From 60cfe541b278ae4d089e373e1b359106ae0cb339 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Fri, 24 May 2019 18:04:06 -0400 Subject: [PATCH] tcg/i386: Fix dupi/dupm for avx1 and 32-bit hosts The VBROADCASTSD instruction only allows %ymm registers as destination. Rather than forcing VEX.L and writing to the entire 256-bit register, revert to using MOVDDUP with an %xmm register. This is sufficient for an avx1 host since we do not support TCG_TYPE_V256 for that case. Also fix the 32-bit avx2, which should have used VPBROADCASTW. Fixes: 1e262b49b533 Backports commit 7b60ef3264e9627ac6efb34e9a6130647e9b55c0 from qemu --- qemu/tcg/i386/tcg-target.inc.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/qemu/tcg/i386/tcg-target.inc.c b/qemu/tcg/i386/tcg-target.inc.c index 7b714a75..98d4ea62 100644 --- a/qemu/tcg/i386/tcg-target.inc.c +++ b/qemu/tcg/i386/tcg-target.inc.c @@ -364,6 +364,7 @@ static inline int tcg_target_const_match(tcg_target_long val, TCGType type, #define OPC_MOVBE_MyGy (0xf1 | P_EXT38) #define OPC_MOVD_VyEy (0x6e | P_EXT | P_DATA16) #define OPC_MOVD_EyVy (0x7e | P_EXT | P_DATA16) +#define OPC_MOVDDUP (0x12 | P_EXT | P_SIMDF2) #define OPC_MOVDQA_VxWx (0x6f | P_EXT | P_DATA16) #define OPC_MOVDQA_WxVx (0x7f | P_EXT | P_DATA16) #define OPC_MOVDQU_VxWx (0x6f | P_EXT | P_SIMDF3) @@ -927,7 +928,7 @@ static bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece, } else { switch (vece) { case MO_64: - tcg_out_vex_modrm_offset(s, OPC_VBROADCASTSD, r, 0, base, offset); + tcg_out_vex_modrm_offset(s, OPC_MOVDDUP, r, 0, base, offset); break; case MO_32: tcg_out_vex_modrm_offset(s, OPC_VBROADCASTSS, r, 0, base, offset); @@ -969,12 +970,12 @@ static void tcg_out_dupi_vec(TCGContext *s, TCGType type, } else if (have_avx2) { tcg_out_vex_modrm_pool(s, OPC_VPBROADCASTQ + vex_l, ret); } else { - tcg_out_vex_modrm_pool(s, OPC_VBROADCASTSD, ret); + tcg_out_vex_modrm_pool(s, OPC_MOVDDUP, ret); } new_pool_label(s, arg, R_386_PC32, s->code_ptr - 4, -4); } else { if (have_avx2) { - tcg_out_vex_modrm_pool(s, OPC_VBROADCASTSD + vex_l, ret); + tcg_out_vex_modrm_pool(s, OPC_VPBROADCASTW + vex_l, ret); } else { tcg_out_vex_modrm_pool(s, OPC_VBROADCASTSS, ret); }