All of lore.kernel.org
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: Peter Maydell <peter.maydell@linaro.org>, qemu-arm@nongnu.org
Subject: [PATCH v7 49/92] target/arm: Pass separate addend to {U, S}DOT helpers
Date: Mon, 24 May 2021 18:03:15 -0700	[thread overview]
Message-ID: <20210525010358.152808-50-richard.henderson@linaro.org> (raw)
In-Reply-To: <20210525010358.152808-1-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>
---
v4: Fix double addition (zhiwei).
v7: Split out type changes.
---
 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 23a7ec5638..f4b092ee1c 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 67b6466a1e..04ef38f148 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 bdd47208b1..61c5fa9656 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 658bd275da..fa67605fdc 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 46f87ee259..2864c3a3cf 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 48e3addd81..f88e572132 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));
 }
 
-- 
2.25.1



  parent reply	other threads:[~2021-05-25  1:48 UTC|newest]

Thread overview: 95+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-25  1:02 [PATCH v7 00/92] target/arm: Implement SVE2 Richard Henderson
2021-05-25  1:02 ` [PATCH v7 01/92] target/arm: Add ID_AA64ZFR0 fields and isar_feature_aa64_sve2 Richard Henderson
2021-05-25  1:02 ` [PATCH v7 02/92] target/arm: Implement SVE2 Integer Multiply - Unpredicated Richard Henderson
2021-05-25  1:02 ` [PATCH v7 03/92] target/arm: Implement SVE2 integer pairwise add and accumulate long Richard Henderson
2021-05-25  1:02 ` [PATCH v7 04/92] target/arm: Implement SVE2 integer unary operations (predicated) Richard Henderson
2021-05-25  1:02 ` [PATCH v7 05/92] target/arm: Split out saturating/rounding shifts from neon Richard Henderson
2021-05-25  1:02 ` [PATCH v7 06/92] target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated) Richard Henderson
2021-05-25  1:02 ` [PATCH v7 07/92] target/arm: Implement SVE2 integer halving add/subtract (predicated) Richard Henderson
2021-05-25  1:02 ` [PATCH v7 08/92] target/arm: Implement SVE2 integer pairwise arithmetic Richard Henderson
2021-05-25  1:02 ` [PATCH v7 09/92] target/arm: Implement SVE2 saturating add/subtract (predicated) Richard Henderson
2021-05-25  1:02 ` [PATCH v7 10/92] target/arm: Implement SVE2 integer add/subtract long Richard Henderson
2021-05-25  1:02 ` [PATCH v7 11/92] target/arm: Implement SVE2 integer add/subtract interleaved long Richard Henderson
2021-05-25  1:02 ` [PATCH v7 12/92] target/arm: Implement SVE2 integer add/subtract wide Richard Henderson
2021-05-25  1:02 ` [PATCH v7 13/92] target/arm: Implement SVE2 integer multiply long Richard Henderson
2021-05-25  1:02 ` [PATCH v7 14/92] target/arm: Implement SVE2 PMULLB, PMULLT Richard Henderson
2021-05-25  1:02 ` [PATCH v7 15/92] target/arm: Implement SVE2 bitwise shift left long Richard Henderson
2021-05-25  1:02 ` [PATCH v7 16/92] target/arm: Implement SVE2 bitwise exclusive-or interleaved Richard Henderson
2021-05-25  1:02 ` [PATCH v7 17/92] target/arm: Implement SVE2 bitwise permute Richard Henderson
2021-05-25  1:02 ` [PATCH v7 18/92] target/arm: Implement SVE2 complex integer add Richard Henderson
2021-05-25  1:02 ` [PATCH v7 19/92] target/arm: Implement SVE2 integer absolute difference and accumulate long Richard Henderson
2021-05-25  1:02 ` [PATCH v7 20/92] target/arm: Implement SVE2 integer add/subtract long with carry Richard Henderson
2021-05-25  1:02 ` [PATCH v7 21/92] target/arm: Implement SVE2 bitwise shift right and accumulate Richard Henderson
2021-05-25  1:02 ` [PATCH v7 22/92] target/arm: Implement SVE2 bitwise shift and insert Richard Henderson
