Apple M1 Microarchitecture Research by Dougall Johnson

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

FADDP (vector, 8H)

Test 1: uops

Code:

  faddp v0.8h, v0.8h, v1.8h
  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
100430372300612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372200612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372300612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110001573116112630100030383038303830383038
100430372300612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372300612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372300612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372200612548251000100810003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372200612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372300612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  faddp v0.8h, v0.8h, v1.8h
  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)031e1f3f4e51inst 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)9facc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826503287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265032874510100200100002002000030037302281110201100991001001000010000710116112963423100001003003830038300383003830038
10204300372250010062954825101001001000010010000500427731313001830037300372826503287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826503287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826503287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826503287451010020010000200200003008530037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826503287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090a0b18191e1f3f4e51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000000010329548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100030274606404164529630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006405165529630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006405164529630010000103003830038300383003830038
10024300372250000000008229548251001010100001010000504277313030018300373003728287328767100102010000202130030037300371110021109101010000100000006405165529630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000306404165529630010000103003830038300383003830038
10024300372250000000007129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006405165529630010000103003830038300383003830038
10024300372250000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006405165429630010000103003830038300383003830038
10024300372240000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006405165529630010000103003830038300383003830038
10024300372250000000008229548251001010100001010000504277313130018300373003728287328767100102010000202000030084300832110021109101010000100000006405165429630010000103003830038300383003830038
10024300372250000000006129530141100631710048141092381428681213023430367303682831234288991105626109822221950303693037081100211091010100001004101932607866895429864110000103027430367303233037330319

Test 3: Latency 1->3

Code:

  faddp v0.8h, v1.8h, v0.8h
  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)031e1f3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225002512954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101251129634100001003003830038300383003830038
102043003722500612954825101171001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430081225480612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307090a0b18191e1f3f4e51inst 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
10024300372250000009061295482510012101000010100006042773130300183003730037282873287671001220100002020000300373003711100211091010100001000010006402162229630010000103003830038300383003830038
100243003722400000000103295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000306402162229630010000103003830038300383003830038
100243003722500000000822954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000101506402162229630010000103003830038300383003830038
1002430037224000000006129548251001010100001010000504277313030018300373008328287328767100102010000202000030037300371110021109101010000100000015006402162229630010000103003830038300383003830038
10024300372250000000061295482510010101000012100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372240000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  faddp v0.8h, v8.8h, v9.8h
  faddp v1.8h, v8.8h, v9.8h
  faddp v2.8h, v8.8h, v9.8h
  faddp v3.8h, v8.8h, v9.8h
  faddp v4.8h, v8.8h, v9.8h
  faddp v5.8h, v8.8h, v9.8h
  faddp v6.8h, v8.8h, v9.8h
  faddp v7.8h, v8.8h, v9.8h
  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)030b191e1f3f51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150000051625801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000000511031611200360800001002004020040200402004020040
802042003915000006225801001018000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040
802042003915000004125801001008000010080000500640788120020200452003999730399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040
8020420039150000041258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000020005110116112003616800001002011620143201172004020040
8020420039150000062258010010080000100800005006400001200202019420140100200399978010020080000200160000200392003911802011009910010080000100420303511011611200360800001002024620199201422019220040
802042003915205540176622580100100800001008000050064000012002020039203009983021101048032420080000200160000200392003911802011009910010080000100420000511011611200360800001002004020040200402004020040
802042003915000004125801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000003511011611200360800001002004020040200402004020040
802042003915000004125801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040
802042003915000008325801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040
8020420039150001204125801001008000010080000500640000120020200392003999730399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a0b18191e1f3a3f51inst 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)5f60696d6edispatch 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)9fa1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000000210040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100000000502016167520036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000050204167520036080000102004020040200402004020040
8002420039150000000006325800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000050207166420036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000050209165420036080000102004020040200402004020040
80024200391500000000051525800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000050201116111020036080000102006220040201002004020040
800242003915000000000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000000005020111611520036080000102004020040200402004020040
80024200391500000000040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100000000502061651120036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000050204165520036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010020009050207163520036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000050206164520036080000102004020040200402004020040