Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHRUN (4S)

Test 1: uops

Code:

  sqrshrun v0.4h, 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)03181e3f4e51inst 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723030612547251000100010003995121305430373037241432895100010001000303730371110011000173116112629100030383038303830383038
1004303722031242547251000100010003981600301830373037241432895100010001000303730371110011000173116112629100030383038303830383038
100430372210612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372200612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723001032547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
10043037220144612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723062512547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshrun v0.4h, 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): 3.0037

retire (01)cycle (02)03080b18191e3f4e51inst 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)9fa6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000726295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500006361295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722400000726295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500000726295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038302303003830038
10204300372250000082295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830083
10204300372250000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722400000726295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500000536295472510100100100081001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830138300383003830038
102043003722400000251295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286828767101612010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030085300371110021109101010000100000006402162229629010000103003830038300383003830038
1002430037225000012061295472510010101000010100005042771601300183003730037282861028767100102010000201000030037300371110021109101010000100000006402162229667110000103008630038300383003830038
10024300372250000006129547251001910100001010000504277160130018300373003728286328767100102010000201000030037300842110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
1002430037225000012010329547251001010100001010000504277160130018300373003728307328767100102010000201098430037300371110021109101010000100000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqrshrun v0.4h, v8.4s, #3
  sqrshrun v1.4h, v8.4s, #3
  sqrshrun v2.4h, v8.4s, #3
  sqrshrun v3.4h, v8.4s, #3
  sqrshrun v4.4h, v8.4s, #3
  sqrshrun v5.4h, v8.4s, #3
  sqrshrun v6.4h, v8.4s, #3
  sqrshrun v7.4h, 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)030b1e3f51inst 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)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811620036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010010111511801620036800001002004020040200402004020040
80204200391500153025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010010111511801620036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020203200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040

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)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)9fa8accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115004025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100050201516101420036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100050201616151520036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000101050201716111020036080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100050201516131320036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100050201516181320036080000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010017450201416151620036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100050201216141120036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000101050201816141520036080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100050201616151520036080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100050201616141420036080000102004020040200402024420040