add alias of vcmpXX{ps,pd,ss,sd} for mask register

4 files changed, 150 insertions, 2 deletions

diff --git a/gen/gen_avx512.cpp b/gen/gen_avx512.cpp
index b2b88c3..f678e39 100644
--- a/gen/gen_avx512.cpp
+++ b/gen/gen_avx512.cpp
@@ -146,6 +146,23 @@ void putVcmp()
 	}
 }
 
+void putVcmpAlias()
+{
+	const char pred[32][16] = {
+		"eq", "lt", "le", "unord", "neq", "nlt", "nle", "ord",
+		"eq_uq", "nge", "ngt", "false", "neq_oq", "ge", "gt",
+		"true", "eq_os", "lt_oq", "le_oq", "unord_s", "neq_us", "nlt_uq", "nle_uq", "ord_s",
+		"eq_us", "nge_uq", "ngt_uq", "false_os", "neq_os", "ge_oq", "gt_oq", "true_us"
+	};
+	const char suf[][4] = { "pd", "ps", "sd", "ss" };
+	for (int i = 0; i < 4; i++) {
+		const char *s = suf[i];
+		for (int j = 0; j < 32; j++) {
+			printf("void vcmp%s%s(const Opmask& k, const Xmm& x, const Operand& op) { vcmp%s(k, x, op, %d); }\n", pred[j], s, s, j);
+		}
+	}
+}
+
 // XM_X
 void putX_XM()
 {
@@ -733,6 +750,7 @@ int main(int argc, char *[])
 		return 0;
 	}
 	putVcmp();
+	putVcmpAlias();
 	putX_XM();
 	putM_X();
 	putXM_X();
diff --git a/readme.md b/readme.md
index d0587b6..ad9ec00 100644
--- a/readme.md
+++ b/readme.md
@@ -1,6 +1,6 @@
 [![Build Status](https://github.com/herumi/xbyak/actions/workflows/main.yml/badge.svg)](https://github.com/herumi/xbyak/actions/workflows/main.yml)
 
-# Xbyak 5.993 ; JIT assembler for x86(IA32), x64(AMD64, x86-64) by C++
+# Xbyak 5.994 ; JIT assembler for x86(IA32), x64(AMD64, x86-64) by C++
 
 ## Abstract
 
@@ -446,6 +446,7 @@ modified new BSD License
 http://opensource.org/licenses/BSD-3-Clause
 
 ## History
+* 2021/Jun/17 ver 5.994 add alias of vcmpXX{ps,pd,ss,sd} with mask register
 * 2021/Jun/06 ver 5.993 strict check of gather/scatter register combination
 * 2021/May/09 ver 5.992 support endbr32 and endbr64
 * 2020/Nov/16 ver 5.991 disable constexpr for gcc-5 with -std=c++-14
diff --git a/readme.txt b/readme.txt
index 3fd57b0..6d50d62 100644
--- a/readme.txt
+++ b/readme.txt
@@ -1,5 +1,5 @@
 

-    C++用x86(IA-32), x64(AMD64, x86-64) JITアセンブラ Xbyak 5.993

+    C++用x86(IA-32), x64(AMD64, x86-64) JITアセンブラ Xbyak 5.994

 

 -----------------------------------------------------------------------------

 ◎概要

@@ -382,6 +382,7 @@ sample/{echo,hello}.bfは http://www.kmonos.net/alang/etc/brainfuck.php から
 -----------------------------------------------------------------------------

 ◎履歴

 

