Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTMS (scalar, H to H)

Test 1: uops

Code:

  fcvtms 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)03191e3f4e51inst 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372400612547251000100010003981600301830373037241432895100010001000303730371110011000073216112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723006542547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372400612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000273116112629100030383038303830383038
1004303724001022547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372400612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303724004762547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtms 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)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116112963300100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116112963300100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116112963300100001003003830038300383003830038
1020430037232011429547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100100710116112963300100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116112963300100001003023430038300383003830038
1020430037233126129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116112963300100001003003830038300383003830038
102043003723206129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116112963300100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001710116112963300100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100100710116112963300100001003003830038300383003830038
1020430037233010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e1f3a3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000101006402162229629010000103003830038300383003830038
100243003722400006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000101006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000101036402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000103006402162229629010000103008130038300383003830038
100243003722500006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006404164129701310000103013130132300853008530133
1002430131226000061295472510010101000010103005042771601300183003730084282863287671001020101622010000300373003711100211091010100001034406404242229629010000103003830038300383003830038
1002430084225131220811205295479010061101000010100005042771601303063041730367283062728877100102211301221130930309304189110021109101010000101006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtms h0, h8
  fcvtms h1, h8
  fcvtms h2, h8
  fcvtms h3, h8
  fcvtms h4, h8
  fcvtms h5, h8
  fcvtms h6, h8
  fcvtms 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)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)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)9fa8acc5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915503025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040201972009120040
80204200391552731125801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001001011151181620036800001002004020040200402004020040
802042003915593025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
802042003915603025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
802042003915598425801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080918191e1f3f51inst 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)9fa1a6a8a9acdtlb miss (c1)c2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015600000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000050201216352003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020416642003680000102004020040200402004020040
80024200391560000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000003005020416532003680000102004020040200402004020040
8002420039156000000402580010108000010800005064000002002020039200399996310019801082080103208010420105200902180021109101080000100207525005055452662012880000102009420090201442010320103
800242008915610000031425800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020416532003680000102004020040200402004020040
80025200391550000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020316642003680000102004020040200402004020040
800242003915600000040258001010800001080000506400000200202003920039100053100198001020800002080000200392003911800211091010800001000000005020516372003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020516662003680000102004020040200402004020040
800242003915600000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010001000050205163132003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020416652003680000102004020040200402004020040