Apple M1 Microarchitecture Research by Dougall Johnson

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

SRSHL (vector, 16B)

Test 1: uops

Code:

  srshl v0.16b, v0.16b, v1.16b
  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)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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723361254825100010001000398313301830373037241532895100010002000303730371110011000073316332630100030383038303830383038
1004303723061254825100010001000398313301830373037241532895100010002000303730371110011000073316332630100030383038303830383038
10043037236661254825100010001000398313301830373037241532895100010002000303730371110011000073216332630100030383038303830383038
1004303723061254825100010001000398313301830373037241532895100010002000303730371110011000073316332630100030383038303830383038
1004303722061254825100010001000398313301830373037241532895100010002000303730371110011000073316332630100030383038303830383038
10043037232761254825100010001000398313301830373037241532895100011612000303730371110011000073316232630100030383038303830383038
10043037231861254825100010001000398313301830373037241532895100010002000303730371110011000073316332659100030383038303830383038
1004303722061254825100010001000398313301830373037241532895100010002000303730371110011000073316332630100030383038303830383038
1004303723061254825100010001000398313301830373037241532895100010002000303730371110011000073316332630100030383038303830383038
1004303723061254825100010001000398313301830373037241532895100010002000303730371110011000073316332630100030383038303830383038

Test 2: Latency 1->2

Code:

  srshl v0.16b, v0.16b, v1.16b
  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)031e3a3f4e51inst 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)9fa0a8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000138007101161129634100001003003830038300383008530038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250010329548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100002874207101161129704100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000141007101161129634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100009007101161129634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100006007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004280027130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000138007101161129634100001003003830038300853003830038
102043003722400612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000129007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa0a1a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830086300383003830038
100243003722500015061295482510010101000010100005042773131300183018030037282873287671001020100002020000300373003711100211091010100001000000006403242229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500018061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300223003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730228282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  srshl v0.16b, v1.16b, v0.16b
  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)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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000040734333222967014100001003032230329303253032530220
1020430368227111785861641082948516210184127100321361089469942854501302343037230376282903428763110302241099622421992302753037281102011009910010010000100004010194480085239222298865100001003037430421303753036930369
10204303732270077933616458929494164101771391005613811043704428684913027030357303232828834288751102720211164224223123036830369711020110099100100100001000430121708340872273362974134100001003037530141303723036930370
102043022622800578046166732954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000030071021622296340100001003003830038300383003830038
10204300372250000005362954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000870071021622296340100001003003830038300383003830038
1020430037225000030612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
102043003722500000073629548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000690171021622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000420071021622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003721102011009910010010000100000000120071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst 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)9fa1a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250822954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010200000640216222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000015300640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000013800640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042827411300183003730037282873287671001020100002020000300373003711100211091010100001001415000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773131300183003730081282873287671001020100002020000300373003711100211091010100001000012900640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000015900640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000011400640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  srshl v0.16b, v8.16b, v9.16b
  srshl v1.16b, v8.16b, v9.16b
  srshl v2.16b, v8.16b, v9.16b
  srshl v3.16b, v8.16b, v9.16b
  srshl v4.16b, v8.16b, v9.16b
  srshl v5.16b, v8.16b, v9.16b
  srshl v6.16b, v8.16b, v9.16b
  srshl v7.16b, v8.16b, v9.16b
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)0308090b18191e1f3a3f51inst 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)9fa1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150000000003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000025000111511801600200360800001002004020040200402004020040
8020420039150000000003025801081008000810080129500640132020059200392003999776999080120200800322001600642003920039118020110099100100800001000023030111511801600200360800001002004020040200402004020040
802042003915000000000302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100002030111511801600200360800001002004020040200402004020040
8020420039150000000003025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000043720111511801600200360800001002004020040200402004020040
802042003915000000000302580108100800081008002050064013202002020039200399973399978010020080000200160000200392003911802011009910010080000100000000000511011611200360800001002004020040200402004020040
802042003915000000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000000000511021611200360800001002004020040200402004020040
802042003915000000600412580100100800001008000050064000012002020091200399973399978010020080000200160000200392003911802011009910010080000100000000000511011611200360800001002004020040200402004020040
802042003915000000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000030000511011611200360800001002004020040200402004020040
802042003915000000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000000000511011611200360800001002004020040200402004020040
802042003915000000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000000511011611200360800001002004020040200402004020040

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)9fa8acc2cfd0d5d6d9ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000102330502009160151220036080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001028005020012160121520036080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001014305020011160151220036080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001059905020015164151520036080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001033005020010160161320036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100005020015160161320036080000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001049005020017160161520036080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100305020012160161320036080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020014160141020036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016028020039200391180021109101080000103005020015160181420036080000102004020040200402004020040