[X64] [tannergooding] Minor cleanup of the Vector64/128/256/512 implementations to improve fall ... #405
Comments
Top method regressions671 (126.37 % of base) - System.Runtime.Intrinsics.Vector512`1[ubyte]:System.Runtime.Intrinsics.ISimdVector,T>.Divide(System.Runtime.Intrinsics.Vector512`1[ubyte],ubyte):System.Runtime.Intrinsics.Vector512`1[ubyte] ; Assembly listing for method System.Runtime.Intrinsics.Vector512`1[ubyte]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Divide(System.Runtime.Intrinsics.Vector512`1[ubyte],ubyte):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
; Emitting BLENDED_CODE for X64 with AVX - Unix
; FullOpts code
; optimized code
; rbp based frame
; partially interruptible
; No PGO data
-; 0 inlinees with PGO data; 17 single block inlinees; 9 inlinees without PGO data
+; 0 inlinees with PGO data; 34 single block inlinees; 27 inlinees without PGO data
; Final local variable assignments
;
-; V00 RetBuf [V00,T09] ( 4, 4 ) byref -> rbx single-def
+; V00 RetBuf [V00,T01] ( 5, 5 ) byref -> rdi single-def
;* V01 arg0 [V01 ] ( 0, 0 ) struct (64) zero-ref single-def <System.Runtime.Intrinsics.Vector512`1[ubyte]>
-; V02 arg1 [V02,T10] ( 3, 3 ) ubyte -> rsi single-def
-; V03 OutArgs [V03 ] ( 1, 1 ) struct (64) [rsp+0x00] do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
-; V04 tmp1 [V04,T18] ( 2, 4 ) simd32 -> [rbp-0x50] spill-single-def "impAppendStmt"
-; V05 tmp2 [V05,T19] ( 2, 4 ) simd32 -> [rbp-0x70] do-not-enreg[HS] hidden-struct-arg "spilled call-like call argument"
-; V06 tmp3 [V06,T15] ( 3, 6 ) simd32 -> [rbp-0x90] spill-single-def "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
-; V07 tmp4 [V07,T20] ( 2, 4 ) simd16 -> [rbp-0xA0] spill-single-def "impAppendStmt"
+; V02 arg1 [V02,T02] ( 3, 3 ) ubyte -> rsi single-def
+;# V03 OutArgs [V03 ] ( 1, 1 ) struct ( 0) [rsp+0x00] do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
+; V04 tmp1 [V04,T25] ( 2, 4 ) simd32 -> mm0 "impAppendStmt"
+; V05 tmp2 [V05,T26] ( 2, 4 ) simd32 -> mm1 "spilled call-like call argument"
+; V06 tmp3 [V06,T19] ( 3, 6 ) simd32 -> mm0 "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+; V07 tmp4 [V07,T27] ( 2, 4 ) simd16 -> mm1 "impAppendStmt"
;* V08 tmp5 [V08 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
-; V09 tmp6 [V09,T16] ( 3, 6 ) simd16 -> [rbp-0xB0] do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+; V09 tmp6 [V09,T20] ( 3, 6 ) simd16 -> [rbp-0x10] do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
;* V10 tmp7 [V10 ] ( 0, 0 ) struct ( 8) zero-ref "impAppendStmt" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
;* V11 tmp8 [V11 ] ( 0, 0 ) struct ( 8) zero-ref "spilled call-like call argument" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
-; V12 tmp9 [V12 ] ( 2, 5 ) struct ( 8) [rbp-0xB8] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
-; V13 tmp10 [V13,T01] ( 5, 17 ) int -> r15 "Inline stloc first use temp"
-; V14 tmp11 [V14 ] ( 2, 10 ) struct ( 8) [rbp-0xC0] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+; V12 tmp9 [V12 ] ( 9, 9 ) struct ( 8) [rbp-0x18] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V13 tmp10 [V13,T11] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
+; V14 tmp11 [V14 ] ( 9, 18 ) struct ( 8) [rbp-0x20] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
;* V15 tmp12 [V15 ] ( 0, 0 ) ubyte -> zero-ref "Inline stloc first use temp"
-; V16 tmp13 [V16 ] ( 2, 5 ) struct ( 8) [rbp-0xC8] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
-; V17 tmp14 [V17,T02] ( 5, 17 ) int -> r13 "Inline stloc first use temp"
