maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Target/X86/Utils/X86ShuffleDecode.cpp

218 lines
7.1 KiB
C++
Raw Normal View History

[AVX] Add decode support for VUNPCKLPS/D instructions, both 128-bit and 256-bit forms. Because the number of elements in a vector does not determine the vector type (4 elements could be v4f32 or v4f64), pass the full type of the vector to decode routines. llvm-svn: 126664
2011-03-01 03:06:56 +08:00
//===-- X86ShuffleDecode.cpp - X86 shuffle decode logic -------------------===//
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// Define several functions to decode x86 specific shuffle semantics into a
// generic vector mask.
//
//===----------------------------------------------------------------------===//
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
#include "X86ShuffleDecode.h"
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
//===----------------------------------------------------------------------===//
// Vector Mask Decoding
//===----------------------------------------------------------------------===//
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
namespace llvm {
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
Move insertps mask decoding to header file llvm-svn: 112896
2010-09-03 06:43:39 +08:00
void DecodeINSERTPSMask(unsigned Imm, SmallVectorImpl<unsigned> &ShuffleMask) {
// Defaults the copying the dest value.
ShuffleMask.push_back(0);
ShuffleMask.push_back(1);
ShuffleMask.push_back(2);
ShuffleMask.push_back(3);
// Decode the immediate.
unsigned ZMask = Imm & 15;
unsigned CountD = (Imm >> 4) & 3;
unsigned CountS = (Imm >> 6) & 3;
// CountS selects which input element to use.
unsigned InVal = 4+CountS;
// CountD specifies which element of destination to update.
ShuffleMask[CountD] = InVal;
// ZMask zaps values, potentially overriding the CountD elt.
if (ZMask & 1) ShuffleMask[0] = SM_SentinelZero;
if (ZMask & 2) ShuffleMask[1] = SM_SentinelZero;
if (ZMask & 4) ShuffleMask[2] = SM_SentinelZero;
if (ZMask & 8) ShuffleMask[3] = SM_SentinelZero;
}
Move decoding of insertps back to avoid unused warnings in x86 isel lowering, and fix movlhps/movhlps to decode 4 elements shuffles llvm-svn: 112869
2010-09-03 05:51:11 +08:00
// <3,1> or <6,7,2,3>
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
void DecodeMOVHLPSMask(unsigned NElts,
SmallVectorImpl<unsigned> &ShuffleMask) {
Move decoding of insertps back to avoid unused warnings in x86 isel lowering, and fix movlhps/movhlps to decode 4 elements shuffles llvm-svn: 112869
2010-09-03 05:51:11 +08:00
for (unsigned i = NElts/2; i != NElts; ++i)
ShuffleMask.push_back(NElts+i);
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
Move decoding of insertps back to avoid unused warnings in x86 isel lowering, and fix movlhps/movhlps to decode 4 elements shuffles llvm-svn: 112869
2010-09-03 05:51:11 +08:00
for (unsigned i = NElts/2; i != NElts; ++i)
ShuffleMask.push_back(i);
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
}
Move decoding of insertps back to avoid unused warnings in x86 isel lowering, and fix movlhps/movhlps to decode 4 elements shuffles llvm-svn: 112869
2010-09-03 05:51:11 +08:00
// <0,2> or <0,1,4,5>
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
void DecodeMOVLHPSMask(unsigned NElts,
SmallVectorImpl<unsigned> &ShuffleMask) {
Move decoding of insertps back to avoid unused warnings in x86 isel lowering, and fix movlhps/movhlps to decode 4 elements shuffles llvm-svn: 112869
2010-09-03 05:51:11 +08:00
for (unsigned i = 0; i != NElts/2; ++i)
ShuffleMask.push_back(i);
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
Move decoding of insertps back to avoid unused warnings in x86 isel lowering, and fix movlhps/movhlps to decode 4 elements shuffles llvm-svn: 112869
2010-09-03 05:51:11 +08:00
for (unsigned i = 0; i != NElts/2; ++i)
ShuffleMask.push_back(NElts+i);
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
}
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
void DecodePSHUFMask(unsigned NElts, unsigned Imm,
SmallVectorImpl<unsigned> &ShuffleMask) {
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
for (unsigned i = 0; i != NElts; ++i) {
ShuffleMask.push_back(Imm % NElts);
Imm /= NElts;
}
}
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
void DecodePSHUFHWMask(unsigned Imm,
