diff mbox series

[v4,11/47] target/ppc: Implement Vector Compare Equal Quadword

Message ID 20220222143646.1268606-12-matheus.ferst@eldorado.org.br
State New
Headers show
Series target/ppc: PowerISA Vector/VSX instruction batch | expand

Commit Message

Matheus K. Ferst Feb. 22, 2022, 2:36 p.m. UTC 
From: Matheus Ferst <matheus.ferst@eldorado.org.br>

Implement the following PowerISA v3.1 instructions:
vcmpequq: Vector Compare Equal Quadword

Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Matheus Ferst <matheus.ferst@eldorado.org.br>
---
v4:
 - Branchless implementation (rth)
---
 target/ppc/insn32.decode            |  1 +
 target/ppc/translate/vmx-impl.c.inc | 36 +++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

Comments

Richard Henderson Feb. 22, 2022, 7:05 p.m. UTC | #1 
On 2/22/22 04:36, matheus.ferst@eldorado.org.br wrote:
> From: Matheus Ferst<matheus.ferst@eldorado.org.br>
> 
> Implement the following PowerISA v3.1 instructions:
> vcmpequq: Vector Compare Equal Quadword
> 
> Suggested-by: Richard Henderson<richard.henderson@linaro.org>
> Signed-off-by: Matheus Ferst<matheus.ferst@eldorado.org.br>
> ---
> v4:
>   - Branchless implementation (rth)
> ---
>   target/ppc/insn32.decode            |  1 +
>   target/ppc/translate/vmx-impl.c.inc | 36 +++++++++++++++++++++++++++++
>   2 files changed, 37 insertions(+)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~
diff mbox series

Patch

diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index be9e05cc73..437a3e29e0 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -382,6 +382,7 @@  VCMPEQUB        000100 ..... ..... ..... . 0000000110   @VC
 VCMPEQUH        000100 ..... ..... ..... . 0001000110   @VC
 VCMPEQUW        000100 ..... ..... ..... . 0010000110   @VC
 VCMPEQUD        000100 ..... ..... ..... . 0011000111   @VC
+VCMPEQUQ        000100 ..... ..... ..... . 0111000111   @VC
 
 VCMPGTSB        000100 ..... ..... ..... . 1100000110   @VC
 VCMPGTSH        000100 ..... ..... ..... . 1101000110   @VC
diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index d7f807b81d..d66a642b67 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -1107,6 +1107,42 @@  TRANS(VCMPNEZB, do_vcmpnez, MO_8)
 TRANS(VCMPNEZH, do_vcmpnez, MO_16)
 TRANS(VCMPNEZW, do_vcmpnez, MO_32)
 
+static bool trans_VCMPEQUQ(DisasContext *ctx, arg_VC *a)
+{
+    TCGv_i64 t0, t1, t2;
+
+    t0 = tcg_temp_new_i64();
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+
+    get_avr64(t0, a->vra, true);
+    get_avr64(t1, a->vrb, true);
+    tcg_gen_xor_i64(t2, t0, t1);
+
+    get_avr64(t0, a->vra, false);
+    get_avr64(t1, a->vrb, false);
+    tcg_gen_xor_i64(t1, t0, t1);
+
+    tcg_gen_or_i64(t1, t1, t2);
+    tcg_gen_setcondi_i64(TCG_COND_EQ, t1, t1, 0);
+    tcg_gen_neg_i64(t1, t1);
+
+    set_avr64(a->vrt, t1, true);
+    set_avr64(a->vrt, t1, false);
+
+    if (a->rc) {
+        tcg_gen_extrl_i64_i32(cpu_crf[6], t1);
+        tcg_gen_andi_i32(cpu_crf[6], cpu_crf[6], 0xa);
+        tcg_gen_xori_i32(cpu_crf[6], cpu_crf[6], 0x2);
+    }
+
+    tcg_temp_free_i64(t0);
+    tcg_temp_free_i64(t1);
+    tcg_temp_free_i64(t2);
+
+    return true;
+}
+
 GEN_VXRFORM(vcmpeqfp, 3, 3)
 GEN_VXRFORM(vcmpgefp, 3, 7)
 GEN_VXRFORM(vcmpgtfp, 3, 11)