[PATCH 06/37] target/ppc: Implement vmsumudm instruction

From: matheus.ferst@eldorado.org.br
To: qemu-devel@nongnu.org, qemu-ppc@nongnu.org
Cc: danielhb413@gmail.com, richard.henderson@linaro.org,
	groug@kaod.org, "Víctor Colombo" <victor.colombo@eldorado.org.br>,
	clg@kaod.org, "Matheus Ferst" <matheus.ferst@eldorado.org.br>,
	david@gibson.dropbear.id.au
Subject: [PATCH 06/37] target/ppc: Implement vmsumudm instruction
Date: Fri,  7 Jan 2022 15:56:22 -0300	[thread overview]
Message-ID: <20220107185653.1609775-7-matheus.ferst@eldorado.org.br> (raw)
In-Reply-To: <20220107185653.1609775-1-matheus.ferst@eldorado.org.br>

From: Víctor Colombo <victor.colombo@eldorado.org.br>

Based on [1] by Lijun Pan <ljp@linux.ibm.com>, which was never merged
into master.

[1]: https://lists.gnu.org/archive/html/qemu-ppc/2020-07/msg00419.html

Signed-off-by: Víctor Colombo <victor.colombo@eldorado.org.br>
Signed-off-by: Matheus Ferst <matheus.ferst@eldorado.org.br>
---
 target/ppc/insn32.decode            |  1 +
 target/ppc/translate/vmx-impl.c.inc | 34 +++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+)

diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 0ec64cb4f4..c4796260b6 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -443,6 +443,7 @@ VEXTRACTQM      000100 ..... 01100 ..... 11001000010    @VX_tb
 ## Vector Multiply-Sum Instructions
 
 VMSUMCUD        000100 ..... ..... ..... ..... 010111   @VA
+VMSUMUDM        000100 ..... ..... ..... ..... 100011   @VA
 
 # VSX Load/Store Instructions
 
diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index 694da75448..b7559cf94c 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -2081,6 +2081,40 @@ static bool trans_VPEXTD(DisasContext *ctx, arg_VX *a)
     return true;
 }
 
+static bool trans_VMSUMUDM(DisasContext *ctx, arg_VA *a)
+{
+    TCGv_i64 rl, rh, src1, src2;
+    int dw;
+
+    REQUIRE_INSNS_FLAGS2(ctx, ISA300);
+    REQUIRE_VECTOR(ctx);
+
+    rh = tcg_temp_new_i64();
+    rl = tcg_temp_new_i64();
+    src1 = tcg_temp_new_i64();
+    src2 = tcg_temp_new_i64();
+
+    get_avr64(rl, a->rc, false);
+    get_avr64(rh, a->rc, true);
+
+    for (dw = 0; dw < 2; dw++) {
+        get_avr64(src1, a->vra, dw);
+        get_avr64(src2, a->vrb, dw);
+        tcg_gen_mulu2_i64(src1, src2, src1, src2);
+        tcg_gen_add2_i64(rl, rh, rl, rh, src1, src2);
+    }
+
+    set_avr64(a->vrt, rl, false);
+    set_avr64(a->vrt, rh, true);
+
+    tcg_temp_free_i64(rl);
+    tcg_temp_free_i64(rh);
+    tcg_temp_free_i64(src1);
+    tcg_temp_free_i64(src2);
+
+    return true;
+}
+
 static bool trans_VMSUMCUD(DisasContext *ctx, arg_VA *a)
 {
     TCGv_i64 tmp0, tmp1, prod1h, prod1l, prod0h, prod0l, zero;
-- 
2.25.1


