hexagon: Q4_0 and MXFP4 repack fixes (llama/20527)

* hexagon: fix tail corruption with rows sizes not multiple of 256

* hexagon: use different stride for repacking partial blocks

* hex-mm: update repack and kernels to avoid shuffles for full 256-element blocks

Previous commit changed the repacking to use even:odd (0:1,2:3,..) packing
instead of the original (0:128,1:129,...) packing in order to fix tail corruption.
Since the mm kernels already deal with partial tails we can use even:odd
packing only for the last block.
This avoid performance penalty of having to shuffle to zip the elements
in the common case.

* hex-mm: update rmpy x8 for better optimizations

* hex-mm: tighten supported MUL_MAT checks to avoid spurios failures

* hex-mm: use vzero to init accumulators

* hex-mm: properly call partial rmpy_x8

diff --git a/src/ggml-hexagon/ggml-hexagon.cpp b/src/ggml-hexagon/ggml-hexagon.cpp
index d6e9776b87831620065347f0998f6e09af2643b6..19917cb114001493688561d77b5b7c292fb20439 100644 (file)
--- a/src/ggml-hexagon/ggml-hexagon.cpp
+++ b/src/ggml-hexagon/ggml-hexagon.cpp
@@ -402,6 +402,7 @@ static void pack_q4_0_quants(block_q4_0 * x, const uint8_t * qs, unsigned int bi
 static void repack_row_q4x4x2(uint8_t * y, const block_q4_0 * x, int64_t k) {
     static const int qk = QK_Q4_0x4x2;
     const int        nb = (k + qk - 1) / qk;  // number of blocks (padded)
+    const int        nloe = k % qk;           // leftovers
 
     const int dblk_size = 8 * 2;              // 8x __fp16
     const int qblk_size = qk / 2;             // int4
@@ -435,9 +436,11 @@ static void repack_row_q4x4x2(uint8_t * y, const block_q4_0 * x, int64_t k) {
         unpack_q4_0_quants(qs, &x[i * 8 + 6], 6);
         unpack_q4_0_quants(qs, &x[i * 8 + 7], 7);
 
+        bool partial = (nloe && i == nb-1);
+
         uint8_t * q = y_q + (i * qblk_size);
         for (int j = 0; j < qk / 2; j++) {
-            q[j] = (qs[j + 128] << 4) | qs[j];
+            q[j] = partial ? (qs[j*2+1] << 4) | qs[j*2+0] : (qs[j+128] << 4) | qs[j+000];
         }
     }
 
@@ -467,6 +470,7 @@ static void repack_row_q4x4x2(uint8_t * y, const block_q4_0 * x, int64_t k) {
 static void unpack_row_q4x4x2(block_q4_0 * x, const uint8_t * y, int64_t k) {
     static const int qk = QK_Q4_0x4x2;
     const int        nb = (k + qk - 1) / qk;  // number of blocks (padded)
+    const int        nloe = k % qk;           // leftovers
 
     const int dblk_size = 8 * 2;              // 8x __fp16
     const int qblk_size = qk / 2;             // int4
@@ -485,10 +489,17 @@ static void unpack_row_q4x4x2(block_q4_0 * x, const uint8_t * y, int64_t k) {
     for (int i = 0; i < nb; i++) {
         uint8_t qs[QK_Q4_0x4x2];  // unpacked quants
 
+        bool partial = (nloe && i == nb-1);
+
         const uint8_t * q = y_q + (i * qblk_size);
         for (int j = 0; j < qk / 2; j++) {
-            qs[j]       = q[j] & 0xf;
-            qs[j + 128] = q[j] >> 4;
+            if (partial) {
+                qs[j*2+0] = q[j] & 0xf;
+                qs[j*2+1] = q[j] >> 4;
+            } else {
+                qs[j+000] = q[j] & 0xf;
+                qs[j+128] = q[j] >> 4;
+            }
         }
 
