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, 2S)

Test 1: uops

Code:

  srshr v0.2s, v0.2s, #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)031e1f3f4e51inst 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
1004303722001492547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372200612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303722001492547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372200612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372200612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372200612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372200612547251000100010003981600301830373037241432895100010001000303730371110011000073116112682100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372200612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  srshr v0.2s, v0.2s, #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)0318191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250021612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037224003612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225009942954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250042612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500144612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000019500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000005362954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629310000103027330369303723037030262
100243032122801175110179211452949313510072141004815109007742851951302343031830322283093328881109142411088241064930274303708110021109101010000102200001693027732643229842310000103003830086300853013230086
100243008422510000000612954725100101010000101000050427716013001830037300372828632876710010201000020106553003730037111002110910101000010003010006402162229629010000103003830038302283003830038
100243003722500000510001032954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006682162229629010000103003830038300383003830038
100243003722500000000612954725100181410000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000600612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000001452954725100301110000101015050427716003001830037300372828632876710010201000020100003003730037111002110910101000010020010007272162229701010000103003830038300383003830038
100243003722500000300612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  srshr v0.2s, v8.2s, #3
  srshr v1.2s, v8.2s, #3
  srshr v2.2s, v8.2s, #3
  srshr v3.2s, v8.2s, #3
  srshr v4.2s, v8.2s, #3
  srshr v5.2s, v8.2s, #3
  srshr v6.2s, v8.2s, #3
  srshr v7.2s, v8.2s, #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)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)cdcfd6dde0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039150489418258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160200360800001002004020040200402004020040
8020420039150630258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160200360800001002004020040200402004020040
80204200391502130258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160200360800001002004020040200402004020040
80204200391502430258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160200360800001002004020040200402004020040
80204200391502130258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160200360800001002004020040200402004020040
802042003915047430258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160200360800001002004020040200402004020040

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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915039402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100502081616162003680000102004020040200402004020040
80024200391509402580010108009810800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100502016166162003680000102004020040200402004020040
800242010015004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001005020161616162003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010050206166162003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100502016166162003680000102004020040200402004020040
8002420039150297402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100502016166162003680000102004020040200402004020040
8002420039150387402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100502016165162003680000102004020040200402004020040
8002420039150940258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010050206166162003680000102004020040200402004020040
80024200391509402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100502061613162003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010050206166162003680000102004020040200402004020040