+2021/06/17 ver 5.994 マスクレジスタ用のvcmpXX{ps,pd,ss,sd}のalias追加

 2021/06/06 ver 5.993 gather/scatterのレジスタの組み合わせの厳密なチェック

 2021/05/09 ver 5.992 endbr32とendbr64のサポート

 2020/11/16 ver 5.991 g++-5のC++14でconstexpr機能の抑制

diff --git a/xbyak/xbyak_mnemonic.h b/xbyak/xbyak_mnemonic.h
index 9392afd..3483d5d 100644
--- a/xbyak/xbyak_mnemonic.h
+++ b/xbyak/xbyak_mnemonic.h
@@ -1755,10 +1755,138 @@ void vbroadcasti32x4(const Ymm& y, const Operand& op) { opAVX_X_XM_IMM(y, op, T_
 void vbroadcasti32x8(const Zmm& z, const Operand& op) { opAVX_X_XM_IMM(z, op, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW0 | T_N32, 0x5B); }
 void vbroadcasti64x2(const Ymm& y, const Operand& op) { opAVX_X_XM_IMM(y, op, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW1 | T_N16, 0x5A); }
 void vbroadcasti64x4(const Zmm& z, const Operand& op) { opAVX_X_XM_IMM(z, op, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW1 | T_N32, 0x5B); }
+void vcmpeq_ospd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 16); }
+void vcmpeq_osps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 16); }
+void vcmpeq_ossd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 16); }
+void vcmpeq_osss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 16); }
+void vcmpeq_uqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 8); }
+void vcmpeq_uqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 8); }
+void vcmpeq_uqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 8); }
+void vcmpeq_uqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 8); }
+void vcmpeq_uspd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 24); }
+void vcmpeq_usps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 24); }
+void vcmpeq_ussd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 24); }
+void vcmpeq_usss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 24); }
+void vcmpeqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 0); }
+void vcmpeqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 0); }
+void vcmpeqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 0); }
+void vcmpeqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 0); }
+void vcmpfalse_ospd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 27); }
+void vcmpfalse_osps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 27); }
+void vcmpfalse_ossd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 27); }
+void vcmpfalse_osss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 27); }
+void vcmpfalsepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 11); }
+void vcmpfalseps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 11); }
+void vcmpfalsesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 11); }
+void vcmpfalsess(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 11); }
+void vcmpge_oqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 29); }
+void vcmpge_oqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 29); }
+void vcmpge_oqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 29); }
+void vcmpge_oqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 29); }
+void vcmpgepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 13); }
+void vcmpgeps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 13); }
+void vcmpgesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 13); }
+void vcmpgess(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 13); }
+void vcmpgt_oqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 30); }
+void vcmpgt_oqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 30); }
+void vcmpgt_oqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 30); }
+void vcmpgt_oqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 30); }
+void vcmpgtpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 14); }
+void vcmpgtps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 14); }
+void vcmpgtsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 14); }
+void vcmpgtss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 14); }
+void vcmple_oqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 18); }
+void vcmple_oqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 18); }
+void vcmple_oqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 18); }
+void vcmple_oqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 18); }
+void vcmplepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 2); }
+void vcmpleps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 2); }
+void vcmplesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 2); }
+void vcmpless(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 2); }
+void vcmplt_oqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 17); }
+void vcmplt_oqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 17); }
+void vcmplt_oqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 17); }
+void vcmplt_oqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 17); }
+void vcmpltpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 1); }
+void vcmpltps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 1); }
+void vcmpltsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 1); }
+void vcmpltss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 1); }
+void vcmpneq_oqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 12); }
+void vcmpneq_oqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 12); }
+void vcmpneq_oqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 12); }
+void vcmpneq_oqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 12); }
+void vcmpneq_ospd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 28); }
+void vcmpneq_osps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 28); }
+void vcmpneq_ossd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 28); }
+void vcmpneq_osss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 28); }
+void vcmpneq_uspd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 20); }
+void vcmpneq_usps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 20); }
+void vcmpneq_ussd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 20); }
+void vcmpneq_usss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 20); }
+void vcmpneqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 4); }
+void vcmpneqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 4); }
+void vcmpneqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 4); }
+void vcmpneqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 4); }
+void vcmpnge_uqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 25); }
+void vcmpnge_uqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 25); }
+void vcmpnge_uqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 25); }
+void vcmpnge_uqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 25); }
+void vcmpngepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 9); }
+void vcmpngeps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 9); }
+void vcmpngesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 9); }
+void vcmpngess(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 9); }
+void vcmpngt_uqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 26); }
+void vcmpngt_uqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 26); }
+void vcmpngt_uqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 26); }
+void vcmpngt_uqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 26); }
+void vcmpngtpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 10); }
+void vcmpngtps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 10); }
+void vcmpngtsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 10); }
+void vcmpngtss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 10); }
+void vcmpnle_uqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 22); }
+void vcmpnle_uqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 22); }
+void vcmpnle_uqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 22); }
+void vcmpnle_uqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 22); }
+void vcmpnlepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 6); }
+void vcmpnleps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 6); }
+void vcmpnlesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 6); }
+void vcmpnless(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 6); }
+void vcmpnlt_uqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 21); }
+void vcmpnlt_uqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 21); }
+void vcmpnlt_uqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 21); }
+void vcmpnlt_uqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 21); }
+void vcmpnltpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 5); }
+void vcmpnltps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 5); }
+void vcmpnltsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 5); }
+void vcmpnltss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 5); }
+void vcmpord_spd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 23); }
+void vcmpord_sps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 23); }
+void vcmpord_ssd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 23); }
+void vcmpord_sss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 23); }
+void vcmpordpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 7); }
+void vcmpordps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 7); }
+void vcmpordsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 7); }
+void vcmpordss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 7); }
 void vcmppd(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_66 | T_0F | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0xC2, imm); }
 void vcmpps(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_0F | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0xC2, imm); }
 void vcmpsd(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_N8 | T_F2 | T_0F | T_EW1 | T_SAE_Z | T_MUST_EVEX, 0xC2, imm); }
 void vcmpss(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_N4 | T_F3 | T_0F | T_EW0 | T_SAE_Z | T_MUST_EVEX, 0xC2, imm); }
+void vcmptrue_uspd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 31); }
+void vcmptrue_usps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 31); }
+void vcmptrue_ussd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 31); }
+void vcmptrue_usss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 31); }
+void vcmptruepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 15); }
+void vcmptrueps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 15); }
+void vcmptruesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 15); }
+void vcmptruess(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 15); }
+void vcmpunord_spd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 19); }
+void vcmpunord_sps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 19); }
+void vcmpunord_ssd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 19); }
+void vcmpunord_sss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 19); }
+void vcmpunordpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 3); }
+void vcmpunordps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 3); }
+void vcmpunordsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 3); }
+void vcmpunordss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 3); }
 void vcompressb(const Operand& op, const Xmm& x) { opAVX_X_XM_IMM(x, op, T_N1 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x63); }
 void vcompresspd(const Operand& op, const Xmm& x) { opAVX_X_XM_IMM(x, op, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x8A); }
 void vcompressps(const Operand& op, const Xmm& x) { opAVX_X_XM_IMM(x, op, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x8A); }