-; V18 tmp15 [V18 ] ( 2, 10 ) struct ( 8) [rbp-0xD0] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
-;* V19 tmp16 [V19 ] ( 0, 0 ) ubyte -> zero-ref "Inline stloc first use temp"
-; V20 tmp17 [V20,T21] ( 3, 3 ) simd16 -> [rbp-0xE0] do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
-; V21 tmp18 [V21,T17] ( 3, 6 ) simd16 -> [rbp-0xF0] do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
-;* V22 tmp19 [V22 ] ( 0, 0 ) struct ( 8) zero-ref "impAppendStmt" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
-;* V23 tmp20 [V23 ] ( 0, 0 ) struct ( 8) zero-ref "spilled call-like call argument" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
-; V24 tmp21 [V24 ] ( 2, 5 ) struct ( 8) [rbp-0xF8] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
-; V25 tmp22 [V25,T03] ( 5, 17 ) int -> r15 "Inline stloc first use temp"
-; V26 tmp23 [V26 ] ( 2, 10 ) struct ( 8) [rbp-0x100] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
-;* V27 tmp24 [V27 ] ( 0, 0 ) ubyte -> zero-ref "Inline stloc first use temp"
-; V28 tmp25 [V28 ] ( 2, 5 ) struct ( 8) [rbp-0x108] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
-; V29 tmp26 [V29,T04] ( 5, 17 ) int -> r13 "Inline stloc first use temp"
-; V30 tmp27 [V30 ] ( 2, 10 ) struct ( 8) [rbp-0x110] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V16 tmp13 [V16 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V17 tmp14 [V17 ] ( 0, 0 ) ubyte -> zero-ref "Inlining Arg"
+; V18 tmp15 [V18 ] ( 9, 9 ) struct ( 8) [rbp-0x28] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V19 tmp16 [V19,T12] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
+; V20 tmp17 [V20 ] ( 9, 18 ) struct ( 8) [rbp-0x30] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V21 tmp18 [V21 ] ( 0, 0 ) ubyte -> zero-ref "Inline stloc first use temp"
+;* V22 tmp19 [V22 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V23 tmp20 [V23 ] ( 0, 0 ) ubyte -> zero-ref "Inlining Arg"
+; V24 tmp21 [V24,T29] ( 3, 3 ) simd16 -> [rbp-0x40] do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+; V25 tmp22 [V25,T21] ( 3, 6 ) simd16 -> [rbp-0x50] do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+;* V26 tmp23 [V26 ] ( 0, 0 ) struct ( 8) zero-ref "impAppendStmt" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V27 tmp24 [V27 ] ( 0, 0 ) struct ( 8) zero-ref "spilled call-like call argument" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+; V28 tmp25 [V28 ] ( 9, 9 ) struct ( 8) [rbp-0x58] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V29 tmp26 [V29,T13] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
+; V30 tmp27 [V30 ] ( 9, 18 ) struct ( 8) [rbp-0x60] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
;* V31 tmp28 [V31 ] ( 0, 0 ) ubyte -> zero-ref "Inline stloc first use temp"
-; V32 tmp29 [V32,T22] ( 3, 3 ) simd16 -> [rbp-0x120] do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
-;* V33 tmp30 [V33 ] ( 0, 0 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
-; V34 tmp31 [V34,T23] ( 1, 1 ) simd32 -> [rbp+0x10] single-def "field V01._lower (fldOffset=0x0)" P-INDEP
-; V35 tmp32 [V35,T24] ( 1, 1 ) simd32 -> [rbp+0x30] single-def "field V01._upper (fldOffset=0x20)" P-INDEP
-; V36 tmp33 [V36,T11] ( 2, 2 ) long -> r15 "field V10._00 (fldOffset=0x0)" P-INDEP
-; V37 tmp34 [V37,T12] ( 2, 2 ) long -> rdi "field V11._00 (fldOffset=0x0)" P-INDEP
-; V38 tmp35 [V38 ] ( 2, 5 ) long -> [rbp-0xB8] do-not-enreg[X] addr-exposed "field V12._00 (fldOffset=0x0)" P-DEP
-; V39 tmp36 [V39 ] ( 2, 9 ) long -> [rbp-0xC0] do-not-enreg[X] addr-exposed "field V14._00 (fldOffset=0x0)" P-DEP
-; V40 tmp37 [V40 ] ( 2, 5 ) long -> [rbp-0xC8] do-not-enreg[X] addr-exposed "field V16._00 (fldOffset=0x0)" P-DEP
