All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Maydell <peter.maydell@linaro.org>
To: qemu-devel@nongnu.org
Subject: [PULL 071/114] target/arm: Pass separate addend to {U, S}DOT helpers
Date: Tue, 25 May 2021 16:02:41 +0100	[thread overview]
Message-ID: <20210525150324.32370-72-peter.maydell@linaro.org> (raw)
In-Reply-To: <20210525150324.32370-1-peter.maydell@linaro.org>

From: Richard Henderson <richard.henderson@linaro.org>

For SVE, we potentially have a 4th argument coming from the
movprfx instruction.  Currently we do not optimize movprfx,
so the problem is not visible.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-50-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h         |  20 +++---
 target/arm/sve.decode       |   7 ++-
 target/arm/translate-a64.c  |  15 ++++-
 target/arm/translate-neon.c |  10 +--
 target/arm/translate-sve.c  |  13 ++--
 target/arm/vec_helper.c     | 120 ++++++++++++++++++++----------------
 6 files changed, 109 insertions(+), 76 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 23a7ec56384..f4b092ee1c1 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -608,15 +608,19 @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_4(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_4(gvec_sdot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_udot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_sdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_udot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 67b6466a1e9..04ef38f1480 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -756,12 +756,13 @@ UMIN_zzi        00100101 .. 101 011 110 ........ .....          @rdn_i8u
 MUL_zzi         00100101 .. 110 000 110 ........ .....          @rdn_i8s
 
 # SVE integer dot product (unpredicated)
-DOT_zzz         01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5      ra=%reg_movprfx
+DOT_zzzz        01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \
+                ra=%reg_movprfx
 
 # SVE integer dot product (indexed)
-DOT_zzx         01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \
+DOT_zzxw        01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \
                 sz=0 ra=%reg_movprfx
-DOT_zzx         01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \
+DOT_zzxw        01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \
                 sz=1 ra=%reg_movprfx
 
 # SVE floating-point complex add (predicated)
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index bdd47208b15..61c5fa96567 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -683,6 +683,17 @@ static void gen_gvec_op3_qc(DisasContext *s, bool is_q, int rd, int rn,
     tcg_temp_free_ptr(qc_ptr);
 }
 
+/* Expand a 4-operand operation using an out-of-line helper.  */
+static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn,
+                             int rm, int ra, int data, gen_helper_gvec_4 *fn)
+{
+    tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd),
+                       vec_full_reg_offset(s, rn),
+                       vec_full_reg_offset(s, rm),
+                       vec_full_reg_offset(s, ra),
+                       is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
+}
+
 /* Set ZF and NF based on a 64 bit result. This is alas fiddlier
  * than the 32 bit equivalent.
  */
@@ -12183,7 +12194,7 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
         return;
 
     case 0x2: /* SDOT / UDOT */
-        gen_gvec_op3_ool(s, is_q, rd, rn, rm, 0,
+        gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0,
                          u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b);
         return;
 
@@ -13442,7 +13453,7 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     switch (16 * u + opcode) {
     case 0x0e: /* SDOT */
     case 0x1e: /* UDOT */
-        gen_gvec_op3_ool(s, is_q, rd, rn, rm, index,
+        gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index,
                          u ? gen_helper_gvec_udot_idx_b
                          : gen_helper_gvec_sdot_idx_b);
         return;
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index 658bd275dac..fa67605fdc4 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -230,7 +230,7 @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a)
 static bool trans_VDOT(DisasContext *s, arg_VDOT *a)
 {
     int opr_sz;
-    gen_helper_gvec_3 *fn_gvec;
+    gen_helper_gvec_4 *fn_gvec;
 
     if (!dc_isar_feature(aa32_dp, s)) {
         return false;
@@ -252,9 +252,10 @@ static bool trans_VDOT(DisasContext *s, arg_VDOT *a)
 
     opr_sz = (1 + a->q) * 8;
     fn_gvec = a->u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b;
-    tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd),
+    tcg_gen_gvec_4_ool(vfp_reg_offset(1, a->vd),
                        vfp_reg_offset(1, a->vn),
                        vfp_reg_offset(1, a->vm),
+                       vfp_reg_offset(1, a->vd),
                        opr_sz, opr_sz, 0, fn_gvec);
     return true;
 }
@@ -332,7 +333,7 @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
 
 static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a)
 {
-    gen_helper_gvec_3 *fn_gvec;
+    gen_helper_gvec_4 *fn_gvec;
     int opr_sz;
     TCGv_ptr fpst;
 
