diff mbox series

[v4,12/47] target/ppc: Implement Vector Compare Greater Than Quadword

Message ID 20220222143646.1268606-13-matheus.ferst@eldorado.org.br (mailing list archive)
State New, archived
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:
vcmpgtsq: Vector Compare Greater Than Signed Quadword
vcmpgtuq: Vector Compare Greater Than Unsigned Quadword

Signed-off-by: Matheus Ferst <matheus.ferst@eldorado.org.br>
---
v4:
 - Branchless implementation (rth)
---
 target/ppc/insn32.decode            |  2 ++
 target/ppc/translate/vmx-impl.c.inc | 39 +++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+)

Comments

Richard Henderson Feb. 22, 2022, 7:07 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:
> vcmpgtsq: Vector Compare Greater Than Signed Quadword
> vcmpgtuq: Vector Compare Greater Than Unsigned Quadword
> 
> Signed-off-by: Matheus Ferst<matheus.ferst@eldorado.org.br>
> ---
> v4:
>   - Branchless implementation (rth)
> ---
>   target/ppc/insn32.decode            |  2 ++
>   target/ppc/translate/vmx-impl.c.inc | 39 +++++++++++++++++++++++++++++
>   2 files changed, 41 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 437a3e29e0..07a4ef9103 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -388,11 +388,13 @@  VCMPGTSB        000100 ..... ..... ..... . 1100000110   @VC
 VCMPGTSH        000100 ..... ..... ..... . 1101000110   @VC
 VCMPGTSW        000100 ..... ..... ..... . 1110000110   @VC
 VCMPGTSD        000100 ..... ..... ..... . 1111000111   @VC
+VCMPGTSQ        000100 ..... ..... ..... . 1110000111   @VC
 
 VCMPGTUB        000100 ..... ..... ..... . 1000000110   @VC
 VCMPGTUH        000100 ..... ..... ..... . 1001000110   @VC
 VCMPGTUW        000100 ..... ..... ..... . 1010000110   @VC
 VCMPGTUD        000100 ..... ..... ..... . 1011000111   @VC
+VCMPGTUQ        000100 ..... ..... ..... . 1010000111   @VC
 
 VCMPNEB         000100 ..... ..... ..... . 0000000111   @VC
 VCMPNEH         000100 ..... ..... ..... . 0001000111   @VC
diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index d66a642b67..4a76e370fc 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -1143,6 +1143,45 @@  static bool trans_VCMPEQUQ(DisasContext *ctx, arg_VC *a)
     return true;
 }
 
+static bool do_vcmpgtq(DisasContext *ctx, arg_VC *a, bool sign)
+{
+    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, false);
+    get_avr64(t1, a->vrb, false);
+    tcg_gen_setcond_i64(TCG_COND_GTU, t2, t0, t1);
+
+    get_avr64(t0, a->vra, true);
+    get_avr64(t1, a->vrb, true);
+    tcg_gen_movcond_i64(TCG_COND_EQ, t2, t0, t1, t2, tcg_constant_i64(0));
+    tcg_gen_setcond_i64(sign ? TCG_COND_GT : TCG_COND_GTU, t1, t0, t1);
+
+    tcg_gen_or_i64(t1, t1, t2);
+    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;
+}
+
+TRANS(VCMPGTSQ, do_vcmpgtq, true)
+TRANS(VCMPGTUQ, do_vcmpgtq, false)
+
 GEN_VXRFORM(vcmpeqfp, 3, 3)
 GEN_VXRFORM(vcmpgefp, 3, 7)
 GEN_VXRFORM(vcmpgtfp, 3, 11)