Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTNS (vector, 2D)

Test 1: uops

Code:

  fcvtns v0.2d, v0.2d
  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
1004303723010325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372436125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372308425472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372408225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtns v0.2d, v0.2d
  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)03081e3f4e51inst 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)9fa7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000137101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000107101161129633100001003003830038300383003830038
102043003723300612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010002407101161129633100001003003830038300383003830038
102043003722500892954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038

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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000360612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006404164429629110000103003830038301803003830038
10024300372250000150612954725100101010000101000050427716003001830037300372828632876710010221000020100003003730037111002110910101000010000006404164429629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006614164429629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163429629010000103003830038300383003830038
1002430037225000000612952925100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403164429629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403164329629010000103003830038300383003830038
1002430037225000045264612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403164329629010000103003830038300383003830038
10024300372250000270612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006404164329629010000103003830038300383003830038
1002430037225000000822954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006404164329629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006404164429629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtns v0.2d, v8.2d
  fcvtns v1.2d, v8.2d
  fcvtns v2.2d, v8.2d
  fcvtns v3.2d, v8.2d
  fcvtns v4.2d, v8.2d
  fcvtns v5.2d, v8.2d
  fcvtns v6.2d, v8.2d
  fcvtns v7.2d, v8.2d
  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)0318191e1f3f51inst 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)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
802042003915500009725801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039161000069525801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039155001203025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
802042003915500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010003111511801620036800001002004020040200402004020040
802042003915500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010030111511801620036800001002004020040200402004020040
802042003915600003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010010111511802920036800001002004020040200402004020040
8020420039161000021225801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010003111516701620036800001002004020040200402019820040
8020420039161006031025801081008000810080020500640132120020200392011799776999080226200800322008003220039200921180201100991001008000010000111511801620036800001002004020040200402004020040
802042003916100005825801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e1f3a3f51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501550000000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000000502017166132003680000102004020040200402004020040
8002420039155000000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000050207166132003680000102004020040200402004020040
8002420039155000121568802306738020710801951080210506416361200832003920039999631001980010208009920801052009220091218002110910108000010204201015050565395172007580000102018820183201352013620195
80024201021582102119888061258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010003000502015165152003680000102004020040200402004020040
80024200391550000000061258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502015165152003680000102004020040200402004020040
800242003915600000000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100029000502016165152003680000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000100050205165152003680000102004020040200402004020040
80024200391550000000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010001000502015161342003680000102004020040200402004020040
800242003915500000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100002475050204161542003680000102004020040200402004020040
80024200391560000000082258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010003000502015165152003680000102004020040200402004020040