Apple M1 Microarchitecture Research by Dougall Johnson

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

FRECPS (vector, 2S)

Test 1: uops

Code:

  frecps v0.2s, v0.2s, v1.2s
  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)031e3a3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004403731006134072510001000100053190840184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730006134072510001000100053190840184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
10044037302406134072510001000100053190840184037403732583389510001000200040374037111001100000073116123473100040384038403840384038
1004403730006134072510001000100053190840184085403732583390310001000200040374037111001100000073116113473100040384038403840384038
10044037301206134072510001000100053190840184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730006134072510001000100053190840184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730006134072510001000100053190840184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
10044037300110334072510001000100053190840184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403731008234072510001000100053190840184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730008434072510001000100053190840184037403732583389510001000200040374037111001100000073116113473100040384038403840384038

Test 2: Latency 1->2

Code:

  frecps v0.2s, v0.2s, v1.2s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003729906139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
1020440037300072639407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004008540038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020020000400374003711102011009910010010000100107101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000000006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
10024400372990000006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
100244003730000000075439407251001010100001010000505706908040018400844003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
100244003729900008706139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384008540038
100244003730000000010339407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038

Test 3: Latency 1->3

Code:

  frecps v0.2s, v1.2s, 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): 4.0037

retire (01)cycle (02)03181e1f3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300000613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010000071041611394790100001004003840038400384003840038
10204400373000007263940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010003071011611394790100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
10204400373000120613940725101001001000010010000500570690804005340037400373810833874510252200100002002000040037400371110201100991001001000010003608071011611394790100001004003840038400384003840038
102044003729901201033940725101001001000010010000500570690804005340037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004022740038400384003840038
1020440037299090613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010003071011611394790100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
10204400373000007263940725101001001000010010000500570690804001840037400373810833876310100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038
1020440037299000613940725101001001000010010000500570690804001840037400373810833874510100200100002002000040037400371110201100991001001000010000071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030818191e3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300000014539407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100045640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000669216223947310000104003840038400384003840038
10024400373010000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  frecps v0.2s, v8.2s, v9.2s
  frecps v1.2s, v8.2s, v9.2s
  frecps v2.2s, v8.2s, v9.2s
  frecps v3.2s, v8.2s, v9.2s
  frecps v4.2s, v8.2s, v9.2s
  frecps v5.2s, v8.2s, v9.2s
  frecps v6.2s, v8.2s, v9.2s
  frecps v7.2s, v8.2s, v9.2s
  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)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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150052258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051105163320037800001002004120041200412004120041
80204200401506642258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051102162320037800001002004120041200412004120041
8020420040150042258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051103163220037800001002004120041200412004120041
80204200401500707258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051103163320037800001002004120041200412004120041
8020420040150042258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051103163220037800001002004120041200412004120041
8020420040150042258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051102164320037800001002004120041200412004120041
8020420040150042258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051103163320037800001002004120041200412004120041
8020420040150042258010010080000100800005006400001200212004020040997339998801002008000020016000020040200401180201100991001008000010000051103163220037800001002004120041200412004120041
8020420040150042258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051103162320037800001002004120041200412004120041
8020420040150042258010010080000100800005006400001200212004020040997339998801002008000020016000020040200401180201100991001008000010000051103163320037800001002004120041200412004120041

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015004125800101280000108000050640000012002120040200409996310020800102080000201600002004020040118002110910108000010005020116112003780000102004120041200412004120041
8002420040150041258001010800001080000506400000120021200402004099963100208001020800002016000020040200401180021109101080000102605020116112003780000102004120041200412004120041
800242004015004125800101080000108000050640000012002120040200409996310020800102080000201600002004020040118002110910108000010005020148112003780000102004120041200412004120041
800242004015004125800101080000108000050640000012002120040200409996310020800102080000201600002004020040118002110910108000010005020116152003780000102004120041200412004120041
80024200401500412580010108000010800005064000001200212004020040999631002080010208000020160000200402004011800211091010800001038125020116112003780000102004120041200412004120041
800242004015004125800101080000108000050640000002002120040200409996310020800102080000201600002004020040118002110910108000010005020116112003780000102004120041200412004120041
800242004015004125800101080000108000050640000012002120040200409996310020800102080000201600002004020040118002110910108000010005020116112003780000102004120041200412004120041
800242004015004125800101080000108000077640000012002120040200409996310020800102080000201600002004020040118002110910108000010005020116112003780000102004120041200412004120041
800242004015004125800101080000108000050640000012007220040200409996310020800102080000201600002004020040118002110910108000010035020116112003780000102004120041200412004120041
800242004015004125800101080000108000050640000012002120040200409996310020800102080000201600002004020040118002110910108000010005020116112003780000102004120041200412004120041