003920039
8002520038150000000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020116912003580000102003920039200392003920039
80024200381500000000039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000103200306051071661022024580000102003920039200392003920039
800242003815000000000416258001010800001080000506400002001920038200389996810018800102080000208000020038200381180021109101080000100000000050201161512003580000102003920039200392003920039
800242003815000000000123258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201161412003580000102003920039200392003920039
800242003814900000000210258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201161312003580000102003920039200392003920039
8002420038150000000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020116612003580000102003920039200392003920039
80024200381500000000039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201161412003580000102003920039200392003920039