-; V41 tmp38 [V41 ] ( 2, 9 ) long -> [rbp-0xD0] do-not-enreg[X] addr-exposed "field V18._00 (fldOffset=0x0)" P-DEP
-; V42 tmp39 [V42,T13] ( 2, 2 ) long -> r15 "field V22._00 (fldOffset=0x0)" P-INDEP
-; V43 tmp40 [V43,T14] ( 2, 2 ) long -> rsi "field V23._00 (fldOffset=0x0)" P-INDEP
-; V44 tmp41 [V44 ] ( 2, 5 ) long -> [rbp-0xF8] do-not-enreg[X] addr-exposed "field V24._00 (fldOffset=0x0)" P-DEP
-; V45 tmp42 [V45 ] ( 2, 9 ) long -> [rbp-0x100] do-not-enreg[X] addr-exposed "field V26._00 (fldOffset=0x0)" P-DEP
-; V46 tmp43 [V46 ] ( 2, 5 ) long -> [rbp-0x108] do-not-enreg[X] addr-exposed "field V28._00 (fldOffset=0x0)" P-DEP
-; V47 tmp44 [V47 ] ( 2, 9 ) long -> [rbp-0x110] do-not-enreg[X] addr-exposed "field V30._00 (fldOffset=0x0)" P-DEP
-; V48 cse0 [V48,T00] ( 6, 18 ) int -> r14 hoist "CSE #01: aggressive"
-; V49 cse1 [V49,T05] ( 3, 12 ) long -> r13 "CSE #02: aggressive"
-; V50 cse2 [V50,T06] ( 3, 12 ) long -> r12 "CSE #03: aggressive"
-; V51 cse3 [V51,T07] ( 3, 12 ) long -> r13 "CSE #04: aggressive"
-; V52 cse4 [V52,T08] ( 3, 12 ) long -> r12 "CSE #05: aggressive"
+;* V32 tmp29 [V32 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V33 tmp30 [V33 ] ( 0, 0 ) ubyte -> zero-ref "Inlining Arg"
+; V34 tmp31 [V34 ] ( 9, 9 ) struct ( 8) [rbp-0x68] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V35 tmp32 [V35,T14] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
+; V36 tmp33 [V36 ] ( 9, 18 ) struct ( 8) [rbp-0x70] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V37 tmp34 [V37 ] ( 0, 0 ) ubyte -> zero-ref "Inline stloc first use temp"
+;* V38 tmp35 [V38 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V39 tmp36 [V39 ] ( 0, 0 ) ubyte -> zero-ref "Inlining Arg"
+; V40 tmp37 [V40,T30] ( 3, 3 ) simd16 -> [rbp-0x80] do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+;* V41 tmp38 [V41 ] ( 0, 0 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+; V42 tmp39 [V42,T22] ( 3, 6 ) simd32 -> mm1 "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+; V43 tmp40 [V43,T28] ( 2, 4 ) simd16 -> mm2 "impAppendStmt"
+;* V44 tmp41 [V44 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
+; V45 tmp42 [V45,T23] ( 3, 6 ) simd16 -> [rbp-0x90] do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+;* V46 tmp43 [V46 ] ( 0, 0 ) struct ( 8) zero-ref "impAppendStmt" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V47 tmp44 [V47 ] ( 0, 0 ) struct ( 8) zero-ref "spilled call-like call argument" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+; V48 tmp45 [V48 ] ( 9, 9 ) struct ( 8) [rbp-0x98] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V49 tmp46 [V49,T15] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
+; V50 tmp47 [V50 ] ( 9, 18 ) struct ( 8) [rbp-0xA0] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V51 tmp48 [V51 ] ( 0, 0 ) ubyte -> zero-ref "Inline stloc first use temp"
+;* V52 tmp49 [V52 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V53 tmp50 [V53 ] ( 0, 0 ) ubyte -> zero-ref "Inlining Arg"
+; V54 tmp51 [V54 ] ( 9, 9 ) struct ( 8) [rbp-0xA8] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V55 tmp52 [V55,T16] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
+; V56 tmp53 [V56 ] ( 9, 18 ) struct ( 8) [rbp-0xB0] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V57 tmp54 [V57 ] ( 0, 0 ) ubyte -> zero-ref "Inline stloc first use temp"
+;* V58 tmp55 [V58 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V59 tmp56 [V59 ] ( 0, 0 ) ubyte -> zero-ref "Inlining Arg"
