Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHLU (vector, 8H)

Test 1: uops

Code:

  sqshlu v0.8h, v0.8h, #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)03081e3f4e51inst 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)a0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
10042037150156116862510001000100026452120182037203715713189510001000100020372037111001100002000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203716096116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100002000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshlu v0.8h, v0.8h, #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)03080a1e3f4e51inst 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
1020420037150002761196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001001071011611197910100001002003820038200382003820038
1020420037150000103196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001001071011611197910100001002003820038200382003820038
102042003715000061196752510100100100001001000052228475211200182003720037184213187451010020010000200100002003720084111020110099100100100001000071012411197910100001002003820038200382003820038
102042003715001061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150001261196862510100100100001001000050028475211200182003720037184293187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500048103196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150001282196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150001582196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150006061196862510100100100001001000050028475211200182003720037184323187451010020010000204100002003720037111020110099100100100001000071011621197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030708090a0b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000039006119686251001010100001010000502847521120018020037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715010000001500385719686251001010100001010000502847521120018020037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000000015619686251001010100001210000602847521120018020037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000024006119686251001210100001210000602847521120018020037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820085
100242003715000000000006119686251001010100001010000502847521120018020037200371844331876710012201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000000000006119686251001010100001010000502847521120018020037200371844331876710010201000020100002003720037111002110910101000010000000606402162219786010000102003820038200382003820038
100242003715000000000006119686251001010100001010000502847521120018020037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000000003006119686251001010100001010000502847521120018020037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000000000006119686251001010100001010000502847521120018020037201781844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000294006119686251001010100001010000502847521120018020037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshlu v0.8h, v8.8h, #3
  sqshlu v1.8h, v8.8h, #3
  sqshlu v2.8h, v8.8h, #3
  sqshlu v3.8h, v8.8h, #3
  sqshlu v4.8h, v8.8h, #3
  sqshlu v5.8h, v8.8h, #3
  sqshlu v6.8h, v8.8h, #3
  sqshlu v7.8h, v8.8h, #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)030708090b18191e1f3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150000000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511811600200350800001002003920039200392003920039
80204200381500000001809425801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
8020420038150000000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
8020420038150000000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
8020420038150000000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511811600200350800001002003920039200392003920039
80204200381500000001502925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
80204200381500000000029258010810080008100800205006401320200192003820038997723998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
8020420038150000000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801640200350800001002003920039200392003920039
80204200381500000003002925801081008000810080020500640132020019200382003899776998980120200800322008003220089200381180201100991001008000010000000000111511841600200350800001002003920039200392003920039
8020420038150000000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511841644200350800001002003920039200392003920039

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)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)9facc5cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050200161620172003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000502008168172003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020018161892003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000502008167172003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000502007161782003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999681001880010208000020800002003820038118002110910108000010005020017371782003580000102003920039200392003920039
800242003815003242580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050200171617172003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020018167182003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020014168172003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000502006168172003580000102003920039200392003920039