Apple M1 Microarchitecture Research by Dougall Johnson

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

URSHL (vector, 4S)

Test 1: uops

Code:

  urshl 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)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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037239612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037233612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
100430372312612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383074303830383038
100430372312612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  urshl 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): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa6a8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042777381300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
10204300372240000061295482510100100100001001000050042773131300183003730037282653287451010020010000202200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
102043003722500021010861295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
102043003722500024061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000060071021622296340100001003003830038300383003830038
10204300372240000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
10204300372240000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e3f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372251000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000007102953064100291210016121029860428002713005430130301332829511288051016022103242020336301213013231100211091010100001020256556612322229702310000103008630132300863013330133
100243008522511000103295482510010101000010100005042773131300183003730037282873287671001020100002020360300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250000661295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372240000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372240000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  urshl 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): 3.0037

retire (01)cycle (02)030708090b18191e1f3a3f4e51inst 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)6061696d6edispatch 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)9fa0a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000000061295482510100100100001001000050042773131030018300373003728265328745101252001000020020000300373003711102011009910010010000100000000710011621296340100001003003830038300853008530038
102043003722500000000061295482510100100100001001000050042773131030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000710011611296340100001003003830038300383003830038
102043003722500000000062295482510100125100001251000062642773131030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000710011611296340100001003003830038300383003830038
102043003722500000000061295482510100100100001001000050042773131030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000710011611296340100001003003830038300383003830038
102043003722500000000061295482510100100100001001000050042773131030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000710011611296340100001003003830038300383003830038
102043003722500000000061295482510100100100001001000050042773131030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000710011611296340100001003003830038300753003830038
102043003722500000000061295482510100100100001001000050042773131030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000710011611296340100001003003830038300383003830038
102043003722500000000061295482510100100100001001000050042773131030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000710011611296340100001003003830038300383003830038
102043003722500000000061295482510100100100001001000050042773131030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000710011611296340100001003003830038300383003830038
102043003722500000000061295482510100125100001001000050042773131030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000710011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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
100243003722400061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000441295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000631295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300543003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038301333003830038
1002430037225000631295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000103295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100221091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  urshl v0.4s, v8.4s, v9.4s
  urshl v1.4s, v8.4s, v9.4s
  urshl v2.4s, v8.4s, v9.4s
  urshl v3.4s, v8.4s, v9.4s
  urshl v4.4s, v8.4s, v9.4s
  urshl v5.4s, v8.4s, v9.4s
  urshl v6.4s, v8.4s, v9.4s
  urshl 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039150041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010048951103161220036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020210099100100800001000051102162220036800001002004020040200402004020040
8020420039150041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010045051102162220036800001002004020040200402004020040
8020420039150041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010037351102162220036800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000351102162220036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001002051102162220036800001002004020040200402004020040
8020420039150041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010031051102162220036800001002004020040200402004020040
802042003915604125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051103162220036800001002004020040200402004020040
8020420039150041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010053351102162220036800001002004020040200402004020040
8020420039150041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010049351102162220036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03193f51inst 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)6061696d6edispatch 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)9fa8accfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010063502050018161717200360080000102004020040200402004020040
8002420039150040258009010800001080000506400001520020200392003999963100198001020800002016000020039200391180021109101080000100050200301616165200360080000102004020040200402004020040
800242003915004025800101080000108000060640000152002020039200399996310019800102080000201600002003920039118002110910108000010005020540616166200360080000102004020040200402004020040
8002420039150040258001010800001080000506400001520020200392003999963100198001020800002016000020039200391180021109101080000100050205401616616200360080000102004020040200402004020040
8002420039150040258001010800001080000506400001020020200392003999963100198001020800002016000020039200391180021109101080000100050200401616166200360080000102004020040200402004020040
8002420039150040258001010800001080000506400001520020200392003999963100198001020800002016000020039200391180021109101080000100050205401616166200360080000102004020040200402004020040
8002420039150040258001010800001080000506400001020020200392003999963100198001020800002016000020039200391180021109101080000100050200401616166200360080000102004020040200402004020040
800242003915004025800101080000108000050640000152002020039200399996310019800102080000201600002003920039118002110910108000010005020540616166200360080000102004020040200402004020040
8002420039150040258001010800001080000506400001520020200392003999963100198001020800002016000020039200391180021109101080000100050205401616616200360080000102004020040200402004020040
80024200391500402580010108000010800005064000005200202003920039999631001980010208000020160000200392003911800211091010800001000502054016161616200360080000102004020040200402004020040