+; V60 tmp57 [V60,T31] ( 3, 3 ) simd16 -> [rbp-0xC0] do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+; V61 tmp58 [V61,T24] ( 3, 6 ) simd16 -> [rbp-0xD0] do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+;* V62 tmp59 [V62 ] ( 0, 0 ) struct ( 8) zero-ref "impAppendStmt" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V63 tmp60 [V63 ] ( 0, 0 ) struct ( 8) zero-ref "spilled call-like call argument" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+; V64 tmp61 [V64 ] ( 9, 9 ) struct ( 8) [rbp-0xD8] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V65 tmp62 [V65,T17] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
+; V66 tmp63 [V66 ] ( 9, 18 ) struct ( 8) [rbp-0xE0] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V67 tmp64 [V67 ] ( 0, 0 ) ubyte -> zero-ref "Inline stloc first use temp"
+;* V68 tmp65 [V68 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V69 tmp66 [V69 ] ( 0, 0 ) ubyte -> zero-ref "Inlining Arg"
+; V70 tmp67 [V70 ] ( 9, 9 ) struct ( 8) [rbp-0xE8] do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V71 tmp68 [V71,T18] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
+; V72 tmp69 [V72 ] ( 9, 18 ) struct ( 8) [rbp-0xF0] do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[ubyte]>
+;* V73 tmp70 [V73 ] ( 0, 0 ) ubyte -> zero-ref "Inline stloc first use temp"
+;* V74 tmp71 [V74 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V75 tmp72 [V75 ] ( 0, 0 ) ubyte -> zero-ref "Inlining Arg"
+; V76 tmp73 [V76,T32] ( 3, 3 ) simd16 -> [rbp-0x100] do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+;* V77 tmp74 [V77 ] ( 0, 0 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V78 tmp75 [V78 ] ( 0, 0 ) struct (64) zero-ref ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+; V79 tmp76 [V79,T35] ( 1, 1 ) simd32 -> [rbp+0x10] single-def "field V01._lower (fldOffset=0x0)" P-INDEP
+; V80 tmp77 [V80,T36] ( 1, 1 ) simd32 -> [rbp+0x30] single-def "field V01._upper (fldOffset=0x20)" P-INDEP
+; V81 tmp78 [V81,T03] ( 2, 2 ) long -> rsi "field V10._00 (fldOffset=0x0)" P-INDEP
+; V82 tmp79 [V82,T04] ( 2, 2 ) long -> rax "field V11._00 (fldOffset=0x0)" P-INDEP
+; V83 tmp80 [V83 ] ( 9, 9 ) long -> [rbp-0x18] do-not-enreg[X] addr-exposed "field V12._00 (fldOffset=0x0)" P-DEP
+; V84 tmp81 [V84 ] ( 9, 17 ) long -> [rbp-0x20] do-not-enreg[X] addr-exposed "field V14._00 (fldOffset=0x0)" P-DEP
+; V85 tmp82 [V85 ] ( 9, 9 ) long -> [rbp-0x28] do-not-enreg[X] addr-exposed "field V18._00 (fldOffset=0x0)" P-DEP
+; V86 tmp83 [V86 ] ( 9, 17 ) long -> [rbp-0x30] do-not-enreg[X] addr-exposed "field V20._00 (fldOffset=0x0)" P-DEP
+; V87 tmp84 [V87,T05] ( 2, 2 ) long -> rsi "field V26._00 (fldOffset=0x0)" P-INDEP
+; V88 tmp85 [V88,T06] ( 2, 2 ) long -> rax "field V27._00 (fldOffset=0x0)" P-INDEP
+; V89 tmp86 [V89 ] ( 9, 9 ) long -> [rbp-0x58] do-not-enreg[X] addr-exposed "field V28._00 (fldOffset=0x0)" P-DEP
+; V90 tmp87 [V90 ] ( 9, 17 ) long -> [rbp-0x60] do-not-enreg[X] addr-exposed "field V30._00 (fldOffset=0x0)" P-DEP
+; V91 tmp88 [V91 ] ( 9, 9 ) long -> [rbp-0x68] do-not-enreg[X] addr-exposed "field V34._00 (fldOffset=0x0)" P-DEP
+; V92 tmp89 [V92 ] ( 9, 17 ) long -> [rbp-0x70] do-not-enreg[X] addr-exposed "field V36._00 (fldOffset=0x0)" P-DEP
+; V93 tmp90 [V93,T07] ( 2, 2 ) long -> rsi "field V46._00 (fldOffset=0x0)" P-INDEP
+; V94 tmp91 [V94,T08] ( 2, 2 ) long -> rax "field V47._00 (fldOffset=0x0)" P-INDEP
+; V95 tmp92 [V95 ] ( 9, 9 ) long -> [rbp-0x98] do-not-enreg[X] addr-exposed "field V48._00 (fldOffset=0x0)" P-DEP
+; V96 tmp93 [V96 ] ( 9, 17 ) long -> [rbp-0xA0] do-not-enreg[X] addr-exposed "field V50._00 (fldOffset=0x0)" P-DEP
+; V97 tmp94 [V97 ] ( 9, 9 ) long -> [rbp-0xA8] do-not-enreg[X] addr-exposed "field V54._00 (fldOffset=0x0)" P-DEP
