Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTL (vector, 2D)

Test 1: uops

Code:

  fcvtl v0.2d, v0.2s
  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
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372506125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372308225472510001000100039816013018303730372414328951000100010003037303711100110003073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723050825472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724021225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtl v0.2d, v0.2s
  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)0318191e1f3f4d4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000610295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003723200001570295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372330000610295382510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372330000610295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003723200120610295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372330000610295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372330000610295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102161129705100001003003830038300383008530038
10204300372330000610295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372410000610295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372320000610295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038

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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000726295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006692162229629010000103003830038300383003830038
1002430037225000000726295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000000726295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000000327295472510010101000010100005042776311300183003730037282863287671001020100002010000300373003711100211091010100001000006832322429703310000103013330131301323013330038
100243003722511223482321374295296010010101000810100005042771600300183003730084282863287671001020100002010000300373003711100211091010100001000006403162229629010000103003830038300383003830038
100243013122501000084295386310019121000810100005542771601300183003730037282863287671016120101612010000300373003711100211091010100001021006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001001036402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000027061295472510010101000010100005042771601300183003730037282863287671001020100002010012300373003711100211091010100001000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtl v0.2d, v8.2s
  fcvtl v1.2d, v8.2s
  fcvtl v2.2d, v8.2s
  fcvtl v3.2d, v8.2s
  fcvtl v4.2d, v8.2s
  fcvtl v5.2d, v8.2s
  fcvtl v6.2d, v8.2s
  fcvtl v7.2d, v8.2s
  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)0307080a0b18191e1f3f51inst 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)9fa0a1a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915500000066030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
8020420039155000000570600258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
80204200391550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003916100000018030258010810080008100800205006410080200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
80204200391550000006030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915500000030030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
8020420039155000000249030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
8020420039156000000183030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801620200360800001002004020040200402004020040
80204200391550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051155040258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001000050208163520036080000102004020040200402004020040
8002420039155040258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001000050203163520036080000102004020040200402004020040
80024200391550128258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001000050204164520036080000102004020040200402004020040
80024200391552182258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001001142350203163520036080000102004020040200402004020040
8002420039155040258001010800841080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000050205165520036080000102004020040200402004020040
8002420039155040258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001000050205164520036080000102004020040200402004020040
8002420039156040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000050205163520036080000102004020040200402004020040
8002420039155040258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001000050205166420036380000102004020040200402004020040
800242003915501891258001010800001080000506400001200202003920039999603100198001020800002080000200392003911800211091010800001000350203166620036080000102004020040200402004020040
8002420039156040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000050206163520036080000102004020040200402004020040