Apple M1 Microarchitecture Research by Dougall Johnson

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

SRSHR (vector, 8B)

Test 1: uops

Code:

  srshr v0.8b, v0.8b, #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)031e3f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612547251000100010003981600301830373037241432895100010001000303730371110011000073316222629100030383038303830383038
10043037220612547251000100010003981600301830373037241432895100010001000303730371110011000073316332629100030383038303830383038
10043037236612547251000100010003981600301830373037241432895100010001000303730371110011000073316332629100030383038303830383038
1004303723252612547251000100010003981600301830373037241432895100010001000303730371110011000073316332629100030383038303830383038
10043037230612547251000100010003981600301830373037241432895100010001000303730371110011000073316332629100030383038303830383038
10043037230612547251000100010003981600301830373037241432895100010001000303730371110011000073316332629100030383038303830383038
10043037230612547251000100010003981600301830373037241432895100010001000303730371110011000073316332629100030383038303830383038
100430372218612547251000100010003981600301830373037241432895100010001000303730371110011000073316332629100030383038303830383038
10043037230612547251000100010003981601301830373037241432895100010001000303730371110011000073316332629100030383038303830383038
10043037230612547251008100010003981600301830373037241432895100010001000303730371110011000073316332629100030383038303830383038

Test 2: Latency 1->2

Code:

  srshr v0.8b, v0.8b, #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)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160130018300373003728264172876310255200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
10204300372250000000822954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
102043003722500002640010362954725101001001000010010000500427716013001830037300372826432874510100204100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
102043003722500001500612954725101001001000010010000500427716013001830037300372826432874510100200100002041000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
102043003722500000004412954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071001611296330100001003003830038300383003830038
102043003722500000005362954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038

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)9fa1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000660612954725100101010000101000050427716003001830037300372828632878510010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037224000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229689010000103003830038300383003830038
1002430037224000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037224000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000005362954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722501110598612954725100101010000101000050427851203005430133300842829132876710010201000020100003003730085311002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830085300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037226000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  srshr v0.8b, v8.8b, #3
  srshr v1.8b, v8.8b, #3
  srshr v2.8b, v8.8b, #3
  srshr v3.8b, v8.8b, #3
  srshr v4.8b, v8.8b, #3
  srshr v5.8b, v8.8b, #3
  srshr v6.8b, v8.8b, #3
  srshr v7.8b, v8.8b, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03081e3f51inst 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)9fa0a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391550123025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100022422251281231120045800001002004920049200492004920049
8020420048150006426801161008001610080028500640196020029200492004899769998680128200800382008003820048200491180201100991001008000010000022251281231120046800001002005020050200492004920049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420040150000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050208161072003680000102004020040200402004020040
80024200391500240402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050209161062003680000102004020040200402004020040
80024200391500004025801081080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502010161082003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019801142080839208042220246201932180021109101080000100000050201016992003680000102004020040200402004020040
800242003915600040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020916892003680000102004020040200402004020040
800242003915000040448010710800961080104506408120200202010120039100057100198001020800002080000200922009011800211091010800001000000502091610102003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050208168102003680000102004020040200402004020040
800242003915005704025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001001030502010161082003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050208167102003680000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502010161082003680000102004020040200402004020040