+; V98 tmp95 [V98 ] ( 9, 17 ) long -> [rbp-0xB0] do-not-enreg[X] addr-exposed "field V56._00 (fldOffset=0x0)" P-DEP
+; V99 tmp96 [V99,T09] ( 2, 2 ) long -> rsi "field V62._00 (fldOffset=0x0)" P-INDEP
+; V100 tmp97 [V100,T10] ( 2, 2 ) long -> rax "field V63._00 (fldOffset=0x0)" P-INDEP
+; V101 tmp98 [V101 ] ( 9, 9 ) long -> [rbp-0xD8] do-not-enreg[X] addr-exposed "field V64._00 (fldOffset=0x0)" P-DEP
+; V102 tmp99 [V102 ] ( 9, 17 ) long -> [rbp-0xE0] do-not-enreg[X] addr-exposed "field V66._00 (fldOffset=0x0)" P-DEP
+; V103 tmp100 [V103 ] ( 9, 9 ) long -> [rbp-0xE8] do-not-enreg[X] addr-exposed "field V70._00 (fldOffset=0x0)" P-DEP
+; V104 tmp101 [V104 ] ( 9, 17 ) long -> [rbp-0xF0] do-not-enreg[X] addr-exposed "field V72._00 (fldOffset=0x0)" P-DEP
+; V105 tmp102 [V105,T33] ( 2, 2 ) simd32 -> mm0 "field V78._lower (fldOffset=0x0)" P-INDEP
+; V106 tmp103 [V106,T34] ( 2, 2 ) simd32 -> mm1 "field V78._upper (fldOffset=0x20)" P-INDEP
+; V107 cse0 [V107,T00] ( 65, 65 ) int -> rcx "CSE #01: aggressive"
;
-; Lcl frame size = 312
+; Lcl frame size = 256
G_M7625_IG01:
push rbp
- push r15
- push r14
- push r13
- push r12
- push rbx
- sub rsp, 312
- lea rbp, [rsp+0x160]
- mov rbx, rdi
- ;; size=28 bbWeight=1 PerfScore 7.00
+ sub rsp, 256
+ lea rbp, [rsp+0x100]
+ ;; size=16 bbWeight=1 PerfScore 1.75
G_M7625_IG02:
vmovups ymm0, ymmword ptr [rbp+0x10]
- vmovups ymmword ptr [rbp-0x90], ymm0
vmovaps ymm1, ymm0
- vmovaps xmmword ptr [rbp-0xB0], xmm1
- mov rdi, qword ptr [rbp-0xB0]
- mov qword ptr [rbp-0xC0], rdi
- xor r15d, r15d
- movzx r14, sil
- ;; size=46 bbWeight=1 PerfScore 8.75
+ vmovaps xmmword ptr [rbp-0x10], xmm1
+ mov rax, qword ptr [rbp-0x10]
+ mov qword ptr [rbp-0x20], rax
+ movzx rax, byte ptr [rbp-0x20]
+ movzx rcx, sil
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x18], al
+ movzx rax, byte ptr [rbp-0x1F]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x17], al
+ movzx rax, byte ptr [rbp-0x1E]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x16], al
+ movzx rax, byte ptr [rbp-0x1D]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x15], al
+ movzx rax, byte ptr [rbp-0x1C]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x14], al
+ movzx rax, byte ptr [rbp-0x1B]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x13], al
+ movzx rax, byte ptr [rbp-0x1A]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x12], al
+ movzx rax, byte ptr [rbp-0x19]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x11], al
+ mov rsi, qword ptr [rbp-0x18]
+ mov rax, qword ptr [rbp-0x08]
+ mov qword ptr [rbp-0x30], rax
+ movzx rax, byte ptr [rbp-0x30]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x28], al
+ movzx rax, byte ptr [rbp-0x2F]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x27], al
+ movzx rax, byte ptr [rbp-0x2E]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x26], al
+ movzx rax, byte ptr [rbp-0x2D]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x25], al
+ movzx rax, byte ptr [rbp-0x2C]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x24], al
+ movzx rax, byte ptr [rbp-0x2B]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x23], al
+ movzx rax, byte ptr [rbp-0x2A]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x22], al
+ ;; size=203 bbWeight=1 PerfScore 419.25
G_M7625_IG03:
- lea rdi, [rbp-0xC0]
- movsxd r13, r15d
- movzx rdi, byte ptr [rdi+r13]
- mov esi, r14d
- mov rax, 0xD1FFAB1E ; code for System.Runtime.Intrinsics.Scalar`1[ubyte]:Divide(ubyte,ubyte):ubyte
- call [rax]System.Runtime.Intrinsics.Scalar`1[ubyte]:Divide(ubyte,ubyte):ubyte
- lea rdi, [rbp-0xB8]
- mov byte ptr [rdi+r13], al
- inc r15d