@@ -357,9 +358,10 @@ static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a)
     fn_gvec = a->u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b;
     opr_sz = (1 + a->q) * 8;
     fpst = fpstatus_ptr(FPST_STD);
-    tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd),
+    tcg_gen_gvec_4_ool(vfp_reg_offset(1, a->vd),
                        vfp_reg_offset(1, a->vn),
                        vfp_reg_offset(1, a->rm),
+                       vfp_reg_offset(1, a->vd),
                        opr_sz, opr_sz, a->index, fn_gvec);
     tcg_temp_free_ptr(fpst);
     return true;
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 46f87ee259e..2864c3a3cfa 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3800,28 +3800,29 @@ DO_ZZI(UMIN, umin)
 
 #undef DO_ZZI
 
-static bool trans_DOT_zzz(DisasContext *s, arg_DOT_zzz *a)
+static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a)
 {
-    static gen_helper_gvec_3 * const fns[2][2] = {
+    static gen_helper_gvec_4 * const fns[2][2] = {
         { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h },
         { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h }
     };
 
     if (sve_access_check(s)) {
-        gen_gvec_ool_zzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, 0);
+        gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0);
     }
     return true;
 }
 
-static bool trans_DOT_zzx(DisasContext *s, arg_DOT_zzx *a)
+static bool trans_DOT_zzxw(DisasContext *s, arg_DOT_zzxw *a)
 {
-    static gen_helper_gvec_3 * const fns[2][2] = {
+    static gen_helper_gvec_4 * const fns[2][2] = {
         { gen_helper_gvec_sdot_idx_b, gen_helper_gvec_sdot_idx_h },
         { gen_helper_gvec_udot_idx_b, gen_helper_gvec_udot_idx_h }
     };
 
     if (sve_access_check(s)) {
-        gen_gvec_ool_zzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, a->index);
+        gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm,
+                          a->ra, a->index);
     }
     return true;
 }
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 48e3addd814..f88e5721321 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -375,71 +375,76 @@ void HELPER(sve2_sqrdmlsh_d)(void *vd, void *vn, void *vm,
  * All elements are treated equally, no matter where they are.
  */
 
-void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-    int32_t *d = vd;
+    int32_t *d = vd, *a = va;
     int8_t *n = vn, *m = vm;
 
     for (i = 0; i < opr_sz / 4; ++i) {
-        d[i] += n[i * 4 + 0] * m[i * 4 + 0]
-              + n[i * 4 + 1] * m[i * 4 + 1]
-              + n[i * 4 + 2] * m[i * 4 + 2]
-              + n[i * 4 + 3] * m[i * 4 + 3];
+        d[i] = (a[i] +
+                n[i * 4 + 0] * m[i * 4 + 0] +
+                n[i * 4 + 1] * m[i * 4 + 1] +
+                n[i * 4 + 2] * m[i * 4 + 2] +
+                n[i * 4 + 3] * m[i * 4 + 3]);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-    uint32_t *d = vd;
+    uint32_t *d = vd, *a = va;
     uint8_t *n = vn, *m = vm;
 
     for (i = 0; i < opr_sz / 4; ++i) {
-        d[i] += n[i * 4 + 0] * m[i * 4 + 0]
-              + n[i * 4 + 1] * m[i * 4 + 1]
-              + n[i * 4 + 2] * m[i * 4 + 2]
-              + n[i * 4 + 3] * m[i * 4 + 3];
+        d[i] = (a[i] +
+                n[i * 4 + 0] * m[i * 4 + 0] +
+                n[i * 4 + 1] * m[i * 4 + 1] +
+                n[i * 4 + 2] * m[i * 4 + 2] +
+                n[i * 4 + 3] * m[i * 4 + 3]);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-    int64_t *d = vd;
+    int64_t *d = vd, *a = va;
     int16_t *n = vn, *m = vm;
 
