Merge branch 'dev'

doc/changelog.md

@@ -1,6 +1,6 @@
 # History
 
-* 2024/Oct/15 ver 7.20 Fixed the specification of setDefaultEncoding, setDefaultEncodingAVX10./
+* 2024/Oct/15 ver 7.20 Fixed the specification of setDefaultEncoding, setDefaultEncodingAVX10.
 * 2024/Oct/15 ver 7.11 Added full support for AVX10.2
 * 2024/Oct/13 ver 7.10 support AVX10 integer and fp16 vnni, media new instructions. setDefaultEncoding is extended.
 * 2024/Oct/10 ver 7.09.1 fix the names of vpcompressb and vpcompressw

doc/usage.md

@@ -148,6 +148,8 @@ feature|AVX-VNNI-INT8, AVX512-FP16|AVX10.2
 - Target functions: vmpsadbw, vpdpbssd, vpdpbssds, vpdpbsud, vpdpbsuds, vpdpbuud, vpdpbuuds, vpdpwsud vpdpwsuds vpdpwusd vpdpwusds vpdpwuud, vpdpwuuds, vmovd, vmovw
 
 - Remark: vmovd and vmovw several kinds of encoding such as AVX/AVX512F/AVX512-FP16/AVX10.2. 
+At first, I attempted to use EvexEncoding (resp. VexEncoding) instead of AVX10v2Encoding (resp. EvexEncoding) for `setDefaultEncodingAVX10`.
+But I abandoned this idea when I found that `vmovd` and `vmovw` had different EVEX encodings in AVX512 and AVX10.2
 
 ### Remark
 * `k1`, ..., `k7` are opmask registers.

readme.md

@@ -1,7 +1,7 @@
 
 # Xbyak 7.20 [![Badge Build]][Build Status]
 
-*A C++ JIT assembler for x86 (IA32), x64 (AMD64, x86-64)*
+*A JIT assembler for x86/x64 architectures supporting advanced instruction sets up to AVX10.2*
 
 ## Menu
 
@@ -11,15 +11,15 @@
 
 ## Abstract
 
-Xbyak is a C++ header library that enables dynamically to assemble x86(IA32), x64(AMD64, x86-64) mnemonic.
+Xbyak is a C++ header-only library that enables dynamic assembly of x86/x64 instructions using mnemonics.
 
-The pronunciation of Xbyak is `kəi-bja-k`.
-It is named from a Japanese word [開闢](https://translate.google.com/?hl=ja&sl=ja&tl=en&text=%E9%96%8B%E9%97%A2&op=translate), which means the beginning of the world.
+The pronunciation of Xbyak is `/kʌɪbjæk/` (kai-byak).
 
-## Feature
+The name is derived from the Japanese word [開闢](https://translate.google.com/?hl=ja&sl=ja&tl=en&text=%E9%96%8B%E9%97%A2&op=translate) (kaibyaku), which means "the beginning of the world" or "creation".
 
-- header file only
-- Intel/MASM like syntax
+## Features
+- Header-only library
+- Intel/MASM-like syntax
 - Full support for AVX-512, APX, and AVX10.2
 
