Some instructions were missing, other implemented falsely. this patch aims at amending those issues. full list:

vcvtps2pd
vcvtudq2pd
vcvtps2qq
vcvttps2qq
vcvtps2uqq
vcvttps2uqq

variants are:

[Dst]XMM(zero-masked/merge-masked/unmasked)
[Src]Mem64

Differential Revision: https://reviews.llvm.org/D26799

llvm-svn: 287500
This commit is contained in:
Coby Tayree 2016-11-20 17:09:56 +00:00
parent 5fadce4a3f
commit 97e9cf62f4
3 changed files with 135 additions and 8 deletions

View File

@ -6096,14 +6096,14 @@ def : Pat<(f32 (fpround FR64X:$src)),
multiclass avx512_vcvt_fp<bits<8> opc, string OpcodeStr, X86VectorVTInfo _, multiclass avx512_vcvt_fp<bits<8> opc, string OpcodeStr, X86VectorVTInfo _,
X86VectorVTInfo _Src, SDNode OpNode, X86VectorVTInfo _Src, SDNode OpNode,
string Broadcast = _.BroadcastStr, string Broadcast = _.BroadcastStr,
string Alias = ""> { string Alias = "", X86MemOperand MemOp = _Src.MemOp> {
defm rr : AVX512_maskable<opc, MRMSrcReg, _, (outs _.RC:$dst), defm rr : AVX512_maskable<opc, MRMSrcReg, _, (outs _.RC:$dst),
(ins _Src.RC:$src), OpcodeStr, "$src", "$src", (ins _Src.RC:$src), OpcodeStr, "$src", "$src",
(_.VT (OpNode (_Src.VT _Src.RC:$src)))>, EVEX; (_.VT (OpNode (_Src.VT _Src.RC:$src)))>, EVEX;
defm rm : AVX512_maskable<opc, MRMSrcMem, _, (outs _.RC:$dst), defm rm : AVX512_maskable<opc, MRMSrcMem, _, (outs _.RC:$dst),
(ins _Src.MemOp:$src), OpcodeStr#Alias, "$src", "$src", (ins MemOp:$src), OpcodeStr#Alias, "$src", "$src",
(_.VT (OpNode (_Src.VT (_.VT (OpNode (_Src.VT
(bitconvert (_Src.LdFrag addr:$src)))))>, EVEX; (bitconvert (_Src.LdFrag addr:$src)))))>, EVEX;
@ -6144,7 +6144,7 @@ multiclass avx512_cvtps2pd<bits<8> opc, string OpcodeStr> {
} }
let Predicates = [HasVLX] in { let Predicates = [HasVLX] in {
defm Z128 : avx512_vcvt_fp<opc, OpcodeStr, v2f64x_info, v4f32x_info, defm Z128 : avx512_vcvt_fp<opc, OpcodeStr, v2f64x_info, v4f32x_info,
X86vfpext, "{1to2}">, EVEX_V128; X86vfpext, "{1to2}", "", f64mem>, EVEX_V128;
defm Z256 : avx512_vcvt_fp<opc, OpcodeStr, v4f64x_info, v4f32x_info, fpextend>, defm Z256 : avx512_vcvt_fp<opc, OpcodeStr, v4f64x_info, v4f32x_info, fpextend>,
EVEX_V256; EVEX_V256;
} }
@ -6203,7 +6203,7 @@ multiclass avx512_cvtdq2pd<bits<8> opc, string OpcodeStr, SDNode OpNode,
let Predicates = [HasVLX] in { let Predicates = [HasVLX] in {
defm Z128 : avx512_vcvt_fp<opc, OpcodeStr, v2f64x_info, v4i32x_info, defm Z128 : avx512_vcvt_fp<opc, OpcodeStr, v2f64x_info, v4i32x_info,
OpNode128, "{1to2}">, EVEX_V128; OpNode128, "{1to2}", "", i64mem>, EVEX_V128;
defm Z256 : avx512_vcvt_fp<opc, OpcodeStr, v4f64x_info, v4i32x_info, OpNode>, defm Z256 : avx512_vcvt_fp<opc, OpcodeStr, v4f64x_info, v4i32x_info, OpNode>,
EVEX_V256; EVEX_V256;
} }
@ -6375,7 +6375,7 @@ multiclass avx512_cvtps2qq<bits<8> opc, string OpcodeStr,
// Explicitly specified broadcast string, since we take only 2 elements // Explicitly specified broadcast string, since we take only 2 elements
// from v4f32x_info source // from v4f32x_info source
defm Z128 : avx512_vcvt_fp<opc, OpcodeStr, v2i64x_info, v4f32x_info, OpNode, defm Z128 : avx512_vcvt_fp<opc, OpcodeStr, v2i64x_info, v4f32x_info, OpNode,
"{1to2}">, EVEX_V128; "{1to2}", "", f64mem>, EVEX_V128;
defm Z256 : avx512_vcvt_fp<opc, OpcodeStr, v4i64x_info, v4f32x_info, OpNode>, defm Z256 : avx512_vcvt_fp<opc, OpcodeStr, v4i64x_info, v4f32x_info, OpNode>,
EVEX_V256; EVEX_V256;
} }
@ -6393,7 +6393,7 @@ multiclass avx512_cvttps2qq<bits<8> opc, string OpcodeStr,
// Explicitly specified broadcast string, since we take only 2 elements // Explicitly specified broadcast string, since we take only 2 elements
// from v4f32x_info source // from v4f32x_info source
defm Z128 : avx512_vcvt_fp<opc, OpcodeStr, v2i64x_info, v4f32x_info, OpNode, defm Z128 : avx512_vcvt_fp<opc, OpcodeStr, v2i64x_info, v4f32x_info, OpNode,
"{1to2}">, EVEX_V128; "{1to2}", "", f64mem>, EVEX_V128;
defm Z256 : avx512_vcvt_fp<opc, OpcodeStr, v4i64x_info, v4f32x_info, OpNode>, defm Z256 : avx512_vcvt_fp<opc, OpcodeStr, v4i64x_info, v4f32x_info, OpNode>,
EVEX_V256; EVEX_V256;
} }
@ -6428,8 +6428,8 @@ multiclass avx512_cvtqq2ps<bits<8> opc, string OpcodeStr,
} }
} }
defm VCVTDQ2PD : avx512_cvtdq2pd<0xE6, "vcvtdq2pd", sint_to_fp, X86cvtdq2pd>, XS, defm VCVTDQ2PD : avx512_cvtdq2pd<0xE6, "vcvtdq2pd", sint_to_fp, X86cvtdq2pd>,
EVEX_CD8<32, CD8VH>; XS, EVEX_CD8<32, CD8VH>;
defm VCVTDQ2PS : avx512_cvtdq2ps<0x5B, "vcvtdq2ps", sint_to_fp, defm VCVTDQ2PS : avx512_cvtdq2ps<0x5B, "vcvtdq2ps", sint_to_fp,
X86VSintToFpRnd>, X86VSintToFpRnd>,