2021-05-25  1:02 ` [PATCH v7 23/92] target/arm: Implement SVE2 integer absolute difference and accumulate Richard Henderson
2021-05-25  1:02 ` [PATCH v7 24/92] target/arm: Implement SVE2 saturating extract narrow Richard Henderson
2021-05-25  1:02 ` [PATCH v7 25/92] target/arm: Implement SVE2 floating-point pairwise Richard Henderson
2021-05-25  1:02 ` [PATCH v7 26/92] target/arm: Implement SVE2 SHRN, RSHRN Richard Henderson
2021-05-25  1:02 ` [PATCH v7 27/92] target/arm: Implement SVE2 SQSHRUN, SQRSHRUN Richard Henderson
2021-05-25  1:02 ` [PATCH v7 28/92] target/arm: Implement SVE2 UQSHRN, UQRSHRN Richard Henderson
2021-05-25  1:02 ` [PATCH v7 29/92] target/arm: Implement SVE2 SQSHRN, SQRSHRN Richard Henderson
2021-05-25  1:02 ` [PATCH v7 30/92] target/arm: Implement SVE2 WHILEGT, WHILEGE, WHILEHI, WHILEHS Richard Henderson
2021-05-25  1:02 ` [PATCH v7 31/92] target/arm: Implement SVE2 WHILERW, WHILEWR Richard Henderson
2021-05-25  1:02 ` [PATCH v7 32/92] target/arm: Implement SVE2 bitwise ternary operations Richard Henderson
2021-05-25  1:02 ` [PATCH v7 33/92] target/arm: Implement SVE2 MATCH, NMATCH Richard Henderson
2021-05-25  1:03 ` [PATCH v7 34/92] target/arm: Implement SVE2 saturating multiply-add long Richard Henderson
2021-05-25  1:03 ` [PATCH v7 35/92] target/arm: Implement SVE2 saturating multiply-add high Richard Henderson
2021-05-25  1:03 ` [PATCH v7 36/92] target/arm: Implement SVE2 integer multiply-add long Richard Henderson
2021-05-25  1:03 ` [PATCH v7 37/92] target/arm: Implement SVE2 complex integer multiply-add Richard Henderson
2021-05-25  1:03 ` [PATCH v7 38/92] target/arm: Implement SVE2 ADDHNB, ADDHNT Richard Henderson
2021-05-25  1:03 ` [PATCH v7 39/92] target/arm: Implement SVE2 RADDHNB, RADDHNT Richard Henderson
2021-05-25  1:03 ` [PATCH v7 40/92] target/arm: Implement SVE2 SUBHNB, SUBHNT Richard Henderson
2021-05-25  1:03 ` [PATCH v7 41/92] target/arm: Implement SVE2 RSUBHNB, RSUBHNT Richard Henderson
2021-05-25  1:03 ` [PATCH v7 42/92] target/arm: Implement SVE2 HISTCNT, HISTSEG Richard Henderson
2021-05-25  1:03 ` [PATCH v7 43/92] target/arm: Implement SVE2 XAR Richard Henderson
2021-05-25  1:03 ` [PATCH v7 44/92] target/arm: Implement SVE2 scatter store insns Richard Henderson
2021-05-25  1:03 ` [PATCH v7 45/92] target/arm: Implement SVE2 gather load insns Richard Henderson
2021-05-25  1:03 ` [PATCH v7 46/92] target/arm: Implement SVE2 FMMLA Richard Henderson
2021-05-25  1:03 ` [PATCH v7 47/92] target/arm: Implement SVE2 SPLICE, EXT Richard Henderson
2021-05-25  1:03 ` [PATCH v7 48/92] target/arm: Use correct output type for gvec_sdot_*_b Richard Henderson
2021-05-25  1:03 ` Richard Henderson [this message]
2021-05-25  1:03 ` [PATCH v7 50/92] target/arm: Pass separate addend to FCMLA helpers Richard Henderson
2021-05-25  1:03 ` [PATCH v7 51/92] target/arm: Split out formats for 2 vectors + 1 index Richard Henderson
2021-05-25  1:03 ` [PATCH v7 52/92] target/arm: Split out formats for 3 " Richard Henderson
2021-05-25  1:03 ` [PATCH v7 53/92] target/arm: Implement SVE2 integer multiply (indexed) Richard Henderson
2021-05-25  1:03 ` [PATCH v7 54/92] target/arm: Implement SVE2 integer multiply-add (indexed) Richard Henderson
2021-05-25  1:03 ` [PATCH v7 55/92] target/arm: Implement SVE2 saturating multiply-add high (indexed) Richard Henderson
2021-05-25  1:03 ` [PATCH v7 56/92] target/arm: Implement SVE2 saturating multiply-add (indexed) Richard Henderson
2021-05-25  1:03 ` [PATCH v7 57/92] target/arm: Implement SVE2 saturating multiply (indexed) Richard Henderson
2021-05-25  1:03 ` [PATCH v7 58/92] target/arm: Implement SVE2 signed saturating doubling multiply high Richard Henderson
2021-05-25  1:03 ` [PATCH v7 59/92] target/arm: Implement SVE2 saturating multiply high (indexed) Richard Henderson
