[AVX512][BUILTIN][vpermilps][intrinsics] Fixing two incorrect IMM check.

[m_zuckerman]

Summary

By SPEC, instruction vpermilps gets IMM bigger than 15.
Below, you can see that IMM can be any number between 0 to 255 include.

SELECT4(src, control){
CASE(control[1:0])
0: tmp[31:0] := src[31:0]
1: tmp[31:0] := src[63:32]
2: tmp[31:0] := src[95:64]
3: tmp[31:0] := src[127:96]
ESAC
RETURN tmp[31:0]
}

tmp_dst[31:0] := SELECT4(a[127:0], imm8[1:0])
tmp_dst[63:32] := SELECT4(a[127:0], imm8[3:2])
tmp_dst[95:64] := SELECT4(a[127:0], imm8[5:4])
tmp_dst[127:96] := SELECT4(a[127:0], imm8[7:6])
FOR j := 0 to 3
i := j*32
IF k[j]

		dst[i+31:i] := tmp_dst[i+31:i]

ELSE

		dst[i+31:i] := src[i+31:i]

FI
ENDFOR
dst[MAX:128] := 0

[igorb]

LGTM

[craig.topper]

lib/Sema/SemaChecking.cpp

1568

Can you put these adjacent to vpermilps512_mask?

[m_zuckerman]

No problem

lib/Sema/SemaChecking.cpp

bool Sema::CheckX86BuiltinFunctionCall(unsigned BuiltinID, CallExpr *TheCall) {
   case X86::BI__builtin_ia32_extractf32x4_256_mask:
   case X86::BI__builtin_ia32_extracti32x4_256_mask:
     i = 1; l = 0; u = 1;
     break;
   case X86::BI_mm_prefetch:
   case X86::BI__builtin_ia32_extractf32x4_mask:
   case X86::BI__builtin_ia32_extracti32x4_mask:
   case X86::BI__builtin_ia32_vpermilpd_mask:
-  case X86::BI__builtin_ia32_vpermilps_mask:
   case X86::BI__builtin_ia32_extractf64x2_512_mask:
   case X86::BI__builtin_ia32_extracti64x2_512_mask:
     i = 1; l = 0; u = 3;
     break;
   case X86::BI__builtin_ia32_insertf32x8_mask:
   case X86::BI__builtin_ia32_inserti32x8_mask:
   case X86::BI__builtin_ia32_insertf64x4_mask:
   case X86::BI__builtin_ia32_inserti64x4_mask:
bool Sema::CheckX86BuiltinFunctionCall(unsigned BuiltinID, CallExpr *TheCall) {
   case X86::BI__builtin_ia32_vpcomq:
     i = 2; l = 0; u = 7;
     break;
   case X86::BI__builtin_ia32_roundps:
   case X86::BI__builtin_ia32_roundpd:
   case X86::BI__builtin_ia32_roundps256:
   case X86::BI__builtin_ia32_roundpd256:
   case X86::BI__builtin_ia32_vpermilpd256_mask:
-  case X86::BI__builtin_ia32_vpermilps256_mask:
     i = 1; l = 0; u = 15;
     break;
   case X86::BI__builtin_ia32_roundss:
   case X86::BI__builtin_ia32_roundsd:
   case X86::BI__builtin_ia32_rangepd128_mask:
   case X86::BI__builtin_ia32_rangepd256_mask:
   case X86::BI__builtin_ia32_rangepd512_mask:
   case X86::BI__builtin_ia32_rangeps128_mask:
bool Sema::CheckX86BuiltinFunctionCall(unsigned BuiltinID, CallExpr *TheCall) {
   case X86::BI__builtin_ia32_fpclasspd128_mask:
   case X86::BI__builtin_ia32_fpclasspd256_mask:
   case X86::BI__builtin_ia32_fpclassps128_mask:
   case X86::BI__builtin_ia32_fpclassps256_mask:
   case X86::BI__builtin_ia32_fpclassps512_mask:
   case X86::BI__builtin_ia32_fpclasspd512_mask:
   case X86::BI__builtin_ia32_fpclasssd_mask:
   case X86::BI__builtin_ia32_fpclassss_mask:
+  case X86::BI__builtin_ia32_vpermilps_mask:
+  case X86::BI__builtin_ia32_vpermilps256_mask:
     i = 1; l = 0; u = 255;
     break;
   case X86::BI__builtin_ia32_palignr:
   case X86::BI__builtin_ia32_insertps128:
   case X86::BI__builtin_ia32_dpps:
   case X86::BI__builtin_ia32_dppd:
   case X86::BI__builtin_ia32_dpps256:
   case X86::BI__builtin_ia32_mpsadbw128: