Apple M1 Microarchitecture Research by Dougall Johnson

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

UCVTF (scalar, integer, D from W)

Test 1: uops

Code:

  ucvtf d0, w0
  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 2.000

Issues: 2.000

Integer unit issues: 0.000

Load/store unit issues: 1.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4f51inst issue (52)~issue fp/simd (54)~issue ld/st (55)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing ld/st (5a)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op ld/st (7d)~map op fp/simd (7e)~map lookup ld/st (80)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a6a8cfd5d6ddinst fetch restart (de)e0ld/st retires (ed)? fp/simd (ee)f5f6f7f8fd
200437620361025200010001000100010001407522820135737637672311320001000100010001000376376111001100010000731161137310001000377377377377377
200437630361025200010001000100010001407522820035737637672310920001000100010001000376376111001100010000731161137310001000377377377377377
200438030361025200010001000100010001427122820135737637672310920001000100010001000376376111001100010000731161137310001000377377377377377
200437630361025200010001000100010001407522820135737637672310920001000100010001000376376111001100010000731161137310001000377377377377377
200437630361025200010001000100010001407522820135737637672310920001000100010001000376376111001100010000731161137310001000377377377377377
200437630361025200010001000100010001407522820135737637672310920001000100010001000376376111001100010000731161137310001000377377377377377
200437630361025200010001000100010001407522820135737637672310920001000100010001000376376111001100010000731161137310001000377381377377377
200437630361025200010001000100010001407522820135737637672310920001000100010001000376376111001100010000731161137310001000377377377380377
200437920361025200010001000100010001407522820135737637672310920001000100010001000376376111001100010000731161141110001000377377377377377
200437630361025200010001000100010001407522820135737637672310920001000100010001000376376111001100010000731161137310001000377398377377377

Test 2: Latency 1->2 roundtrip

Code:

  ucvtf d0, w0
  fmov x0, d0
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 13.0032

retire (01)cycle (02)030b18191e1f3f4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
302041300329740000013001711940825401001010020000100001002000010000500621449714802709113001313003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010000100000000000131012162212951910000100001000010100130062130034130065130033130033
302041300329740000013001711940825401001010020000100001002000010000500621449714802709113001313003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010000100000000000131012162212956510000100001000010100130069130033130061130033130033
302041300329740000013001711940825401001010020000100001002000010000500621449714802709113001313003213011312546631262403010020010000200002001000020000130032130032112020110099100101001000010000100000000000131012162212951910000100001000010100130103130034130108130033130033
302041300329740000013001711940825401001010020000100001002000010000500621449714802709113001313003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010000100000000000131012162212951910000100001000010100130080130059130033130033130033
302041300329740000013001711940825401001010020000100001002000010000500621449714802709113001313003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010002100000000000131012162212951910000100001000010100130051130035130033130033130033
302041300329740000013001711940825401001010020000100001002000010000500621449714802709113001313003213003212546631262403010020010000200002001000020000130032130032212020110099100101001000010000100000000000131012162212951910000100001000010100130168130307130119130033130033
302041300329730271068580130017119408254010010100200001000010020000100005006214497148027091130013130032130066125466312624030100200100002000020010000200001300321300321120201100991001010010000100001000005600000131012162212951910000100001000010100130078130035130033130033130033
302041300329740000013001711940825401001010020000100001002000010000500621454514802709113001313003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010000100000000000131012162212951910000100001000010100130076130036130033130033130033
302041300329730000013001711940825401001010020000100001002000010000500621449714802709113001313003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010000100000009000131012162212951910000100001000010100130099130033130033130033130033
302041300329740000013001711940825401001010020000100001002000010000500621449714802709113001313003213003212546631262403010020010000200002001000020000130032130032112020110099100101001000010020100000000000131012162212951910000100001000010100130142130034130033130033130033

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0032

retire (01)cycle (02)030b18191e1f3f4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)5f60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~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)9fa0a6a8acc2cdcfd5d6daddinst fetch restart (de)e0? int output thing (e9)ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
3002413003297400076501300171194082540010100102000010000102000010000506214497148005280113002101300321300321254893126262300102010000201312010000200001300321300321120021109101001010000100100000000127011601112951910000100001000010010130033130038130033130033130033
3002413003297400069901300171194082540010100102000010000102000010000506214497148005280113001301300321300321254893126262300102010000200002010000200001300321300321120021109101001010000100100000001127021601112951910000100001000010010130033130033130033130033130033
3002413003297300048301300171194082540010100102000010000102000010000506214641148005280113001301300321300321254893126309300102010000200002010000200001300321300321120021109101001010000100100000000127011601112951910000100001000010010130033130033130033130033130033
3002413003297400034201300171194082540017100102000010000102000010000506214497148005280013001301300841300361254893126262300102010000200002010000200001300321300321120021109101001010000100100000000127011601112951910000100001000010010130033130033130033130033130033
30024130032974000104701300171194082540010100102000010000102000010000506214497148005280013001301300321300321254893126262300102010000200002010000200001300321300321120021109101001010000100100000000127011702112951910000100001000010010130033130033130033130033130033
3002413003297400087601300171194082540010100102000010000102000010000506214497148005280113001301300321300321254893126262300102010000200002010000200001300321300321120021109101001010000100100000000127011601112951910000100001000010010130033130033130033130033130033
30024130032974000108601300171194082540010100102000010000102000010000506214497148019960113001301300321300321254893126270300102010000200002010000200001300321300321120021109101001010000100100000000127011601112951910000100001000010010130033130033130033130033130033
3002413003297400073501300171194083340010100102000010000102000010000506214497148005280113001301300321300321254893126262300102010000200002010000200001300321300331120021109101001010000100100001000127011601112952210000100001000010010130033130033130033130033130033
300241301159761322491921300171194082540010100102000010000102000010000506214497148005280113001301300321300321254893126262300102010000200002010000200001300321300341120021109101001010000102100000000127011601112951910000100001000010010130033130378130033130372130033
30024130032974000129881300171194082540010100102000010000102000010000506214497148005280113001301300321300321254893126315300102010000200002010066200001300371300321120021109101001010000100100000000127011601112952010000100001000010010130033130033130033130033130033