     for (i = 0; i < opr_sz / 8; ++i) {
-        d[i] += (int64_t)n[i * 4 + 0] * m[i * 4 + 0]
-              + (int64_t)n[i * 4 + 1] * m[i * 4 + 1]
-              + (int64_t)n[i * 4 + 2] * m[i * 4 + 2]
-              + (int64_t)n[i * 4 + 3] * m[i * 4 + 3];
+        d[i] = (a[i] +
+                (int64_t)n[i * 4 + 0] * m[i * 4 + 0] +
+                (int64_t)n[i * 4 + 1] * m[i * 4 + 1] +
+                (int64_t)n[i * 4 + 2] * m[i * 4 + 2] +
+                (int64_t)n[i * 4 + 3] * m[i * 4 + 3]);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-    uint64_t *d = vd;
+    uint64_t *d = vd, *a = va;
     uint16_t *n = vn, *m = vm;
 
     for (i = 0; i < opr_sz / 8; ++i) {
-        d[i] += (uint64_t)n[i * 4 + 0] * m[i * 4 + 0]
-              + (uint64_t)n[i * 4 + 1] * m[i * 4 + 1]
-              + (uint64_t)n[i * 4 + 2] * m[i * 4 + 2]
-              + (uint64_t)n[i * 4 + 3] * m[i * 4 + 3];
+        d[i] = (a[i] +
+                (uint64_t)n[i * 4 + 0] * m[i * 4 + 0] +
+                (uint64_t)n[i * 4 + 1] * m[i * 4 + 1] +
+                (uint64_t)n[i * 4 + 2] * m[i * 4 + 2] +
+                (uint64_t)n[i * 4 + 3] * m[i * 4 + 3]);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm,
+                             void *va, uint32_t desc)
 {
     intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4;
     intptr_t index = simd_data(desc);
-    int32_t *d = vd;
+    int32_t *d = vd, *a = va;
     int8_t *n = vn;
     int8_t *m_indexed = (int8_t *)vm + H4(index) * 4;
 
@@ -455,10 +460,11 @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
         int8_t m3 = m_indexed[i * 4 + 3];
 
         do {
-            d[i] += n[i * 4 + 0] * m0
-                  + n[i * 4 + 1] * m1
-                  + n[i * 4 + 2] * m2
-                  + n[i * 4 + 3] * m3;
+            d[i] = (a[i] +
+                    n[i * 4 + 0] * m0 +
+                    n[i * 4 + 1] * m1 +
+                    n[i * 4 + 2] * m2 +
+                    n[i * 4 + 3] * m3);
         } while (++i < segend);
         segend = i + 4;
     } while (i < opr_sz_4);
@@ -466,11 +472,12 @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm,
+                             void *va, uint32_t desc)
 {
     intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4;
     intptr_t index = simd_data(desc);
-    uint32_t *d = vd;
+    uint32_t *d = vd, *a = va;
     uint8_t *n = vn;
     uint8_t *m_indexed = (uint8_t *)vm + H4(index) * 4;
 
@@ -486,10 +493,11 @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
         uint8_t m3 = m_indexed[i * 4 + 3];
 
         do {
-            d[i] += n[i * 4 + 0] * m0
-                  + n[i * 4 + 1] * m1
-                  + n[i * 4 + 2] * m2
-                  + n[i * 4 + 3] * m3;
+            d[i] = (a[i] +
+                    n[i * 4 + 0] * m0 +
+                    n[i * 4 + 1] * m1 +
+                    n[i * 4 + 2] * m2 +
+                    n[i * 4 + 3] * m3);
         } while (++i < segend);
         segend = i + 4;
     } while (i < opr_sz_4);
@@ -497,11 +505,12 @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm,
+                             void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8;
     intptr_t index = simd_data(desc);
-    int64_t *d = vd;
+    int64_t *d = vd, *a = va;
     int16_t *n = vn;
     int16_t *m_indexed = (int16_t *)vm + index * 4;
 
