[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
diff --git a/llvm/lib/Target/X86/Utils/X86ShuffleDecode.cpp b/llvm/lib/Target/X86/Utils/X86ShuffleDecode.cpp
index 12879774..76f4d3b 100644
--- a/llvm/lib/Target/X86/Utils/X86ShuffleDecode.cpp
+++ b/llvm/lib/Target/X86/Utils/X86ShuffleDecode.cpp
@@ -1,4 +1,4 @@
-//===-- X86ShuffleDecode.h - X86 shuffle decode logic ---------------------===//
+//===-- X86ShuffleDecode.cpp - X86 shuffle decode logic -------------------===//
//
// The LLVM Compiler Infrastructure
//
@@ -95,12 +95,29 @@
ShuffleMask.push_back(7);
}
-void DecodePUNPCKLMask(unsigned NElts,
+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,
SmallVectorImpl<unsigned> &ShuffleMask) {
- for (unsigned i = 0; i != NElts/2; ++i) {
- ShuffleMask.push_back(i);
- ShuffleMask.push_back(i+NElts);
- }
+ DecodeUNPCKLPMask(VT, ShuffleMask);
}
void DecodePUNPCKHMask(unsigned NElts,
@@ -133,12 +150,24 @@
}
}
+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);
+}
/// DecodeUNPCKLPMask - This decodes the shuffle masks for unpcklps/unpcklpd
-/// etc. NElts indicates the number of elements in the vector allowing it to
-/// handle different datatypes and vector widths.
-void DecodeUNPCKLPMask(unsigned NElts,
+/// etc. VT indicates the type of the vector allowing it to handle different
+/// datatypes and vector widths.
+void DecodeUNPCKLPMask(EVT VT,
SmallVectorImpl<unsigned> &ShuffleMask) {
+
+ int NElts = VT.getVectorNumElements();
+
for (unsigned i = 0; i != NElts/2; ++i) {
ShuffleMask.push_back(i); // Reads from dest
ShuffleMask.push_back(i+NElts); // Reads from src
diff --git a/llvm/lib/Target/X86/Utils/X86ShuffleDecode.h b/llvm/lib/Target/X86/Utils/X86ShuffleDecode.h
index 50d9ccb..b18f670 100644
--- a/llvm/lib/Target/X86/Utils/X86ShuffleDecode.h
+++ b/llvm/lib/Target/X86/Utils/X86ShuffleDecode.h
@@ -16,6 +16,7 @@
#define X86_SHUFFLE_DECODE_H
#include "llvm/ADT/SmallVector.h"
+#include "llvm/CodeGen/ValueTypes.h"
//===----------------------------------------------------------------------===//
// Vector Mask Decoding
@@ -45,7 +46,19 @@
void DecodePSHUFLWMask(unsigned Imm,
SmallVectorImpl<unsigned> &ShuffleMask);
-void DecodePUNPCKLMask(unsigned NElts,
+void DecodePUNPCKLBWMask(unsigned NElts,
+ SmallVectorImpl<unsigned> &ShuffleMask);
+
+void DecodePUNPCKLWDMask(unsigned NElts,
+ SmallVectorImpl<unsigned> &ShuffleMask);
+
+void DecodePUNPCKLDQMask(unsigned NElts,
+ SmallVectorImpl<unsigned> &ShuffleMask);
+
+void DecodePUNPCKLQDQMask(unsigned NElts,
+ SmallVectorImpl<unsigned> &ShuffleMask);
+
+void DecodePUNPCKLMask(EVT VT,
SmallVectorImpl<unsigned> &ShuffleMask);
void DecodePUNPCKHMask(unsigned NElts,
@@ -57,11 +70,16 @@
void DecodeUNPCKHPMask(unsigned NElts,
SmallVectorImpl<unsigned> &ShuffleMask);
+void DecodeUNPCKLPSMask(unsigned NElts,
+ SmallVectorImpl<unsigned> &ShuffleMask);
+
+void DecodeUNPCKLPDMask(unsigned NElts,
+ SmallVectorImpl<unsigned> &ShuffleMask);
/// DecodeUNPCKLPMask - This decodes the shuffle masks for unpcklps/unpcklpd
-/// etc. NElts indicates the number of elements in the vector allowing it to
-/// handle different datatypes and vector widths.
-void DecodeUNPCKLPMask(unsigned NElts,
+/// etc. VT indicates the type of the vector allowing it to handle different
+/// datatypes and vector widths.
+void DecodeUNPCKLPMask(EVT VT,
SmallVectorImpl<unsigned> &ShuffleMask);
} // llvm namespace