Test 3: throughput

Count: 8

Code:

  ucvtf d0, w8
  ucvtf d1, w8
  ucvtf d2, w8
  ucvtf d3, w8
  ucvtf d4, w8
  ucvtf d5, w8
  ucvtf d6, w8
  ucvtf d7, w8
  mov x8, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3339

retire (01)cycle (02)030918191e1f3f4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)60696b6d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst function returns (8f)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a5a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042670920700000266940251601001008000080000100800208001550011689511884163126690026709267096632066658160135200800208002020080020800202689226717118020110009910010080000100000800000000011151172160026719080000800001002671026710267102671026710
1602042670920700000266980251601001008000080000100800208001550011684991901644026690026709267096632066658160135200800208002020080020800202721626716118020110009910010080000100000800000000011151170250026717080000800001002671026710267102671026710
1602042670920700000266940251601001008000080000100800208001550011689511884163026690326716267166632066658160135200800208002020080020800202672326719118020110009910010080000100000800000000011151170160026706080000800001002671426710267102671026710
1602042670920700000266940251601001008000080000100800208001550011689511884163026690026709267096632066658160135200800208002020080020800202670926709118020110009910010080000100000800000000011151171160026706080000800001002671026710267102671026710
1602042670920700000266940251601001008000080000100800208001550011689511884163026690026709267096632066658160135200800208002020080020800202671326709118020110009910010080000100000800000310011151170160026714080000800001002671026813267102671426710
16020426709207000120266940251601001008000080000100800208001550011689511884163126706026709267096632066658160135200800208002020080020800202670926709118020110009910010080000100000800000003011151170160026720080000800001002671027215267142671926710
1602042670920700000267070251601001008000080000100800208001550011753221883406026690026709267096632066658160135200800208002020080020800202670926709118020110009910010080000100000800000000011151170160026706080000800001002671026710267102671026710
1602042670920700000266940251601001008000080000100800208001550011689511884163026690026709267096632066658160135200800208002020080020800202670926709118020110009910010080000100000800000000011151170160026709080000800001002671026710267102671026710
1602042670920700000266940251601001008000080000100802088001550011689511884163026690026709267096633066658160135200800208002020080020800202670926709218020110009910010080000100000800000000011151170160026715080000800001002671026710267102671026710
1602042670920700000266970251601001008000080000100800208001350011689511884163026690026709267096632066658160135200800208002020080020800202679426719118020110009910010080000100000800000000011151170160026706080000800001002671026710267102671026710

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.3339

retire (01)cycle (02)030408090b18191e1f3a3f4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~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)9fa0a1a5a6a7a8a9acc2cfd5d6d9dbddinst fetch restart (de)e0? int output thing (e9)ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242671020700000000026702025160010108000080000108000080356501168577188435426690267092671266580366891600102080000800002080000800002670926709118002110910108000010000800000000050202116005112670608000080000102671026901270462684326714
160024267142071000000002669402516001010800008000010800008000050116888018840322669026709267096653036689160010208000080000208000080000267132670911800211091010800001000080000000005020101600892688508000080000102671026710267102671026710
16002426709207000000000266940251600101080000800001080000800005011717401875194266902670926709665303668916001020800008000020800008000026709267091180021109101080000100008000000000502051600992695908000080000102671026710267102671026710
160024267092070000000002669402516001010800008000010800008000050116888018840322669026709267096653036689160010208000080000208000080000267092670911800211091010800001000080000000005020716017102694408000080000102671026710267102671026710
16002426709206000000000266940251600101080000800001080000800005011688801884032266902670926709665303668916001020800008000020800008000026709267091180021109101080000100008000000000502071601852689608000080000102671026710267102671026710
16002426709207000000000266940251600101080000800001080000800005011688801884032266902670926709665303668916001020800008000020800008057026717267091180021109101080000100008000000000502061600992690408000080000102671026710267102671026710
16002426709207000000000266940251600101080000800001080000800005011688801884032266902670926709665303668916001020800008000020800008000026709267091180021109101080000100008000000000502071600572687508000080000102671026710267102671026710
160024267092070000000002669402516001010800008000010800008000050119067518842572669026709267096653036689160010208000080378208000080000267092670911800211091010800001000080000000005020716007102672608000080000102671026710267102671026710
16002426709207000000000266940251600101080000800001080000800005011703911883845266902670926709665303668916001020800008000020800008000026709267091180021109101080000100008000000000502051600482681108000080000102676026765267172671426710
160024272092152011778106160277014292661615721080910809101081301812465012076491908018275342786327705709714312773451625592081326815152081329813262786427915818002110910108000010002508091200263604517610790018152778908000080000102786927874278622787827712