Apple M1 Microarchitecture Research by Dougall Johnson

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

RADDHN (4S)

Test 1: uops

Code:

  raddhn v0.4h, v0.4s, v1.4s
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073416332630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073316332630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110001373316332630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073316332630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073316332630100030383038303830383038
10043037232286125482510001000100039831303018303730372415328951000100020003037303711100110000073316332630100030383038303830383038
1004303723426125482510001000100039831303018303730372415328951000100020003037303711100110000073316332630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073316332630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073316332630100030383038303830383038
1004303723486125482510001000100039831303018303730372415328951000100020003037303711100110000073316332630100030383038303830383038

Test 2: Latency 1->2

Code:

  raddhn v0.4h, v0.4s, v1.4s
  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)0309191e3f4e51inst 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)9fa1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225001282295482510100100100001001000050042773131300183003730037282650328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282650328745101002001000020020000300373008511102011009910010010000100213071011611296340100001003003830086300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282650328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225001261295482510100100100001001000050042773130300183003730037282650328745101002021000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372240012124295482510100100100001001000050042773131300183003730037282650328745101002001000020020000300373003711102011009910010010000100013071011611296340100001003003830038300383003830038
1020430037225000296295482510100100100001001000050042773130300183003730084282650328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773131300183003730037282650328745102512001000020020000300373003711102011009910010010000100000074111611296340100001003003830038300383003830038
1020430037225000189295482510100100100001001000050042773131300183003730037282650328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225000429295482510100100100001001000050042773131300183003730037282650328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225000429295482510100100100001001000050042773131300183003730037282650328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003726400000061295482510010101000010100005042773131301623003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300863008630038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722400000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000027061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630110000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722510000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000002021295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  raddhn v0.4h, v1.4s, v0.4s
  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)0304080b191e1f3f4e51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd6e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372251000007129548251010010010000100100005004277313130018300373003728272628741101002001000820020016300373003711102011009910010010000100100111718162964700100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728272728741101002001000820020016300373003711102011009910010010000100109111717162964705100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728272628741101002001000820020016300373003711102011009910010010000100500111717162964700100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728272628740101002001000820020016300373003711102011009910010010000100000111718422964600100001003003830038300383003830038
10204300372240000006129548251010010010000100100005004277313130018300373003728272728741101002001000820020016300373003711102011009910010010000100000111718162964600100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728272628741101002001000820020016300373003711102011009910010010000100000111717162964600100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728272628741101002001000820020016300373003711102011009910010010000100100111718162964700100001003003830038300383003830038
102043003722500000072629548251010010010000100100005004277313130018300373003728272728740102502001000820020016300373003711102011009910010010000100000111717162964600100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313130018300373003728272728741101002001000820020016300373003711102011009910010010000100000111718162964600100001003003830038300383003830038
10204300372240000006129548251010010010000100100005004277313130018300373003728272628741101002001000820020016300373003711102011009910010010000100000111717162964700100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030a0b191e3f4e51inst 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)9fa8a9acc5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010003006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010502829006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010100006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300822828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010500006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000101045006402162229630010000103003830038300383003830038
100243003722500001472954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  raddhn v0.4h, v8.4s, v9.4s
  raddhn v1.4h, v8.4s, v9.4s
  raddhn v2.4h, v8.4s, v9.4s
  raddhn v3.4h, v8.4s, v9.4s
  raddhn v4.4h, v8.4s, v9.4s
  raddhn v5.4h, v8.4s, v9.4s
  raddhn v6.4h, v8.4s, v9.4s
  raddhn v7.4h, v8.4s, v9.4s
  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)031e1f3f51inst 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)9fa8accfd2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915000150258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100005110021611200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100135110012911200780800001002004020098200912004020040
8020420039150026441258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100005110021621200360800001002014320040201922004020040
80204201401500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100005110011611200360800001002010220040200402004020040
80204200391500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100305110011611200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100005110011611200360800001002004020040200402004020040
802042003915000455258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100005110011611200360800001002004020040200402004020040
802042003915000190258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100005110011611200360800001002004020040200402004020040
8020420039150001502580100100800001008000050064000020020200392010299737999780225200800002001600002003920039118020110099100100800001001351100116112003617800001002004020040200912004020040
802042003915012083258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100005110011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a0b191e3a3f51inst 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)9fa8cfd0d5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391501100024725800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100502401116014152003680000102004020040200402004020040
80024200391501100024725800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100502401416014162003680000102004020040200402004020040
80024200391501100024725800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100502401516014162003680000102004020040200402004020040
8002420039150110002472580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010050240151601792003680000102004020040200402004020040
800242003915011000247258001010800001080000506400001200202003920039999621100198001020800002016000020039200391180021109101080000100502401316013172003680000102004020040200402004020040
800242003915011000261725800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100502401616016162003680000102004020040200402004020040
80024200391501100024725800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100502401516013162003680000102004020040200402004020040
8002420039150110002472580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010050240151601692003680000102004020040200402004020040
80024200391501100024725800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100502401516014162003680000102004020040200402004020040
80024200391501100024725800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100502401816013152003680000102004020040200402004020040