@@ -509,30 +518,33 @@ void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
      * Process the entire segment all at once, writing back the results
      * only after we've consumed all of the inputs.
      */
-    for (i = 0; i < opr_sz_8 ; i += 2) {
-        uint64_t d0, d1;
+    for (i = 0; i < opr_sz_8; i += 2) {
+        int64_t d0, d1;
 
-        d0  = n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0];
+        d0  = a[i + 0];
+        d0 += n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0];
         d0 += n[i * 4 + 1] * (int64_t)m_indexed[i * 4 + 1];
         d0 += n[i * 4 + 2] * (int64_t)m_indexed[i * 4 + 2];
         d0 += n[i * 4 + 3] * (int64_t)m_indexed[i * 4 + 3];
-        d1  = n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0];
+
+        d1  = a[i + 1];
+        d1 += n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0];
         d1 += n[i * 4 + 5] * (int64_t)m_indexed[i * 4 + 1];
         d1 += n[i * 4 + 6] * (int64_t)m_indexed[i * 4 + 2];
         d1 += n[i * 4 + 7] * (int64_t)m_indexed[i * 4 + 3];
 
-        d[i + 0] += d0;
-        d[i + 1] += d1;
+        d[i + 0] = d0;
+        d[i + 1] = d1;
     }
-
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm,
+                             void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8;
     intptr_t index = simd_data(desc);
-    uint64_t *d = vd;
+    uint64_t *d = vd, *a = va;
     uint16_t *n = vn;
     uint16_t *m_indexed = (uint16_t *)vm + index * 4;
 
@@ -540,22 +552,24 @@ void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
      * Process the entire segment all at once, writing back the results
      * only after we've consumed all of the inputs.
      */
-    for (i = 0; i < opr_sz_8 ; i += 2) {
+    for (i = 0; i < opr_sz_8; i += 2) {
         uint64_t d0, d1;
 
-        d0  = n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0];
+        d0  = a[i + 0];
+        d0 += n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0];
         d0 += n[i * 4 + 1] * (uint64_t)m_indexed[i * 4 + 1];
         d0 += n[i * 4 + 2] * (uint64_t)m_indexed[i * 4 + 2];
         d0 += n[i * 4 + 3] * (uint64_t)m_indexed[i * 4 + 3];
-        d1  = n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0];
+
+        d1  = a[i + 1];
+        d1 += n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0];
         d1 += n[i * 4 + 5] * (uint64_t)m_indexed[i * 4 + 1];
         d1 += n[i * 4 + 6] * (uint64_t)m_indexed[i * 4 + 2];
         d1 += n[i * 4 + 7] * (uint64_t)m_indexed[i * 4 + 3];
 
-        d[i + 0] += d0;
-        d[i + 1] += d1;
+        d[i + 0] = d0;
+        d[i + 1] = d1;
     }
-
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-- 
2.20.1