View File

@ -1343,3 +1343,32 @@
// CHECK: vcvtuqq2ps xmm16, ymmword ptr [rax] // CHECK: vcvtuqq2ps xmm16, ymmword ptr [rax]
// CHECK: encoding: [0x62,0xe1,0xff,0x28,0x7a,0x00] // CHECK: encoding: [0x62,0xe1,0xff,0x28,0x7a,0x00]
vcvtuqq2psy xmm16, ymmword ptr [rax] vcvtuqq2psy xmm16, ymmword ptr [rax]
// CHECK: vcvtps2pd xmm1 {k2} {z}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7c,0x8a,0x5a,0x49,0x10]
vcvtps2pd xmm1 {k2} {z}, qword ptr [rcx+0x80]
// CHECK: vcvtps2pd xmm1 {k2}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7c,0x0a,0x5a,0x49,0x10]
vcvtps2pd xmm1 {k2}, qword ptr [rcx+0x80]
// CHECK: vcvtudq2pd xmm2 {k2} {z}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7e,0x8a,0x7a,0x51,0x10]
vcvtudq2pd xmm2 {k2} {z}, qword ptr [rcx+0x80]
// CHECK: vcvtudq2pd xmm2 {k2}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7e,0x0a,0x7a,0x51,0x10]
vcvtudq2pd xmm2 {k2}, qword ptr [rcx+0x80]
// CHECK: vcvtudq2pd xmm2, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7e,0x08,0x7a,0x51,0x10]
vcvtudq2pd xmm2, qword ptr [rcx+0x80]
// CHECK: vcvtdq2pd xmm2 {k1}, qword ptr [rcx]
// CHECK: encoding: [0x62,0xf1,0x7e,0x09,0xe6,0x11]
vcvtdq2pd xmm2 {k1}, qword ptr [rcx]
// CHECK: vcvtdq2pd xmm2 {k1} {z}, qword ptr [rcx]
// CHECK: encoding: [0x62,0xf1,0x7e,0x89,0xe6,0x11]
vcvtdq2pd xmm2 {k1} {z}, qword ptr [rcx]