SmallVectorImpl<unsigned> &ShuffleMask) {
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
ShuffleMask.push_back(0);
ShuffleMask.push_back(1);
ShuffleMask.push_back(2);
ShuffleMask.push_back(3);
for (unsigned i = 0; i != 4; ++i) {
ShuffleMask.push_back(4+(Imm & 3));
Imm >>= 2;
}
}
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
void DecodePSHUFLWMask(unsigned Imm,
SmallVectorImpl<unsigned> &ShuffleMask) {
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
for (unsigned i = 0; i != 4; ++i) {
ShuffleMask.push_back((Imm & 3));
Imm >>= 2;
}
ShuffleMask.push_back(4);
ShuffleMask.push_back(5);
ShuffleMask.push_back(6);
ShuffleMask.push_back(7);
}
[AVX] Add decode support for VUNPCKLPS/D instructions, both 128-bit and 256-bit forms. Because the number of elements in a vector does not determine the vector type (4 elements could be v4f32 or v4f64), pass the full type of the vector to decode routines. llvm-svn: 126664
2011-03-01 03:06:56 +08:00
void DecodePUNPCKLBWMask(unsigned NElts,
SmallVectorImpl<unsigned> &ShuffleMask) {
DecodeUNPCKLPMask(MVT::getVectorVT(MVT::i8, NElts), ShuffleMask);
}
void DecodePUNPCKLWDMask(unsigned NElts,
SmallVectorImpl<unsigned> &ShuffleMask) {
DecodeUNPCKLPMask(MVT::getVectorVT(MVT::i16, NElts), ShuffleMask);
}
void DecodePUNPCKLDQMask(unsigned NElts,
SmallVectorImpl<unsigned> &ShuffleMask) {
DecodeUNPCKLPMask(MVT::getVectorVT(MVT::i32, NElts), ShuffleMask);
}
void DecodePUNPCKLQDQMask(unsigned NElts,
SmallVectorImpl<unsigned> &ShuffleMask) {
DecodeUNPCKLPMask(MVT::getVectorVT(MVT::i64, NElts), ShuffleMask);
}
void DecodePUNPCKLMask(EVT VT,
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
SmallVectorImpl<unsigned> &ShuffleMask) {
[AVX] Add decode support for VUNPCKLPS/D instructions, both 128-bit and 256-bit forms. Because the number of elements in a vector does not determine the vector type (4 elements could be v4f32 or v4f64), pass the full type of the vector to decode routines. llvm-svn: 126664
2011-03-01 03:06:56 +08:00
DecodeUNPCKLPMask(VT, ShuffleMask);
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
}
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
void DecodePUNPCKHMask(unsigned NElts,
SmallVectorImpl<unsigned> &ShuffleMask) {
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
for (unsigned i = 0; i != NElts/2; ++i) {
ShuffleMask.push_back(i+NElts/2);
ShuffleMask.push_back(i+NElts+NElts/2);
}
}
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
void DecodeSHUFPSMask(unsigned NElts, unsigned Imm,
SmallVectorImpl<unsigned> &ShuffleMask) {
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
// Part that reads from dest.
for (unsigned i = 0; i != NElts/2; ++i) {
ShuffleMask.push_back(Imm % NElts);
Imm /= NElts;
}
// Part that reads from src.
for (unsigned i = 0; i != NElts/2; ++i) {
ShuffleMask.push_back(Imm % NElts + NElts);
Imm /= NElts;
}
}
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
void DecodeUNPCKHPMask(unsigned NElts,
SmallVectorImpl<unsigned> &ShuffleMask) {
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
for (unsigned i = 0; i != NElts/2; ++i) {
ShuffleMask.push_back(i+NElts/2); // Reads from dest
ShuffleMask.push_back(i+NElts+NElts/2); // Reads from src
}
}
[AVX] Add decode support for VUNPCKLPS/D instructions, both 128-bit and 256-bit forms. Because the number of elements in a vector does not determine the vector type (4 elements could be v4f32 or v4f64), pass the full type of the vector to decode routines. llvm-svn: 126664
2011-03-01 03:06:56 +08:00
void DecodeUNPCKLPSMask(unsigned NElts,
SmallVectorImpl<unsigned> &ShuffleMask) {
DecodeUNPCKLPMask(MVT::getVectorVT(MVT::i32, NElts), ShuffleMask);
}
void DecodeUNPCKLPDMask(unsigned NElts,
SmallVectorImpl<unsigned> &ShuffleMask) {
DecodeUNPCKLPMask(MVT::getVectorVT(MVT::i64, NElts), ShuffleMask);
}
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
/// DecodeUNPCKLPMask - This decodes the shuffle masks for unpcklps/unpcklpd
[AVX] Add decode support for VUNPCKLPS/D instructions, both 128-bit and 256-bit forms. Because the number of elements in a vector does not determine the vector type (4 elements could be v4f32 or v4f64), pass the full type of the vector to decode routines. llvm-svn: 126664
2011-03-01 03:06:56 +08:00
/// etc. VT indicates the type of the vector allowing it to handle different
/// datatypes and vector widths.