  parent reply	other threads:[~2021-05-25 15:54 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-25 15:01 [PULL 000/114] target-arm queue Peter Maydell
2021-05-25 15:01 ` [PULL 001/114] hw/arm/smmuv3: Another range invalidation fix Peter Maydell
2021-05-25 15:01 ` [PULL 002/114] hw/intc/arm_gicv3_cpuif: Fix EOIR write access check logic Peter Maydell
2021-05-25 15:01 ` [PULL 003/114] hw/arm/mps2-tz: Don't duplicate modelling of SRAM in AN524 Peter Maydell
2021-05-25 15:01 ` [PULL 004/114] hw/arm/mps2-tz: Make SRAM_ADDR_WIDTH board-specific Peter Maydell
2021-05-25 15:01 ` [PULL 005/114] hw/arm/armsse.c: Correct modelling of SSE-300 internal SRAMs Peter Maydell
2021-05-25 15:01 ` [PULL 006/114] hw/arm/armsse: Convert armsse_realize() to use ERRP_GUARD Peter Maydell
2021-05-25 15:01 ` [PULL 007/114] hw/arm/mps2-tz: Allow board to specify a boot RAM size Peter Maydell
2021-05-25 15:01 ` [PULL 008/114] hw/arm: Model TCMs in the SSE-300, not the AN547 Peter Maydell
2021-05-25 15:01 ` [PULL 009/114] target/arm: Use correct SP in M-profile exception return Peter Maydell
2021-05-25 15:01 ` [PULL 010/114] accel/tcg: Replace g_new() + memcpy() by g_memdup() Peter Maydell
2021-05-25 15:01 ` [PULL 011/114] accel/tcg: Pass length argument to tlb_flush_range_locked() Peter Maydell
2021-05-25 15:01 ` [PULL 012/114] accel/tlb: Rename TLBFlushPageBitsByMMUIdxData -> TLBFlushRangeData Peter Maydell
2021-05-25 15:01 ` [PULL 013/114] accel/tcg: Remove {encode,decode}_pbm_to_runon Peter Maydell
2021-05-25 15:01 ` [PULL 014/114] accel/tcg: Add tlb_flush_range_by_mmuidx() Peter Maydell
2021-05-25 15:01 ` [PULL 015/114] accel/tcg: Add tlb_flush_range_by_mmuidx_all_cpus() Peter Maydell
2021-05-25 15:01 ` [PULL 016/114] accel/tlb: Add tlb_flush_range_by_mmuidx_all_cpus_synced() Peter Maydell
2021-05-25 15:01 ` [PULL 017/114] accel/tcg: Rename tlb_flush_page_bits -> range]_by_mmuidx_async_0 Peter Maydell
2021-05-25 15:01 ` [PULL 018/114] accel/tlb: Rename tlb_flush_[page_bits > range]_by_mmuidx_async_[2 > 1] Peter Maydell
2021-05-25 15:01 ` [PULL 019/114] target/arm: Add support for FEAT_TLBIRANGE Peter Maydell
2021-05-25 15:01 ` [PULL 020/114] target/arm: Add support for FEAT_TLBIOS Peter Maydell
2021-05-25 15:01 ` [PULL 021/114] target/arm: set ID_AA64ISAR0.TLB to 2 for max AARCH64 CPU type Peter Maydell
2021-05-25 15:01 ` [PULL 022/114] disas/libvixl: Protect C system header for C++ compiler Peter Maydell
2021-05-25 15:01 ` [PULL 023/114] target/arm: Add ID_AA64ZFR0 fields and isar_feature_aa64_sve2 Peter Maydell
2021-05-25 15:01 ` [PULL 024/114] target/arm: Implement SVE2 Integer Multiply - Unpredicated Peter Maydell
2021-05-25 15:01 ` [PULL 025/114] target/arm: Implement SVE2 integer pairwise add and accumulate long Peter Maydell
2021-05-25 15:01 ` [PULL 026/114] target/arm: Implement SVE2 integer unary operations (predicated) Peter Maydell
2021-05-25 15:01 ` [PULL 027/114] target/arm: Split out saturating/rounding shifts from neon Peter Maydell
2021-05-25 15:01 ` [PULL 028/114] target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated) Peter Maydell
2021-05-25 15:01 ` [PULL 029/114] target/arm: Implement SVE2 integer halving add/subtract (predicated) Peter Maydell
2021-05-25 15:02 ` [PULL 030/114] target/arm: Implement SVE2 integer pairwise arithmetic Peter Maydell