2021-05-25  1:03 ` [PATCH v7 60/92] target/arm: Implement SVE2 multiply-add long (indexed) Richard Henderson
2021-05-25  1:03 ` [PATCH v7 61/92] target/arm: Implement SVE2 integer multiply " Richard Henderson
2021-05-25  1:03 ` [PATCH v7 62/92] target/arm: Implement SVE2 complex integer multiply-add (indexed) Richard Henderson
2021-05-25  1:03 ` [PATCH v7 63/92] target/arm: Implement SVE2 complex integer dot product Richard Henderson
2021-05-25  1:03 ` [PATCH v7 64/92] target/arm: Macroize helper_gvec_{s,u}dot_{b,h} Richard Henderson
2021-05-25  1:03 ` [PATCH v7 65/92] target/arm: Macroize helper_gvec_{s,u}dot_idx_{b,h} Richard Henderson
2021-05-25  1:03 ` [PATCH v7 66/92] target/arm: Implement SVE mixed sign dot product (indexed) Richard Henderson
2021-05-25  1:03 ` [PATCH v7 67/92] target/arm: Implement SVE mixed sign dot product Richard Henderson
2021-05-25  1:03 ` [PATCH v7 68/92] target/arm: Implement SVE2 crypto unary operations Richard Henderson
2021-05-25  1:03 ` [PATCH v7 69/92] target/arm: Implement SVE2 crypto destructive binary operations Richard Henderson
2021-05-25  1:03 ` [PATCH v7 70/92] target/arm: Implement SVE2 crypto constructive " Richard Henderson
2021-05-25  1:03 ` [PATCH v7 71/92] target/arm: Implement SVE2 TBL, TBX Richard Henderson
2021-05-25  1:03 ` [PATCH v7 72/92] target/arm: Implement SVE2 FCVTNT Richard Henderson
2021-05-25  1:03 ` [PATCH v7 73/92] target/arm: Implement SVE2 FCVTLT Richard Henderson
2021-05-25  1:03 ` [PATCH v7 74/92] target/arm: Implement SVE2 FCVTXNT, FCVTX Richard Henderson
2021-05-25  1:03 ` [PATCH v7 75/92] target/arm: Implement SVE2 FLOGB Richard Henderson
2021-05-25  1:03 ` [PATCH v7 76/92] target/arm: Share table of sve load functions Richard Henderson
2021-05-25  1:03 ` [PATCH v7 77/92] target/arm: Tidy do_ldrq Richard Henderson
2021-05-25  1:03 ` [PATCH v7 78/92] target/arm: Implement SVE2 LD1RO Richard Henderson
2021-05-25  1:03 ` [PATCH v7 79/92] target/arm: Implement 128-bit ZIP, UZP, TRN Richard Henderson
2021-05-25  1:03 ` [PATCH v7 80/92] target/arm: Implement SVE2 bitwise shift immediate Richard Henderson
2021-05-25  1:03 ` [PATCH v7 81/92] target/arm: Move endian adjustment macros to vec_internal.h Richard Henderson
2021-05-25  1:03 ` [PATCH v7 82/92] target/arm: Implement SVE2 fp multiply-add long Richard Henderson
2021-05-25  1:03 ` [PATCH v7 83/92] target/arm: Implement aarch64 SUDOT, USDOT Richard Henderson
2021-05-25  1:03 ` [PATCH v7 84/92] target/arm: Split out do_neon_ddda_fpst Richard Henderson
2021-05-25  1:03 ` [PATCH v7 85/92] target/arm: Remove unused fpst from VDOT_scalar Richard Henderson
2021-05-25  1:03 ` [PATCH v7 86/92] target/arm: Fix decode for VDOT (indexed) Richard Henderson
2021-05-25  1:03 ` [PATCH v7 87/92] target/arm: Split out do_neon_ddda Richard Henderson
2021-05-25  1:03 ` [PATCH v7 88/92] target/arm: Split decode of VSDOT and VUDOT Richard Henderson
2021-05-25  1:03 ` [PATCH v7 89/92] target/arm: Implement aarch32 VSUDOT, VUSDOT Richard Henderson
2021-05-25  1:03 ` [PATCH v7 90/92] target/arm: Implement integer matrix multiply accumulate Richard Henderson
2021-05-25  1:03 ` [PATCH v7 91/92] linux-user/aarch64: Enable hwcap bits for sve2 and related extensions Richard Henderson
2021-05-25  1:03 ` [PATCH v7 92/92] target/arm: Enable SVE2 " Richard Henderson
2021-05-25  2:37 ` [PATCH v7 00/92] target/arm: Implement SVE2 no-reply
2021-05-25 12:33 ` 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=20210525010358.152808-50-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-arm@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --subject='Re: [PATCH v7 49/92] 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.