void DecodeUNPCKLPMask(EVT VT,
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
SmallVectorImpl<unsigned> &ShuffleMask) {
[AVX] Fix mask predicates for 256-bit UNPCKLPS/D and implement missing patterns for them. Add a SIMD test subdirectory to hold tests for SIMD instruction selection correctness and quality. ' llvm-svn: 126845
2011-03-03 01:23:43 +08:00
unsigned NumElts = VT.getVectorNumElements();
// Handle vector lengths > 128 bits. Define a "section" as a set of
// 128 bits. AVX defines UNPCK* to operate independently on 128-bit
// sections.
unsigned NumSections = VT.getSizeInBits() / 128;
if (NumSections == 0 ) NumSections = 1; // Handle MMX
unsigned NumSectionElts = NumElts / NumSections;
unsigned Start = 0;
unsigned End = NumSectionElts / 2;
for (unsigned s = 0; s < NumSections; ++s) {
for (unsigned i = Start; i != End; ++i) {
ShuffleMask.push_back(i); // Reads from dest/src1
ShuffleMask.push_back(i+NumSectionElts); // Reads from src/src2
}
// Process the next 128 bits.
Start += NumSectionElts;
End += NumSectionElts;
Move x86 specific shuffle mask decoding to its own header, it's also going to be used elsewhere. Also trim trailing whitespaces llvm-svn: 112846
2010-09-03 02:40:13 +08:00
}
}
Add support for 256-bit versions of VPERMIL instruction. This is a new instruction introduced in AVX, which can operate on 128 and 256-bit vectors. It considers a 256-bit vector as two independent 128-bit lanes. It can permute any 32 or 64 elements inside a lane, and restricts the second lane to have the same permutation of the first one. With the improved splat support introduced early today, adding codegen for this instruction enable more efficient 256-bit code: Instead of: vextractf128 $0, %ymm0, %xmm0 punpcklbw %xmm0, %xmm0 punpckhbw %xmm0, %xmm0 vinsertf128 $0, %xmm0, %ymm0, %ymm1 vinsertf128 $1, %xmm0, %ymm1, %ymm0 vextractf128 $1, %ymm0, %xmm1 shufps $1, %xmm1, %xmm1 movss %xmm1, 28(%rsp) movss %xmm1, 24(%rsp) movss %xmm1, 20(%rsp) movss %xmm1, 16(%rsp) vextractf128 $0, %ymm0, %xmm0 shufps $1, %xmm0, %xmm0 movss %xmm0, 12(%rsp) movss %xmm0, 8(%rsp) movss %xmm0, 4(%rsp) movss %xmm0, (%rsp) vmovaps (%rsp), %ymm0 We get: vextractf128 $0, %ymm0, %xmm0 punpcklbw %xmm0, %xmm0 punpckhbw %xmm0, %xmm0 vinsertf128 $0, %xmm0, %ymm0, %ymm1 vinsertf128 $1, %xmm0, %ymm1, %ymm0 vpermilps $85, %ymm0, %ymm0 llvm-svn: 135662
2011-07-21 09:55:47 +08:00
void DecodeVPERMILPSMask(unsigned NElts, unsigned Imm,
SmallVectorImpl<unsigned> &ShuffleMask) {
DecodeVPERMILMask(MVT::getVectorVT(MVT::i32, NElts), Imm, ShuffleMask);
}
void DecodeVPERMILPDMask(unsigned NElts, unsigned Imm,
SmallVectorImpl<unsigned> &ShuffleMask) {
DecodeVPERMILMask(MVT::getVectorVT(MVT::i64, NElts), Imm, ShuffleMask);
}
// DecodeVPERMILMask - Decodes VPERMIL permutes for any 128-bit
// with 32/64-bit elements. For 256-bit vectors, it's considered
// as two 128 lanes and the mask of the first lane should be
// identical of the second one.
void DecodeVPERMILMask(EVT VT, unsigned Imm,
SmallVectorImpl<unsigned> &ShuffleMask) {
unsigned NumElts = VT.getVectorNumElements();
unsigned NumLanes = VT.getSizeInBits()/128;
for (unsigned l = 0; l != NumLanes; ++l) {
for (unsigned i = 0; i != NumElts/NumLanes; ++i) {
unsigned Idx = (Imm >> (i*2)) & 0x3 ;
ShuffleMask.push_back(Idx+(l*NumElts/NumLanes));
}
}
}
[AVX] Recorganize X86ShuffleDecode into its own library (LLVMX86Utils.a) to break cyclic library dependencies between LLVMX86CodeGen.a and LLVMX86AsmParser.a. Previously this code was in a header file and marked static but AVX requires some additional functionality here that won't be used by all clients. Since including unused static functions causes a gcc compiler warning, keeping it as a header would break builds that use -Werror. Putting this in its own library solves both problems at once. llvm-svn: 125765
2011-02-18 03:18:59 +08:00
} // llvm namespace