2021-05-25 15:02 ` [PULL 031/114] target/arm: Implement SVE2 saturating add/subtract (predicated) Peter Maydell
2021-05-25 15:02 ` [PULL 032/114] target/arm: Implement SVE2 integer add/subtract long Peter Maydell
2021-05-25 15:02 ` [PULL 033/114] target/arm: Implement SVE2 integer add/subtract interleaved long Peter Maydell
2021-05-25 15:02 ` [PULL 034/114] target/arm: Implement SVE2 integer add/subtract wide Peter Maydell
2021-05-25 15:02 ` [PULL 035/114] target/arm: Implement SVE2 integer multiply long Peter Maydell
2021-05-25 15:02 ` [PULL 036/114] target/arm: Implement SVE2 PMULLB, PMULLT Peter Maydell
2021-05-25 15:02 ` [PULL 037/114] target/arm: Implement SVE2 bitwise shift left long Peter Maydell
2021-05-25 15:02 ` [PULL 038/114] target/arm: Implement SVE2 bitwise exclusive-or interleaved Peter Maydell
2021-05-25 15:02 ` [PULL 039/114] target/arm: Implement SVE2 bitwise permute Peter Maydell
2021-05-25 15:02 ` [PULL 040/114] target/arm: Implement SVE2 complex integer add Peter Maydell
2021-05-25 15:02 ` [PULL 041/114] target/arm: Implement SVE2 integer absolute difference and accumulate long Peter Maydell
2021-05-25 15:02 ` [PULL 042/114] target/arm: Implement SVE2 integer add/subtract long with carry Peter Maydell
2021-05-25 15:02 ` [PULL 043/114] target/arm: Implement SVE2 bitwise shift right and accumulate Peter Maydell
2021-05-25 15:02 ` [PULL 044/114] target/arm: Implement SVE2 bitwise shift and insert Peter Maydell
2021-05-25 15:02 ` [PULL 045/114] target/arm: Implement SVE2 integer absolute difference and accumulate Peter Maydell
2021-05-25 15:02 ` [PULL 046/114] target/arm: Implement SVE2 saturating extract narrow Peter Maydell
2021-05-25 15:02 ` [PULL 047/114] target/arm: Implement SVE2 floating-point pairwise Peter Maydell
2021-05-25 15:02 ` [PULL 048/114] target/arm: Implement SVE2 SHRN, RSHRN Peter Maydell
2021-05-25 15:02 ` [PULL 049/114] target/arm: Implement SVE2 SQSHRUN, SQRSHRUN Peter Maydell
2021-05-25 15:02 ` [PULL 050/114] target/arm: Implement SVE2 UQSHRN, UQRSHRN Peter Maydell
2021-05-25 15:02 ` [PULL 051/114] target/arm: Implement SVE2 SQSHRN, SQRSHRN Peter Maydell
2021-05-25 15:02 ` [PULL 052/114] target/arm: Implement SVE2 WHILEGT, WHILEGE, WHILEHI, WHILEHS Peter Maydell
2021-05-25 15:02 ` [PULL 053/114] target/arm: Implement SVE2 WHILERW, WHILEWR Peter Maydell
2021-05-25 15:02 ` [PULL 054/114] target/arm: Implement SVE2 bitwise ternary operations Peter Maydell
2021-05-25 15:02 ` [PULL 055/114] target/arm: Implement SVE2 MATCH, NMATCH Peter Maydell
2021-05-25 15:02 ` [PULL 056/114] target/arm: Implement SVE2 saturating multiply-add long Peter Maydell
2021-05-25 15:02 ` [PULL 057/114] target/arm: Implement SVE2 saturating multiply-add high Peter Maydell
2021-05-25 15:02 ` [PULL 058/114] target/arm: Implement SVE2 integer multiply-add long Peter Maydell
2021-05-25 15:02 ` [PULL 059/114] target/arm: Implement SVE2 complex integer multiply-add Peter Maydell
2021-05-25 15:02 ` [PULL 060/114] target/arm: Implement SVE2 ADDHNB, ADDHNT Peter Maydell
2021-05-25 15:02 ` [PULL 061/114] target/arm: Implement SVE2 RADDHNB, RADDHNT Peter Maydell
2021-05-25 15:02 ` [PULL 062/114] target/arm: Implement SVE2 SUBHNB, SUBHNT Peter Maydell
2021-05-25 15:02 ` [PULL 063/114] target/arm: Implement SVE2 RSUBHNB, RSUBHNT Peter Maydell
2021-05-25 15:02 ` [PULL 064/114] target/arm: Implement SVE2 HISTCNT, HISTSEG Peter Maydell