- cmp r15d, 8
- jl SHORT G_M7625_IG03
- ;; size=50 bbWeight=4 PerfScore 37.00
+ movzx rax, byte ptr [rbp-0x29]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x21], al
+ mov rax, qword ptr [rbp-0x28]
+ mov qword ptr [rbp-0x40], rsi
+ mov qword ptr [rbp-0x38], rax
+ vmovaps xmm1, xmmword ptr [rbp-0x40]
+ vextractf128 xmm0, ymm0, 1
+ vmovaps xmmword ptr [rbp-0x50], xmm0
+ mov rax, qword ptr [rbp-0x50]
+ mov qword ptr [rbp-0x60], rax
+ movzx rax, byte ptr [rbp-0x60]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x58], al
+ movzx rax, byte ptr [rbp-0x5F]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x57], al
+ movzx rax, byte ptr [rbp-0x5E]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x56], al
+ movzx rax, byte ptr [rbp-0x5D]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x55], al
+ movzx rax, byte ptr [rbp-0x5C]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x54], al
+ movzx rax, byte ptr [rbp-0x5B]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x53], al
+ movzx rax, byte ptr [rbp-0x5A]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x52], al
+ movzx rax, byte ptr [rbp-0x59]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x51], al
+ mov rsi, qword ptr [rbp-0x58]
+ mov rax, qword ptr [rbp-0x48]
+ mov qword ptr [rbp-0x70], rax
+ movzx rax, byte ptr [rbp-0x70]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x68], al
+ movzx rax, byte ptr [rbp-0x6F]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x67], al
+ movzx rax, byte ptr [rbp-0x6E]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x66], al
+ movzx rax, byte ptr [rbp-0x6D]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x65], al
+ movzx rax, byte ptr [rbp-0x6C]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x64], al
+ movzx rax, byte ptr [rbp-0x6B]
+ xor edx, edx
+ ;; size=208 bbWeight=1 PerfScore 396.75
G_M7625_IG04:
- mov r15, qword ptr [rbp-0xB8]
- mov rdi, qword ptr [rbp-0xA8]
- mov qword ptr [rbp-0xD0], rdi
- xor r13d, r13d
- ;; size=24 bbWeight=1 PerfScore 3.25
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x63], al
+ movzx rax, byte ptr [rbp-0x6A]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x62], al
+ movzx rax, byte ptr [rbp-0x69]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x61], al
+ mov rax, qword ptr [rbp-0x68]
+ mov qword ptr [rbp-0x80], rsi
+ mov qword ptr [rbp-0x78], rax
+ vinserti128 ymm0, ymm1, xmmword ptr [rbp-0x80], 1
+ vmovups ymm1, ymmword ptr [rbp+0x30]
+ vmovaps ymm2, ymm1
+ vmovaps xmmword ptr [rbp-0x90], xmm2
+ mov rax, qword ptr [rbp-0x90]
+ mov qword ptr [rbp-0xA0], rax
+ movzx rax, byte ptr [rbp-0xA0]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x98], al
+ movzx rax, byte ptr [rbp-0x9F]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x97], al
+ movzx rax, byte ptr [rbp-0x9E]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x96], al
+ movzx rax, byte ptr [rbp-0x9D]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x95], al
+ movzx rax, byte ptr [rbp-0x9C]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x94], al
+ movzx rax, byte ptr [rbp-0x9B]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x93], al
+ movzx rax, byte ptr [rbp-0x9A]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x92], al
+ movzx rax, byte ptr [rbp-0x99]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0x91], al
+ mov rsi, qword ptr [rbp-0x98]
+ mov rax, qword ptr [rbp-0x88]
+ mov qword ptr [rbp-0xB0], rax
+ movzx rax, byte ptr [rbp-0xB0]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xA8], al
+ movzx rax, byte ptr [rbp-0xAF]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xA7], al