         pack_q4_0_quants(&x[i * 8 + 0], qs, 0);
@@ -1078,6 +1089,7 @@ static void pack_mxfp4_quants(block_mxfp4 * x, const uint8_t * qs, unsigned int
 static void repack_row_mxfp4x4x2(uint8_t * y, const block_mxfp4 * x, int64_t k) {
     static const int qk = QK_MXFP4x4x2;
     const int        nb = (k + qk - 1) / qk;  // number of blocks (padded)
+    const int        nloe = k % qk;           // leftovers
 
     const int eblk_size = 8 * 1;              // 8x E8M0
     const int qblk_size = qk / 2;             // int4
@@ -1112,9 +1124,11 @@ static void repack_row_mxfp4x4x2(uint8_t * y, const block_mxfp4 * x, int64_t k)
         unpack_mxfp4_quants(qs, &x[i * 8 + 6], 6);
         unpack_mxfp4_quants(qs, &x[i * 8 + 7], 7);
 
+        bool partial = (nloe && i == nb-1);
+
         uint8_t * q = y_q + (i * qblk_size);
         for (int j = 0; j < qk / 2; j++) {
-            q[j] = (qs[j + 128] << 4) | qs[j];
+            q[j] = partial ? (qs[j*2+1] << 4) | qs[j*2+0] : (qs[j+128] << 4) | qs[j+000];
         }
     }
 
@@ -1144,6 +1158,7 @@ static void repack_row_mxfp4x4x2(uint8_t * y, const block_mxfp4 * x, int64_t k)
 static void unpack_row_mxfp4x4x2(block_mxfp4 * x, const uint8_t * y, int64_t k) {
     static const int qk = QK_MXFP4x4x2;
     const int        nb = (k + qk - 1) / qk;  // number of blocks (padded)
+    const int        nloe = k % qk;           // leftovers
 
     const int eblk_size = 8 * 1;              // 8x E8M0
     const int qblk_size = qk / 2;             // int4
@@ -1162,10 +1177,17 @@ static void unpack_row_mxfp4x4x2(block_mxfp4 * x, const uint8_t * y, int64_t k)
     for (int i = 0; i < nb; i++) {
         uint8_t qs[QK_MXFP4x4x2];  // unpacked quants
 
+        bool partial = (nloe && i == nb-1);
+
         const uint8_t * q = y_q + (i * qblk_size);
         for (int j = 0; j < qk / 2; j++) {
-            qs[j]       = q[j] & 0xf;
-            qs[j + 128] = q[j] >> 4;
+            if (partial) {
+                qs[j*2+0] = q[j] & 0xf;
+                qs[j*2+1] = q[j] >> 4;
+            } else {
+                qs[j+000] = q[j] & 0xf;
+                qs[j+128] = q[j] >> 4;
+            }
         }
 
         pack_mxfp4_quants(&x[i * 8 + 0], qs, 0);
@@ -1801,12 +1823,12 @@ static bool ggml_hexagon_supported_mul_mat(const struct ggml_hexagon_session * s
                 return false;
             }
 
-            if (src0->ne[1] > 16 * 1024) {
+            if (ggml_nrows(src0) > 16 * 1024) {
                 return false;  // typically the lm-head which would be too large for VTCM
             }
 
-            if ((src1->ne[2] != 1 || src1->ne[3] != 1)) {
-                return false;
+            if (ggml_nrows(src1) > 1024 || src1->ne[2] != 1 || src1->ne[3] != 1) {
+                return false;  // no huge batches or broadcasting (for now)
             }
 
             // src0 (weights) must be repacked
@@ -1820,6 +1842,9 @@ static bool ggml_hexagon_supported_mul_mat(const struct ggml_hexagon_session * s
                 GGML_LOG_DEBUG("ggml_hexagon_supported_mul_mat: permuted F16 src0 not supported\n");
                 return false;
             }
+            if (ggml_nrows(src1) > 1024) {
+                return false;  // no huge batches (for now)
+            }
             break;
 
         default:

diff --git a/src/ggml-hexagon/htp/matmul-ops.c b/src/ggml-hexagon/htp/matmul-ops.c
index 9ca74aedfef25eefa4d375fb3bc4a87fbc40b952..73aaba79ebf32c61cbf1289986c8c5d5f115af54 100644 (file)
--- a/src/ggml-hexagon/htp/matmul-ops.c
+++ b/src/ggml-hexagon/htp/matmul-ops.c
@@ -77,7 +77,7 @@ static inline size_t q8x4x2_row_size(uint32_t ne) {
     return hex_round_up(ne + nb * 8 * sizeof(__fp16), 128);
 }
 
