diff mbox series

[v4,1/8] target/ppc: Implement xxm[tf]acc and xxsetaccz

Message ID 20220520135129.63664-2-lucas.araujo@eldorado.org.br
State New
Headers show
Series VSX MMA Implementation | expand

Commit Message

Lucas Mateus Martins Araujo e Castro May 20, 2022, 1:51 p.m. UTC 
From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Implement the following PowerISA v3.1 instructions:
xxmfacc: VSX Move From Accumulator
xxmtacc: VSX Move To Accumulator
xxsetaccz: VSX Set Accumulator to Zero

The PowerISA 3.1 mentions that for the current version of the
architecture, "the hardware implementation provides the effect of ACC[i]
and VSRs 4*i to 4*i + 3 logically containing the same data" and "The
Accumulators introduce no new logical state at this time" (page 501).
For now it seems unnecessary to create new structures, so this patch
just uses ACC[i] as VSRs 4*i to 4*i+3 and therefore move to and from
accumulators are no-ops.

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/ppc/cpu.h                    |  5 +++++
 target/ppc/insn32.decode            |  9 +++++++++
 target/ppc/translate/vsx-impl.c.inc | 31 +++++++++++++++++++++++++++++
 3 files changed, 45 insertions(+)
diff mbox series

Patch

diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index 901ded79e9..2e80d0978f 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -2661,6 +2661,11 @@  static inline int vsr_full_offset(int i)
     return offsetof(CPUPPCState, vsr[i].u64[0]);
 }
 
+static inline int acc_full_offset(int i)
+{
+    return vsr_full_offset(i * 4);
+}
+
 static inline int fpr_offset(int i)
 {
     return vsr64_offset(i, true);
diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 39372fe673..7a76bedfa6 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -151,6 +151,9 @@ 
 &X_vrt_frbp     vrt frbp
 @X_vrt_frbp     ...... vrt:5 ..... ....0 .......... .           &X_vrt_frbp frbp=%x_frbp
 
+&X_a            ra
+@X_a            ...... ra:3 .. ..... ..... .......... .         &X_a
+
 %xx_xt          0:1 21:5
 %xx_xb          1:1 11:5
 %xx_xa          2:1 16:5
@@ -710,3 +713,9 @@  XVTLSBB         111100 ... -- 00010 ..... 111011011 . - @XX2_bf_xb
 &XL_s           s:uint8_t
 @XL_s           ......-------------- s:1 .......... -   &XL_s
 RFEBB           010011-------------- .   0010010010 -   @XL_s
+
+## Accumulator Instructions
+
+XXMFACC         011111 ... -- 00000 ----- 0010110001 -   @X_a
+XXMTACC         011111 ... -- 00001 ----- 0010110001 -   @X_a
+XXSETACCZ       011111 ... -- 00011 ----- 0010110001 -   @X_a
diff --git a/target/ppc/translate/vsx-impl.c.inc b/target/ppc/translate/vsx-impl.c.inc
index 3692740736..dc8875d5d3 100644
--- a/target/ppc/translate/vsx-impl.c.inc
+++ b/target/ppc/translate/vsx-impl.c.inc
@@ -2787,6 +2787,37 @@  static bool trans_XVCVBF16SPN(DisasContext *ctx, arg_XX2 *a)
     return true;
 }
 
+    /*
+     *  The PowerISA 3.1 mentions that for the current version of the
+     *  architecture, "the hardware implementation provides the effect of
+     *  ACC[i] and VSRs 4*i to 4*i + 3 logically containing the same data"
+     *  and "The Accumulators introduce no new logical state at this time"
+     *  (page 501). For now it seems unnecessary to create new structures,
+     *  so ACC[i] is the same as VSRs 4*i to 4*i+3 and therefore
+     *  move to and from accumulators are no-ops.
+     */
+static bool trans_XXMFACC(DisasContext *ctx, arg_X_a *a)
+{
+    REQUIRE_INSNS_FLAGS2(ctx, ISA310);
+    REQUIRE_VSX(ctx);
+    return true;
+}
+
+static bool trans_XXMTACC(DisasContext *ctx, arg_X_a *a)
+{
+    REQUIRE_INSNS_FLAGS2(ctx, ISA310);
+    REQUIRE_VSX(ctx);
+    return true;
+}
+
+static bool trans_XXSETACCZ(DisasContext *ctx, arg_X_a *a)
+{
+    REQUIRE_INSNS_FLAGS2(ctx, ISA310);
+    REQUIRE_VSX(ctx);
+    tcg_gen_gvec_dup_imm(MO_64, acc_full_offset(a->ra), 64, 64, 0);
+    return true;
+}
+
 #undef GEN_XX2FORM
 #undef GEN_XX3FORM
 #undef GEN_XX2IFORM