+ movzx rax, byte ptr [rbp-0xAE]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xA6], al
+ movzx rax, byte ptr [rbp-0xAD]
+ xor edx, edx
+ div edx:eax, ecx
+ ;; size=296 bbWeight=1 PerfScore 423.75
G_M7625_IG05:
- lea rdi, [rbp-0xD0]
- movsxd r12, r13d
- movzx rdi, byte ptr [rdi+r12]
- mov esi, r14d
- mov rax, 0xD1FFAB1E ; code for System.Runtime.Intrinsics.Scalar`1[ubyte]:Divide(ubyte,ubyte):ubyte
- call [rax]System.Runtime.Intrinsics.Scalar`1[ubyte]:Divide(ubyte,ubyte):ubyte
- lea rdi, [rbp-0xC8]
- mov byte ptr [rdi+r12], al
- inc r13d
- cmp r13d, 8
- jl SHORT G_M7625_IG05
- ;; size=50 bbWeight=4 PerfScore 37.00
+ mov byte ptr [rbp-0xA5], al
+ movzx rax, byte ptr [rbp-0xAC]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xA4], al
+ movzx rax, byte ptr [rbp-0xAB]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xA3], al
+ movzx rax, byte ptr [rbp-0xAA]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xA2], al
+ movzx rax, byte ptr [rbp-0xA9]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xA1], al
+ mov rax, qword ptr [rbp-0xA8]
+ mov qword ptr [rbp-0xC0], rsi
+ mov qword ptr [rbp-0xB8], rax
+ vmovaps xmm2, xmmword ptr [rbp-0xC0]
+ vextractf128 xmm1, ymm1, 1
+ vmovaps xmmword ptr [rbp-0xD0], xmm1
+ mov rax, qword ptr [rbp-0xD0]
+ mov qword ptr [rbp-0xE0], rax
+ movzx rax, byte ptr [rbp-0xE0]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xD8], al
+ movzx rax, byte ptr [rbp-0xDF]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xD7], al
+ movzx rax, byte ptr [rbp-0xDE]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xD6], al
+ movzx rax, byte ptr [rbp-0xDD]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xD5], al
+ movzx rax, byte ptr [rbp-0xDC]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xD4], al
+ movzx rax, byte ptr [rbp-0xDB]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xD3], al
+ movzx rax, byte ptr [rbp-0xDA]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xD2], al
+ movzx rax, byte ptr [rbp-0xD9]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xD1], al
+ mov rsi, qword ptr [rbp-0xD8]
+ mov rax, qword ptr [rbp-0xC8]
+ mov qword ptr [rbp-0xF0], rax
+ movzx rax, byte ptr [rbp-0xF0]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xE8], al
+ movzx rax, byte ptr [rbp-0xEF]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xE7], al
+ ;; size=322 bbWeight=1 PerfScore 396.50
G_M7625_IG06:
- mov rdi, qword ptr [rbp-0xC8]
- mov qword ptr [rbp-0xE0], r15
- mov qword ptr [rbp-0xD8], rdi
- vmovaps xmm1, xmmword ptr [rbp-0xE0]
- vmovaps xmmword ptr [rbp-0xA0], xmm1
- vmovups ymm0, ymmword ptr [rbp-0x90]
- vextractf128 xmm0, ymm0, 1
- vmovaps xmmword ptr [rbp-0xF0], xmm0
- mov rdi, qword ptr [rbp-0xF0]
- mov qword ptr [rbp-0x100], rdi
- xor r15d, r15d
- ;; size=76 bbWeight=1 PerfScore 16.25
+ movzx rax, byte ptr [rbp-0xEE]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xE6], al
+ movzx rax, byte ptr [rbp-0xED]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xE5], al
+ movzx rax, byte ptr [rbp-0xEC]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xE4], al
+ movzx rax, byte ptr [rbp-0xEB]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xE3], al
+ movzx rax, byte ptr [rbp-0xEA]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xE2], al
+ movzx rax, byte ptr [rbp-0xE9]
+ xor edx, edx
+ div edx:eax, ecx
+ mov byte ptr [rbp-0xE1], al
+ mov rax, qword ptr [rbp-0xE8]
+ mov qword ptr [rbp-0x100], rsi
+ mov qword ptr [rbp-0xF8], rax
+ vinserti128 ymm1, ymm2, xmmword ptr [rbp-0x100], 1
+ vmovups ymmword ptr [rdi], ymm0
+ vmovups ymmword ptr [rdi+0x20], ymm1
+ mov rax, rdi