2021-05-25 15:02 ` [PULL 065/114] target/arm: Implement SVE2 XAR Peter Maydell
2021-05-25 15:02 ` [PULL 066/114] target/arm: Implement SVE2 scatter store insns Peter Maydell
2021-05-25 15:02 ` [PULL 067/114] target/arm: Implement SVE2 gather load insns Peter Maydell
2021-05-25 15:02 ` [PULL 068/114] target/arm: Implement SVE2 FMMLA Peter Maydell
2021-05-25 15:02 ` [PULL 069/114] target/arm: Implement SVE2 SPLICE, EXT Peter Maydell
2021-05-25 15:02 ` [PULL 070/114] target/arm: Use correct output type for gvec_sdot_*_b Peter Maydell
2021-05-25 15:02 ` Peter Maydell [this message]
2021-05-25 15:02 ` [PULL 072/114] target/arm: Pass separate addend to FCMLA helpers Peter Maydell
2021-05-25 15:02 ` [PULL 073/114] target/arm: Split out formats for 2 vectors + 1 index Peter Maydell
2021-05-25 15:02 ` [PULL 074/114] target/arm: Split out formats for 3 " Peter Maydell
2021-05-25 15:02 ` [PULL 075/114] target/arm: Implement SVE2 integer multiply (indexed) Peter Maydell
2021-05-25 15:02 ` [PULL 076/114] target/arm: Implement SVE2 integer multiply-add (indexed) Peter Maydell
2021-05-25 15:02 ` [PULL 077/114] target/arm: Implement SVE2 saturating multiply-add high (indexed) Peter Maydell
2021-05-25 15:02 ` [PULL 078/114] target/arm: Implement SVE2 saturating multiply-add (indexed) Peter Maydell
2021-05-25 15:02 ` [PULL 079/114] target/arm: Implement SVE2 saturating multiply (indexed) Peter Maydell
2021-05-25 15:02 ` [PULL 080/114] target/arm: Implement SVE2 signed saturating doubling multiply high Peter Maydell
2021-05-25 15:02 ` [PULL 081/114] target/arm: Implement SVE2 saturating multiply high (indexed) Peter Maydell
2021-05-25 15:02 ` [PULL 082/114] target/arm: Implement SVE2 multiply-add long (indexed) Peter Maydell
2021-05-25 15:02 ` [PULL 083/114] target/arm: Implement SVE2 integer multiply " Peter Maydell
2021-05-25 15:02 ` [PULL 084/114] target/arm: Implement SVE2 complex integer multiply-add (indexed) Peter Maydell
2021-05-25 15:02 ` [PULL 085/114] target/arm: Implement SVE2 complex integer dot product Peter Maydell
2021-05-25 15:02 ` [PULL 086/114] target/arm: Macroize helper_gvec_{s,u}dot_{b,h} Peter Maydell
2021-05-25 15:02 ` [PULL 087/114] target/arm: Macroize helper_gvec_{s,u}dot_idx_{b,h} Peter Maydell
2021-05-25 15:02 ` [PULL 088/114] target/arm: Implement SVE mixed sign dot product (indexed) Peter Maydell
2021-05-25 15:02 ` [PULL 089/114] target/arm: Implement SVE mixed sign dot product Peter Maydell
2021-05-25 15:03 ` [PULL 090/114] target/arm: Implement SVE2 crypto unary operations Peter Maydell
2021-05-25 15:03 ` [PULL 091/114] target/arm: Implement SVE2 crypto destructive binary operations Peter Maydell
2021-05-25 15:03 ` [PULL 092/114] target/arm: Implement SVE2 crypto constructive " Peter Maydell
2021-05-25 15:03 ` [PULL 093/114] target/arm: Implement SVE2 TBL, TBX Peter Maydell
2021-05-25 15:03 ` [PULL 094/114] target/arm: Implement SVE2 FCVTNT Peter Maydell
2021-05-25 16:30 ` [PULL 000/114] target-arm queue Peter Maydell

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=20210525150324.32370-72-peter.maydell@linaro.org \
    --to=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --subject='Re: [PULL 071/114] target/arm: Pass separate addend to {U, S}DOT helpers' \
    /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.