View File

@ -0,0 +1,98 @@
// RUN: llvm-mc -triple x86_64-unknown-unknown -mcpu=knl -mattr=+avx512vl -mattr=+avx512dq -x86-asm-syntax=intel -output-asm-variant=1 --show-encoding %s | FileCheck %s
// CHECK: vcvtps2qq xmm2 {k2} {z}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x8a,0x7b,0x51,0x10]
vcvtps2qq xmm2 {k2} {z}, qword ptr [rcx + 0x80]
// CHECK: vcvtps2qq xmm2 {k2}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x0a,0x7b,0x51,0x10]
vcvtps2qq xmm2 {k2}, qword ptr [rcx + 0x80]
// CHECK: vcvtps2qq xmm2, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x08,0x7b,0x51,0x10]
vcvtps2qq xmm2, qword ptr [rcx + 0x80]
// CHECK: vcvttps2qq xmm1 {k2} {z}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x8a,0x7a,0x49,0x10]
vcvttps2qq xmm1 {k2} {z}, qword ptr [rcx + 0x80]
// CHECK: vcvttps2qq xmm1 {k2}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x0a,0x7a,0x49,0x10]
vcvttps2qq xmm1 {k2}, qword ptr [rcx + 0x80]
// CHECK: vcvttps2qq xmm1, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x08,0x7a,0x49,0x10]
vcvttps2qq xmm1, qword ptr [rcx + 0x80]
// CHECK: vcvtps2uqq xmm1 {k2} {z}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x8a,0x79,0x49,0x10]
vcvtps2uqq xmm1 {k2} {z}, qword ptr [rcx + 128]
// CHECK: vcvtps2uqq xmm1 {k2}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x0a,0x79,0x49,0x10]
vcvtps2uqq xmm1 {k2}, qword ptr [rcx + 128]
// CHECK: vcvtps2uqq xmm1, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x08,0x79,0x49,0x10]
vcvtps2uqq xmm1, qword ptr [rcx + 128]
// CHECK: vcvttps2uqq xmm1 {k2} {z}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x8a,0x78,0x49,0x10]
vcvttps2uqq xmm1 {k2} {z}, qword ptr [rcx + 128]
// CHECK: vcvttps2uqq xmm1 {k2}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x0a,0x78,0x49,0x10]
vcvttps2uqq xmm1 {k2}, qword ptr [rcx + 128]
// CHECK: vcvttps2uqq xmm1, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x08,0x78,0x49,0x10]
vcvttps2uqq xmm1, qword ptr [rcx + 128]
// RUN: llvm-mc -triple x86_64-unknown-unknown -mcpu=knl -mattr=+avx512vl -mattr=+avx512dq -x86-asm-syntax=intel -output-asm-variant=1 --show-encoding %s | FileCheck %s
// CHECK: vcvtps2qq xmm2 {k2} {z}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x8a,0x7b,0x51,0x10]
vcvtps2qq xmm2 {k2} {z}, qword ptr [rcx + 0x80]
// CHECK: vcvtps2qq xmm2 {k2}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x0a,0x7b,0x51,0x10]
vcvtps2qq xmm2 {k2}, qword ptr [rcx + 0x80]
// CHECK: vcvtps2qq xmm2, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x08,0x7b,0x51,0x10]
vcvtps2qq xmm2, qword ptr [rcx + 0x80]
// CHECK: vcvttps2qq xmm1 {k2} {z}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x8a,0x7a,0x49,0x10]
vcvttps2qq xmm1 {k2} {z}, qword ptr [rcx + 0x80]
// CHECK: vcvttps2qq xmm1 {k2}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x0a,0x7a,0x49,0x10]
vcvttps2qq xmm1 {k2}, qword ptr [rcx + 0x80]
// CHECK: vcvttps2qq xmm1, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x08,0x7a,0x49,0x10]
vcvttps2qq xmm1, qword ptr [rcx + 0x80]
// CHECK: vcvtps2uqq xmm1 {k2} {z}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x8a,0x79,0x49,0x10]
vcvtps2uqq xmm1 {k2} {z}, qword ptr [rcx + 128]
// CHECK: vcvtps2uqq xmm1 {k2}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x0a,0x79,0x49,0x10]
vcvtps2uqq xmm1 {k2}, qword ptr [rcx + 128]
// CHECK: vcvtps2uqq xmm1, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x08,0x79,0x49,0x10]
vcvtps2uqq xmm1, qword ptr [rcx + 128]
// CHECK: vcvttps2uqq xmm1 {k2} {z}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x8a,0x78,0x49,0x10]
vcvttps2uqq xmm1 {k2} {z}, qword ptr [rcx + 128]
// CHECK: vcvttps2uqq xmm1 {k2}, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x0a,0x78,0x49,0x10]
vcvttps2uqq xmm1 {k2}, qword ptr [rcx + 128]
// CHECK: vcvttps2uqq xmm1, qword ptr [rcx + 128]
// CHECK: encoding: [0x62,0xf1,0x7d,0x08,0x78,0x49,0x10]
vcvttps2uqq xmm1, qword ptr [rcx + 128]