 **Note**:
@@ -32,22 +32,22 @@ If you want to use them, then specify `-fno-operator-names` option to gcc/clang.
 
 ### News
 
-- support AVX10.2
-- support xresldtrk/xsusldtrk
-- support RAO-INT for APX
-- support AVX10 detection, AESKLE, WIDE_KL, KEYLOCKER, KEYLOCKER_WIDE
-- support APX except for a few instructions
-- add amx_fp16/avx_vnni_int8/avx_ne_convert/avx-ifma
-- add movdiri, movdir64b, clwb, cldemote
+- Support AVX10.2
+- Support xresldtrk/xsusldtrk
+- Support RAO-INT for APX
+- Support AVX10 detection, AESKLE, WIDE_KL, KEYLOCKER, KEYLOCKER_WIDE
+- Support APX except for a few instructions
+- Add amx_fp16/avx_vnni_int8/avx_ne_convert/avx-ifma
+- Add movdiri, movdir64b, clwb, cldemote
 - WAITPKG instructions (tpause, umonitor, umwait) are supported.
 - MmapAllocator supports memfd with user-defined strings. see sample/memfd.cpp
-- strictly check address offset disp32 in a signed 32-bit integer. e.g., `ptr[(void*)0xffffffff]` causes an error.
-  - define `XBYAK_OLD_DISP_CHECK` if you need an old check, but the option will be remoevd.
-- add `jmp(mem, T_FAR)`, `call(mem, T_FAR)` `retf()` for far absolute indirect jump.
-- vnni instructions such as vpdpbusd supports vex encoding.
-- (break backward compatibility) `push(byte, imm)` (resp. `push(word, imm)`) forces to cast `imm` to 8(resp. 16) bit.
+- Strictly check address offset disp32 in a signed 32-bit integer. e.g., `ptr[(void*)0xffffffff]` causes an error.
+  - Define `XBYAK_OLD_DISP_CHECK` if you need an old check, but the option will be remoevd.
+- Add `jmp(mem, T_FAR)`, `call(mem, T_FAR)` `retf()` for far absolute indirect jump.
+- VNNI instructions such as vpdpbusd supports vex encoding.
+- (Break backward compatibility) `push(byte, imm)` (resp. `push(word, imm)`) forces to cast `imm` to 8(resp. 16) bit.
 - (Windows) `#include <winsock2.h>` has been removed from xbyak.h, so add it explicitly if you need it.
-- support exception-less mode see. [Exception-less mode](#exception-less-mode)
+- Support exception-less mode see. [Exception-less mode](#exception-less-mode)
 - `XBYAK_USE_MMAP_ALLOCATOR` will be defined on Linux/macOS unless `XBYAK_DONT_USE_MMAP_ALLOCATOR` is defined.
 
 ### Supported OS

xbyak/xbyak.h

@@ -2794,6 +2794,30 @@ class CodeGenerator : public CodeArray {
 		}
 		opSSE(x, op, type1, code1, isXMM_XMMorMEM, imm);
 	}
+	// AVX10 zero-extending for vmovd, vmovw
+	void opAVX10ZeroExt(const Operand& op1, const Operand& op2, const uint64_t typeTbl[4], const int codeTbl[4], PreferredEncoding enc, int bit)
+	{
+		const Operand *p1 = &op1;
+		const Operand *p2 = &op2;
+		bool rev = false;
+		if (p1->isMEM()) {
+			std::swap(p1, p2);
+			rev = true;
+		}
+		if (p1->isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION)
+		if (p1->isXMM()) {
+			std::swap(p1, p2);
+			rev = !rev;
+		}
+		int sel = -1;
+		if (getEncoding(enc, 1) == AVX10v2Encoding) {
+			if ((p1->isXMM() || p1->isMEM()) && p2->isXMM()) sel = 2 + int(rev);
+		} else {
+			if ((p1->isREG(bit) || p1->isMEM()) && p2->isXMM()) sel = int(rev);
+		}
+		if (sel == -1) XBYAK_THROW(ERR_BAD_COMBINATION)
+		opAVX_X_X_XM(*static_cast<const Xmm*>(p2), xm0, *p1, typeTbl[sel], codeTbl[sel]);
+	}
 public:
 	unsigned int getVersion() const { return VERSION; }
 	using CodeArray::db;
@@ -3203,30 +3227,6 @@ class CodeGenerator : public CodeArray {
 		}
 		db(0xC8 + (idx & 7));
 	}
-	// AVX10 zero-extending for vmovd, vmovw
-	void opAVX10ZeroExt(const Operand& op1, const Operand& op2, const uint64_t typeTbl[4], const int codeTbl[4], PreferredEncoding enc, int bit)
-	{
-		const Operand *p1 = &op1;
-		const Operand *p2 = &op2;
-		bool rev = false;
-		if (p1->isMEM()) {
-			std::swap(p1, p2);
-			rev = true;
-		}
-		if (p1->isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION)
-		if (p1->isXMM()) {
-			std::swap(p1, p2);
-			rev = !rev;
-		}
-		int sel = -1;
-		if (getEncoding(enc, 1) == AVX10v2Encoding) {
-			if ((p1->isXMM() || p1->isMEM()) && p2->isXMM()) sel = 2 + int(rev);
-		} else {
-			if ((p1->isREG(bit) || p1->isMEM()) && p2->isXMM()) sel = int(rev);
-		}
-		if (sel == -1) XBYAK_THROW(ERR_BAD_COMBINATION)
-		opAVX_X_X_XM(*static_cast<const Xmm*>(p2), xm0, *p1, typeTbl[sel], codeTbl[sel]);
-	}
 	void vmovd(const Operand& op1, const Operand& op2, PreferredEncoding enc = DefaultEncoding)
 	{
 		const uint64_t typeTbl[] = {