Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTPS (scalar, H to H)

Test 1: uops

Code:

  fcvtps h0, h0
  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
100430372306125472510081000100039816003018303730372414328951000100010003037303711100110000073216332629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
100430372307525472510001000100039816003018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000673316332629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110005073316332629100030383038303830383038
100430372406125472510001000100039816003018303730372413328951000100010003037303711100110000073316332629100030383038303830383038
1004303724041625472510001000100039816003018303730372414328951000100010003037303711100110000373316332629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073316332629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtps h0, h0
  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)0308090e18191e1f3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
102043003723200000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
1020430037233000000035129547251010010010000122100005004277160300543003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000003710116112963300100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
102043003723200000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
102043003723200000006129547251010010010000100100005004278512300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)033f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037232172229547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003723390829547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100210640216222962910000103003830038300383003830038
100243003724190129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722598629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225801295472510010101000010100005042771600300183003730037282863287671001020100001271000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722543629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722539829547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722584729547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225100829547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722581629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtps h0, h8
  fcvtps h1, h8
  fcvtps h2, h8
  fcvtps h3, h8
  fcvtps h4, h8
  fcvtps h5, h8
  fcvtps h6, h8
  fcvtps h7, h8
  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)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)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)9fa8c2c5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915512011425801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001001011151181620036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
8020420039155005425801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001001011151181620036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
8020420039156003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
802042003916005983025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
8020420039156003025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
8020420039161003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040

1000 unrolls and 10 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)9fa0a1a8a9accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502021164692003680000102004020040200402004020040
800242003915600001702580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100010050208165772003680000102004020040200402004020040
8002420039155000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010001005020716512112003680000102004020040200402004020040
80024200391550000107258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020111647102003680000102004020040200402004020040
8002420039155000028925800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000502071656112003680000102004020040200402004020040
800242003915600004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502081651092003680000102004020040200402004020040
8002420039155001204025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000502071651052003680000102004020040200402004020040
80024200391560000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050206165672003680000102004020040200402004020040
800242003915500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003921800211091010800001000000502010165852003680000102004020040200402004020040
80024200391550000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050206165872003680000102004020040200402004020040