From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([209.51.188.92]:33360) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1go9Jf-0004ne-1q for qemu-devel@nongnu.org; Mon, 28 Jan 2019 10:59:20 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1go9Jd-0007hv-5J for qemu-devel@nongnu.org; Mon, 28 Jan 2019 10:59:18 -0500 Received: from mail-pg1-x535.google.com ([2607:f8b0:4864:20::535]:43918) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1go9Jc-0007hR-U9 for qemu-devel@nongnu.org; Mon, 28 Jan 2019 10:59:17 -0500 Received: by mail-pg1-x535.google.com with SMTP id v28so7381336pgk.10 for ; Mon, 28 Jan 2019 07:59:16 -0800 (PST) From: Richard Henderson Date: Mon, 28 Jan 2019 07:58:47 -0800 Message-Id: <20190128155907.20607-4-richard.henderson@linaro.org> In-Reply-To: <20190128155907.20607-1-richard.henderson@linaro.org> References: <20190128155907.20607-1-richard.henderson@linaro.org> Subject: [Qemu-devel] [PULL 03/23] tcg: Add write_aofs to GVecGen4 List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: peter.maydell@linaro.org This allows writing 2 output, 3 input operations. Signed-off-by: Richard Henderson --- tcg/tcg-op-gvec.h | 2 ++ tcg/tcg-op-gvec.c | 27 +++++++++++++++++++-------- 2 files changed, 21 insertions(+), 8 deletions(-) diff --git a/tcg/tcg-op-gvec.h b/tcg/tcg-op-gvec.h index d65b9d9d4c..2cb447112e 100644 --- a/tcg/tcg-op-gvec.h +++ b/tcg/tcg-op-gvec.h @@ -181,6 +181,8 @@ typedef struct { uint8_t vece; /* Prefer i64 to v64. */ bool prefer_i64; + /* Write aofs as a 2nd dest operand. */ + bool write_aofs; } GVecGen4; void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs, diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index 81689d02f7..c10d3d7b26 100644 --- a/tcg/tcg-op-gvec.c +++ b/tcg/tcg-op-gvec.c @@ -665,7 +665,7 @@ static void expand_3_i32(uint32_t dofs, uint32_t aofs, /* Expand OPSZ bytes worth of three-operand operations using i32 elements. */ static void expand_4_i32(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t cofs, uint32_t oprsz, + uint32_t cofs, uint32_t oprsz, bool write_aofs, void (*fni)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32)) { TCGv_i32 t0 = tcg_temp_new_i32(); @@ -680,6 +680,9 @@ static void expand_4_i32(uint32_t dofs, uint32_t aofs, uint32_t bofs, tcg_gen_ld_i32(t3, cpu_env, cofs + i); fni(t0, t1, t2, t3); tcg_gen_st_i32(t0, cpu_env, dofs + i); + if (write_aofs) { + tcg_gen_st_i32(t1, cpu_env, aofs + i); + } } tcg_temp_free_i32(t3); tcg_temp_free_i32(t2); @@ -769,7 +772,7 @@ static void expand_3_i64(uint32_t dofs, uint32_t aofs, /* Expand OPSZ bytes worth of three-operand operations using i64 elements. */ static void expand_4_i64(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t cofs, uint32_t oprsz, + uint32_t cofs, uint32_t oprsz, bool write_aofs, void (*fni)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64)) { TCGv_i64 t0 = tcg_temp_new_i64(); @@ -784,6 +787,9 @@ static void expand_4_i64(uint32_t dofs, uint32_t aofs, uint32_t bofs, tcg_gen_ld_i64(t3, cpu_env, cofs + i); fni(t0, t1, t2, t3); tcg_gen_st_i64(t0, cpu_env, dofs + i); + if (write_aofs) { + tcg_gen_st_i64(t1, cpu_env, aofs + i); + } } tcg_temp_free_i64(t3); tcg_temp_free_i64(t2); @@ -880,7 +886,7 @@ static void expand_3_vec(unsigned vece, uint32_t dofs, uint32_t aofs, /* Expand OPSZ bytes worth of four-operand operations using host vectors. */ static void expand_4_vec(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, uint32_t oprsz, - uint32_t tysz, TCGType type, + uint32_t tysz, TCGType type, bool write_aofs, void (*fni)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec, TCGv_vec)) { @@ -896,6 +902,9 @@ static void expand_4_vec(unsigned vece, uint32_t dofs, uint32_t aofs, tcg_gen_ld_vec(t3, cpu_env, cofs + i); fni(vece, t0, t1, t2, t3); tcg_gen_st_vec(t0, cpu_env, dofs + i); + if (write_aofs) { + tcg_gen_st_vec(t1, cpu_env, aofs + i); + } } tcg_temp_free_vec(t3); tcg_temp_free_vec(t2); @@ -1187,7 +1196,7 @@ void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, */ some = QEMU_ALIGN_DOWN(oprsz, 32); expand_4_vec(g->vece, dofs, aofs, bofs, cofs, some, - 32, TCG_TYPE_V256, g->fniv); + 32, TCG_TYPE_V256, g->write_aofs, g->fniv); if (some == oprsz) { break; } @@ -1200,18 +1209,20 @@ void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, /* fallthru */ case TCG_TYPE_V128: expand_4_vec(g->vece, dofs, aofs, bofs, cofs, oprsz, - 16, TCG_TYPE_V128, g->fniv); + 16, TCG_TYPE_V128, g->write_aofs, g->fniv); break; case TCG_TYPE_V64: expand_4_vec(g->vece, dofs, aofs, bofs, cofs, oprsz, - 8, TCG_TYPE_V64, g->fniv); + 8, TCG_TYPE_V64, g->write_aofs, g->fniv); break; case 0: if (g->fni8 && check_size_impl(oprsz, 8)) { - expand_4_i64(dofs, aofs, bofs, cofs, oprsz, g->fni8); + expand_4_i64(dofs, aofs, bofs, cofs, oprsz, + g->write_aofs, g->fni8); } else if (g->fni4 && check_size_impl(oprsz, 4)) { - expand_4_i32(dofs, aofs, bofs, cofs, oprsz, g->fni4); + expand_4_i32(dofs, aofs, bofs, cofs, oprsz, + g->write_aofs, g->fni4); } else { assert(g->fno != NULL); tcg_gen_gvec_4_ool(dofs, aofs, bofs, cofs, -- 2.17.2