Apple M1 Microarchitecture Research by Dougall Johnson

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

FACGE (vector, 4S)

Test 1: uops

Code:

  facge v0.4s, v0.4s, v1.4s
  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)03183f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150701687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100041573116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420851606116872510001000100026468020182037203715723189510001000200020372037111001100002473116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110002073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100001273116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  facge v0.4s, v0.4s, v1.4s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308181e3f4e51inst 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)9fa1a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500002321968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000003071001161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
10204200371500002741968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
10204200371500001931968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)696d6edispatch 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640316221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820086200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820084200371844403187671001020100002020000200372003711100211091010100001002000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000003640216221978510000102003820038200382003820038
10025200371500061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  facge v0.4s, v1.4s, v0.4s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e1f3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100002807102162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000107102162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010002107102162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000207102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308191e3f4e51inst 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)9fa0a8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010009000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001002300640216221978510000102003820038200382003820038
1002420037150000726196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000600640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003714910061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  facge v0.4s, v8.4s, v9.4s
  facge v1.4s, v8.4s, v9.4s
  facge v2.4s, v8.4s, v9.4s
  facge v3.4s, v8.4s, v9.4s
  facge v4.4s, v8.4s, v9.4s
  facge v5.4s, v8.4s, v9.4s
  facge v6.4s, v8.4s, v9.4s
  facge v7.4s, v8.4s, v9.4s
  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)03191e1f3f51inst 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)9fa8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000061258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051102161120035800001002003920039200392003920039
8020420038150096132527258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500001208258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000339258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392010520039
8020420038150000187258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000168258010010080000100800005006400002001920038200879973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000063258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2cfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000000000014425800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502020166212120035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050202116472120035080000102003920039200392003920039
800242003815000000100039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000005020916519820035080000102003920039200392003920039
8002420038156000000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050202116421920035080000102003920039200392003920039
8002420038150000000000622580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050202116421920035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050209164212120035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050209164212120035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050209165192120035080000102003920039200392003920039
80024200381500000000001482580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050209164211920035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502021165191020035080000102003920039200392003920039