Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZS (scalar, fixed-point, S to S)

Test 1: uops

Code:

  fcvtzs s0, s0, #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)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
100430372308825472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372396125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037231210325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzs s0, s0, #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)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)inst ldst (9b)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723301702954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000001000007102161129633100001003003830038300383003830038
102043003723301892954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000001000007101161129633100001003003830038300383003830038
102043003723302112954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000001000007101161129633100001003003830038300383003830038
10204300372320842954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000001000007101161129633100001003003830038300383003830038
10204300372330842954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000001000007101161129633100001003003830038300383003830038
102043003723305432954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000001001007101161129633100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000001000007101161129633100001003003830038300383003830038
102043003723201702954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000001000007101161129633100001003003830038300383003830038
102043003723302002954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000001000007101161129633100001003003830038300383003830038
102043003723305402954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000001000007101161129633100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa8a9acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723300612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010490000640616222962910000103003830038300383003830038
1002430037232007262954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010520000640216222962910000103003830038300383003830038
1002430037233006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000105301200640216222962910000103003830038300383003830085
100243003723300612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010440000640216222962910000103003830038300383003830038
100243003723315061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372320061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001030000640216222962910000103003830038300383003830038
1002430037233001452954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010490600640216222962910000103003830038300383003830038
100243003723300612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010490283800640216222962910000103003830038300383003830038
100243003723200612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010450000640216222962910000103003830038300383003830038
1002430037232006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100013500640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzs s0, s8, #3
  fcvtzs s1, s8, #3
  fcvtzs s2, s8, #3
  fcvtzs s3, s8, #3
  fcvtzs s4, s8, #3
  fcvtzs s5, s8, #3
  fcvtzs s6, s8, #3
  fcvtzs s7, s8, #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)03191e3a3f51inst 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)9fa0a8acc2c5branch mispredict (cb)cdcfd5d6e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200691550003025801081008000810080020500640132020020200392003999776999080120200800322008033920039200391180201100991001008000010000001115118116200360800001002004020040200402004020040
80204200391550003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016200360800001002004020040200402004020040
802042003915501203025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016200360800001002004020040200402004020040
80204200391550003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016200360800001002004020040200402004020040
802042003915500027725801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016200360800001002004020040200402004020040
80204200391660003025801081008000810080020500640132020020200392003999776999080120200800322008045720092200391180201100991001008000010000001115118016200360800001002004020040200402004020040
80204200391550003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016200360800001002004020040200402004020040
80204200391550003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010020001115118016200360800001002004020040200402004020040
80204200391560003525801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016200360800001002004020040200402004020040
80204200391560005825801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000301115118016200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03040809181e1f3f51inst 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)9fa8accfd2icache miss (d3)itlb miss (d4)d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501551010004025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100650210012346221920036080000102004020040200402004020040
800242003915510100011625800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000101350210012230221320036080000102004020040200402004020040
80024200391551010008925800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100050210011830221120036080000102004020040200402004020040
8002420090155111001768847800101080000108000050640000020020020142200399996310019800102080000208000020039200391180021109101080000100050210012231232320036080000102004020040200402004020040
80024200391551010008825800101080000108000050640000020020020039200399996310019800102080000208000020039200394180021109101080000101050210012231142220036080000102004020040200402004020040
80024200391551010008825800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100050210012346232220036080000102004020040200402004020040
800242003915610100079525800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100050210012130221520036080000102004020040200402004020040
800242003915510100013025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100050210012330172220036080000102004020040200402004020040
800242003915610130088258001010800001080000506400000200200200392003910006310019800102080000208000020039200391180021109101080000101050210011830212320036080000102004020040200402004020040
80024200981551010008825800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100050210012231192220036080000102004020040200402004020040