+ ;; size=145 bbWeight=1 PerfScore 174.75
G_M7625_IG07:
- lea rdi, [rbp-0x100]
- movsxd r13, r15d
- movzx rdi, byte ptr [rdi+r13]
- mov esi, r14d
- mov rax, 0xD1FFAB1E ; code for System.Runtime.Intrinsics.Scalar`1[ubyte]:Divide(ubyte,ubyte):ubyte
- call [rax]System.Runtime.Intrinsics.Scalar`1[ubyte]:Divide(ubyte,ubyte):ubyte
- lea rdi, [rbp-0xF8]
- mov byte ptr [rdi+r13], al
- inc r15d
- cmp r15d, 8
- jl SHORT G_M7625_IG07
- ;; size=50 bbWeight=4 PerfScore 37.00
-G_M7625_IG08:
- mov r15, qword ptr [rbp-0xF8]
- mov rdi, qword ptr [rbp-0xE8]
- mov qword ptr [rbp-0x110], rdi
- xor r13d, r13d
- ;; size=24 bbWeight=1 PerfScore 3.25
-G_M7625_IG09:
- lea rdi, [rbp-0x110]
- movsxd r12, r13d
- movzx rdi, byte ptr [rdi+r12]
- mov esi, r14d
- mov rax, 0xD1FFAB1E ; code for System.Runtime.Intrinsics.Scalar`1[ubyte]:Divide(ubyte,ubyte):ubyte
- call [rax]System.Runtime.Intrinsics.Scalar`1[ubyte]:Divide(ubyte,ubyte):ubyte
- lea rsi, [rbp-0x108]
- mov byte ptr [rsi+r12], al
- inc r13d
- cmp r13d, 8
- jl SHORT G_M7625_IG09
- ;; size=50 bbWeight=4 PerfScore 37.00
-G_M7625_IG10:
- mov rsi, qword ptr [rbp-0x108]
- mov qword ptr [rbp-0x120], r15
- mov qword ptr [rbp-0x118], rsi
- vmovaps xmm1, xmmword ptr [rbp-0xA0]
- vinserti128 ymm0, ymm1, xmmword ptr [rbp-0x120], 1
- vmovups ymmword ptr [rbp-0x50], ymm0
- vmovups ymm1, ymmword ptr [rbp+0x30]
- vmovups ymmword ptr [rsp], ymm1
- mov esi, r14d
- lea rdi, [rbp-0x70]
- mov rax, 0xD1FFAB1E ; code for System.Runtime.Intrinsics.Vector256`1[ubyte]:op_Division(System.Runtime.Intrinsics.Vector256`1[ubyte],ubyte):System.Runtime.Intrinsics.Vector256`1[ubyte]
- call [rax]System.Runtime.Intrinsics.Vector256`1[ubyte]:op_Division(System.Runtime.Intrinsics.Vector256`1[ubyte],ubyte):System.Runtime.Intrinsics.Vector256`1[ubyte]
- vmovups ymm0, ymmword ptr [rbp-0x50]
- vmovups ymmword ptr [rsp], ymm0
- vmovups ymm0, ymmword ptr [rbp-0x70]
- vmovups ymmword ptr [rsp+0x20], ymm0
- mov rdi, rbx
- mov rax, 0xD1FFAB1E ; code for System.Runtime.Intrinsics.Vector512:Create[ubyte](System.Runtime.Intrinsics.Vector256`1[ubyte],System.Runtime.Intrinsics.Vector256`1[ubyte]):System.Runtime.Intrinsics.Vector512`1[ubyte]
- call [rax]System.Runtime.Intrinsics.Vector512:Create[ubyte](System.Runtime.Intrinsics.Vector256`1[ubyte],System.Runtime.Intrinsics.Vector256`1[ubyte]):System.Runtime.Intrinsics.Vector512`1[ubyte]
- mov rax, rbx
- ;; size=112 bbWeight=1 PerfScore 33.75
-G_M7625_IG11:
vzeroupper
- add rsp, 312
- pop rbx
- pop r12
- pop r13
- pop r14
- pop r15
+ add rsp, 256
pop rbp
ret
- ;; size=21 bbWeight=1 PerfScore 5.25
+ ;; size=12 bbWeight=1 PerfScore 2.75
-; Total bytes of code 531, prolog size 25, PerfScore 225.50, instruction count 109, allocated bytes for code 531 (MethodHash=ae93e236) for method System.Runtime.Intrinsics.Vector512`1[ubyte]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Divide(System.Runtime.Intrinsics.Vector512`1[ubyte],ubyte):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
+; Total bytes of code 1202, prolog size 16, PerfScore 1815.50, instruction count 313, allocated bytes for code 1202 (MethodHash=ae93e236) for method System.Runtime.Intrinsics.Vector512`1[ubyte]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Divide(System.Runtime.Intrinsics.Vector512`1[ubyte],ubyte):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)Larger list of diffs: https://gist.github.com/MihuBot/2e6b570f129278754cbc7faa290ec7da |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Job completed in 26 minutes.
dotnet/runtime#103095
Diffs
Diffs
Artifacts:
The text was updated successfully, but these errors were encountered: