All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Maydell <peter.maydell@linaro.org>
To: qemu-arm@nongnu.org, qemu-devel@nongnu.org
Cc: Richard Henderson <richard.henderson@linaro.org>
Subject: [PATCH v2 57/57] target/arm: Make VMOV scalar <-> gpreg beatwise for MVE
Date: Mon, 14 Jun 2021 16:10:07 +0100	[thread overview]
Message-ID: <20210614151007.4545-58-peter.maydell@linaro.org> (raw)
In-Reply-To: <20210614151007.4545-1-peter.maydell@linaro.org>

In a CPU with MVE, the VMOV (vector lane to general-purpose register)
and VMOV (general-purpose register to vector lane) insns are not
predicated, but they are subject to beatwise execution if they
are not in an IT block.

Since our implementation always executes all 4 beats in one tick,
this means only that we need to handle PSR.ECI:
 * we must do the usual check for bad ECI state
 * we must advance ECI state if the insn succeeds
 * if ECI says we should not be executing the beat corresponding
   to the lane of the vector register being accessed then we
   should skip performing the move

Note that if PSR.ECI is non-zero then we cannot be in an IT block.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/translate-a32.h |  2 +
 target/arm/translate-mve.c |  4 +-
 target/arm/translate-vfp.c | 77 +++++++++++++++++++++++++++++++++++---
 3 files changed, 75 insertions(+), 8 deletions(-)

diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h
index 0a0053949f5..e160c7d42f0 100644
--- a/target/arm/translate-a32.h
+++ b/target/arm/translate-a32.h
@@ -46,6 +46,8 @@ long neon_full_reg_offset(unsigned reg);
 long neon_element_offset(int reg, int element, MemOp memop);
 void gen_rev16(TCGv_i32 dest, TCGv_i32 var);
 void clear_eci_state(DisasContext *s);
+bool mve_eci_check(DisasContext *s);
+void mve_update_and_store_eci(DisasContext *s);
 
 static inline TCGv_i32 load_cpu_offset(int offset)
 {
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 3d54ad1270a..43763e90762 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -57,7 +57,7 @@ static bool mve_check_qreg_bank(DisasContext *s, int qmask)
     return qmask < 8;
 }
 
-static bool mve_eci_check(DisasContext *s)
+bool mve_eci_check(DisasContext *s)
 {
     /*
      * This is a beatwise insn: check that ECI is valid (not a
@@ -91,7 +91,7 @@ static void mve_update_eci(DisasContext *s)
     }
 }
 
-static void mve_update_and_store_eci(DisasContext *s)
+void mve_update_and_store_eci(DisasContext *s)
 {
     /*
      * For insns which don't call a helper function that will call
diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c
index 01e26a246d6..0bdacba394c 100644
--- a/target/arm/translate-vfp.c
+++ b/target/arm/translate-vfp.c
@@ -553,6 +553,48 @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a)
     return true;
 }
 
+static bool mve_skip_vmov(DisasContext *s, int vn, int index, int size)
+{
+    /*
+     * In a CPU with MVE, the VMOV (vector lane to general-purpose register)
+     * and VMOV (general-purpose register to vector lane) insns are not
+     * predicated, but they are subject to beatwise execution if they are
+     * not in an IT block.
+     *
+     * Since our implementation always executes all 4 beats in one tick,
+     * this means only that if PSR.ECI says we should not be executing
+     * the beat corresponding to the lane of the vector register being
+     * accessed then we should skip performing the move, and that we need
+     * to do the usual check for bad ECI state and advance of ECI state.
+     *
+     * Note that if PSR.ECI is non-zero then we cannot be in an IT block.
+     *
+     * Return true if this VMOV scalar <-> gpreg should be skipped because
+     * the MVE PSR.ECI state says we skip the beat where the store happens.
+     */
+
+    /* Calculate the byte offset into Qn which we're going to access */
+    int ofs = (index << size) + ((vn & 1) * 8);
+
+    if (!dc_isar_feature(aa32_mve, s)) {
+        return false;
+    }
+
+    switch (s->eci) {
+    case ECI_NONE:
+        return false;
+    case ECI_A0:
+        return ofs < 4;
+    case ECI_A0A1:
+        return ofs < 8;
+    case ECI_A0A1A2:
+    case ECI_A0A1A2B0:
+        return ofs < 12;
+    default:
+        g_assert_not_reached();
+    }
+}
+
 static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a)
 {
     /* VMOV scalar to general purpose register */
@@ -575,14 +617,26 @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a)
         return false;
     }
 
+    if (dc_isar_feature(aa32_mve, s)) {
+        if (!mve_eci_check(s)) {
+            return true;
+        }
+    }
+
     if (!vfp_access_check(s)) {
         return true;
     }
 
-    tmp = tcg_temp_new_i32();
-    read_neon_element32(tmp, a->vn, a->index, a->size | (a->u ? 0 : MO_SIGN));
-    store_reg(s, a->rt, tmp);
+    if (!mve_skip_vmov(s, a->vn, a->index, a->size)) {
+        tmp = tcg_temp_new_i32();
+        read_neon_element32(tmp, a->vn, a->index,
+                            a->size | (a->u ? 0 : MO_SIGN));
+        store_reg(s, a->rt, tmp);
+    }
 
+    if (dc_isar_feature(aa32_mve, s)) {
+        mve_update_and_store_eci(s);
+    }
     return true;
 }
 
@@ -608,14 +662,25 @@ static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a)
         return false;
     }
 
+    if (dc_isar_feature(aa32_mve, s)) {
+        if (!mve_eci_check(s)) {
+            return true;
+        }
+    }
+
     if (!vfp_access_check(s)) {
         return true;
     }
 
-    tmp = load_reg(s, a->rt);
-    write_neon_element32(tmp, a->vn, a->index, a->size);
-    tcg_temp_free_i32(tmp);
+    if (!mve_skip_vmov(s, a->vn, a->index, a->size)) {
+        tmp = load_reg(s, a->rt);
+        write_neon_element32(tmp, a->vn, a->index, a->size);
+        tcg_temp_free_i32(tmp);
+    }
 
+    if (dc_isar_feature(aa32_mve, s)) {
+        mve_update_and_store_eci(s);
+    }
     return true;
 }
 
-- 
2.20.1



  parent reply	other threads:[~2021-06-14 15:58 UTC|newest]

Thread overview: 77+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-14 15:09 [PATCH v2 00/57] target/arm: First slice of MVE implementation Peter Maydell
2021-06-14 15:09 ` [PATCH v2 01/57] target/arm: Provide and use H8 and H1_8 macros Peter Maydell
2021-06-14 15:09 ` [PATCH v2 02/57] target/arm: Enable FPSCR.QC bit for MVE Peter Maydell
2021-06-14 15:09 ` [PATCH v2 03/57] target/arm: Handle VPR semantics in existing code Peter Maydell
2021-06-14 15:09 ` [PATCH v2 04/57] target/arm: Add handling for PSR.ECI/ICI Peter Maydell
2021-06-14 19:15   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 05/57] target/arm: Let vfp_access_check() handle late NOCP checks Peter Maydell
2021-06-14 15:09 ` [PATCH v2 06/57] target/arm: Implement MVE LCTP Peter Maydell
2021-06-14 15:09 ` [PATCH v2 07/57] target/arm: Implement MVE WLSTP insn Peter Maydell
2021-06-14 19:20   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 08/57] target/arm: Implement MVE DLSTP Peter Maydell
2021-06-14 15:09 ` [PATCH v2 09/57] target/arm: Implement MVE LETP insn Peter Maydell
2021-06-14 15:09 ` [PATCH v2 10/57] target/arm: Add framework for MVE decode Peter Maydell
2021-06-14 15:09 ` [PATCH v2 11/57] target/arm: Implement MVE VLDR/VSTR (non-widening forms) Peter Maydell
2021-06-14 19:29   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 12/57] target/arm: Implement widening/narrowing MVE VLDR/VSTR insns Peter Maydell
2021-06-14 19:39   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 13/57] target/arm: Move expand_pred_b() data to translate.c Peter Maydell
2021-06-14 19:41   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 14/57] target/arm: Implement MVE VCLZ Peter Maydell
2021-06-14 20:00   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 15/57] target/arm: Implement MVE VCLS Peter Maydell
2021-06-14 15:09 ` [PATCH v2 16/57] bitops.h: Provide hswap32(), hswap64(), wswap64() swapping operations Peter Maydell
2021-06-14 15:09 ` [PATCH v2 17/57] target/arm: Implement MVE VREV16, VREV32, VREV64 Peter Maydell
2021-06-14 20:03   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 18/57] target/arm: Implement MVE VMVN (register) Peter Maydell
2021-06-14 15:09 ` [PATCH v2 19/57] target/arm: Implement MVE VABS Peter Maydell
2021-06-14 20:06   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 20/57] target/arm: Implement MVE VNEG Peter Maydell
2021-06-14 15:09 ` [PATCH v2 21/57] tcg: Make gen_dup_i32() public Peter Maydell
2021-06-14 20:12   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 22/57] target/arm: Implement MVE VDUP Peter Maydell
2021-06-14 20:15   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 23/57] target/arm: Implement MVE VAND, VBIC, VORR, VORN, VEOR Peter Maydell
2021-06-14 15:09 ` [PATCH v2 24/57] target/arm: Implement MVE VADD, VSUB, VMUL Peter Maydell
2021-06-14 15:09 ` [PATCH v2 25/57] target/arm: Implement MVE VMULH Peter Maydell
2021-06-14 15:09 ` [PATCH v2 26/57] target/arm: Implement MVE VRMULH Peter Maydell
2021-06-14 15:09 ` [PATCH v2 27/57] target/arm: Implement MVE VMAX, VMIN Peter Maydell
2021-06-14 15:09 ` [PATCH v2 28/57] target/arm: Implement MVE VABD Peter Maydell
2021-06-14 15:09 ` [PATCH v2 29/57] target/arm: Implement MVE VHADD, VHSUB Peter Maydell
2021-06-14 15:09 ` [PATCH v2 30/57] target/arm: Implement MVE VMULL Peter Maydell
2021-06-14 15:09 ` [PATCH v2 31/57] target/arm: Implement MVE VMLALDAV Peter Maydell
2021-06-14 15:09 ` [PATCH v2 32/57] target/arm: Implement MVE VMLSLDAV Peter Maydell
2021-06-14 15:09 ` [PATCH v2 33/57] include/qemu/int128.h: Add function to create Int128 from int64_t Peter Maydell
2021-06-14 15:09 ` [PATCH v2 34/57] target/arm: Implement MVE VRMLALDAVH, VRMLSLDAVH Peter Maydell
2021-06-14 21:27   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 35/57] target/arm: Implement MVE VADD (scalar) Peter Maydell
2021-06-14 21:30   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 36/57] target/arm: Implement MVE VSUB, VMUL (scalar) Peter Maydell
2021-06-14 15:09 ` [PATCH v2 37/57] target/arm: Implement MVE VHADD, VHSUB (scalar) Peter Maydell
2021-06-14 15:09 ` [PATCH v2 38/57] target/arm: Implement MVE VBRSR Peter Maydell
2021-06-14 15:09 ` [PATCH v2 39/57] target/arm: Implement MVE VPST Peter Maydell
2021-06-14 15:09 ` [PATCH v2 40/57] target/arm: Implement MVE VQADD and VQSUB Peter Maydell
2021-06-14 15:09 ` [PATCH v2 41/57] target/arm: Implement MVE VQDMULH and VQRDMULH (scalar) Peter Maydell
2021-06-14 15:09 ` [PATCH v2 42/57] target/arm: Implement MVE VQDMULL scalar Peter Maydell
2021-06-14 15:09 ` [PATCH v2 43/57] target/arm: Implement MVE VQDMULH, VQRDMULH (vector) Peter Maydell
2021-06-14 15:09 ` [PATCH v2 44/57] target/arm: Implement MVE VQADD, VQSUB (vector) Peter Maydell
2021-06-14 15:09 ` [PATCH v2 45/57] target/arm: Implement MVE VQSHL (vector) Peter Maydell
2021-06-14 21:43   ` Richard Henderson
2021-06-14 15:09 ` [PATCH v2 46/57] target/arm: Implement MVE VQRSHL Peter Maydell
2021-06-14 15:09 ` [PATCH v2 47/57] target/arm: Implement MVE VSHL insn Peter Maydell
2021-06-14 15:09 ` [PATCH v2 48/57] target/arm: Implmement MVE VRSHL Peter Maydell
2021-06-14 15:09 ` [PATCH v2 49/57] target/arm: Implement MVE VQDMLADH and VQRDMLADH Peter Maydell
2021-06-14 15:10 ` [PATCH v2 50/57] target/arm: Implement MVE VQDMLSDH and VQRDMLSDH Peter Maydell
2021-06-14 15:10 ` [PATCH v2 51/57] target/arm: Implement MVE VQDMULL (vector) Peter Maydell
2021-06-14 15:10 ` [PATCH v2 52/57] target/arm: Implement MVE VRHADD Peter Maydell
2021-06-14 15:10 ` [PATCH v2 53/57] target/arm: Implement MVE VADC, VSBC Peter Maydell
2021-06-14 21:58   ` Richard Henderson
2021-06-14 15:10 ` [PATCH v2 54/57] target/arm: Implement MVE VCADD Peter Maydell
2021-06-14 15:10 ` [PATCH v2 55/57] target/arm: Implement MVE VHCADD Peter Maydell
2021-06-14 22:01   ` Richard Henderson
2021-06-14 15:10 ` [PATCH v2 56/57] target/arm: Implement MVE VADDV Peter Maydell
2021-06-14 15:10 ` Peter Maydell [this message]
2021-06-14 22:20 ` [PATCH v2 00/57] target/arm: First slice of MVE implementation no-reply
2021-06-14 22:22 ` Richard Henderson
2021-06-21 16:37   ` Peter Maydell
2021-06-21 17:13     ` Richard Henderson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210614151007.4545-58-peter.maydell@linaro.org \
    --to=peter.maydell@linaro.org \
    --cc=qemu-arm@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --subject='Re: [PATCH v2 57/57] target/arm: Make VMOV scalar <-> gpreg beatwise for MVE' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.