-static inline HVX_Vector_x8 hvx_vec_load_q4x4x8(const uint8_t * restrict ptr) {
+static inline HVX_Vector_x8 hvx_vec_load_q4x4x8_full(const uint8_t * restrict ptr) {
     const HVX_Vector * restrict vptr = (const HVX_Vector *) ptr;
 
     HVX_Vector v0_1 = vptr[0];  // first 256 elements (128 bytes)
@@ -88,9 +88,9 @@ static inline HVX_Vector_x8 hvx_vec_load_q4x4x8(const uint8_t * restrict ptr) {
     const HVX_Vector mask_h4 = Q6_Vb_vsplat_R(0x0F);
     const HVX_Vector i8 = Q6_Vb_vsplat_R(8);
 
-    HVX_Vector v0 = Q6_V_vand_VV(v0_1, mask_h4);  // & 0x0F
-    HVX_Vector v1 = Q6_Vub_vlsr_VubR(v0_1, 4);    // >> 4
-    HVX_Vector v2 = Q6_V_vand_VV(v2_3, mask_h4);  // & 0x0F
+    HVX_Vector v0 = Q6_V_vand_VV(v0_1, mask_h4);  // & 0x0F : first  128 elements
+    HVX_Vector v1 = Q6_Vub_vlsr_VubR(v0_1, 4);    // >> 4   : second 128 elements
+    HVX_Vector v2 = Q6_V_vand_VV(v2_3, mask_h4);  // & 0x0F ...
     HVX_Vector v3 = Q6_Vub_vlsr_VubR(v2_3, 4);    // >> 4
     HVX_Vector v4 = Q6_V_vand_VV(v4_5, mask_h4);  // & 0x0F
     HVX_Vector v5 = Q6_Vub_vlsr_VubR(v4_5, 4);    // >> 4
@@ -111,7 +111,41 @@ static inline HVX_Vector_x8 hvx_vec_load_q4x4x8(const uint8_t * restrict ptr) {
     return r;
 }
 
-static inline HVX_Vector_x8 hvx_vec_load_mxfp4x4x8(const uint8_t * restrict ptr) {
+static HVX_Vector_x8 hvx_vec_load_q4x4x8_partial(const uint8_t * restrict ptr, uint32_t n) {
+    const HVX_Vector * restrict vptr = (const HVX_Vector *) ptr;
+
+    const uint32_t qk   = QK_Q4_0x4x2; // 256
+    const uint32_t nb   = n / qk;
+    const uint32_t nloe = n % qk;
+
+    const HVX_Vector mask_h4 = Q6_Vb_vsplat_R(0x0F);
+    const HVX_Vector i8      = Q6_Vb_vsplat_R(8);
+
+    HVX_Vector_x8 r;
+    uint32_t i = 0;
+
+    #pragma unroll(2)
+    for (i=0; i < nb; i++) {
+        HVX_Vector v = vptr[i];                    // 256 elements (128 bytes)
+        HVX_Vector v0 = Q6_V_vand_VV(v, mask_h4);  // & 0x0F : first  128 elements
+        HVX_Vector v1 = Q6_Vub_vlsr_VubR(v, 4);    // >> 4   : second 128 elements
+        r.v[i*2+0] = Q6_Vb_vsub_VbVb(v0, i8);
+        r.v[i*2+1] = Q6_Vb_vsub_VbVb(v1, i8);
+    }
+
+    if (nloe) {
+        HVX_Vector v = vptr[i];                    // 256 elements (128 bytes)
+        HVX_Vector v0 = Q6_V_vand_VV(v, mask_h4);  // & 0x0F : even 128 elements
+        HVX_Vector v1 = Q6_Vub_vlsr_VubR(v, 4);    // >> 4   : odd  128 elements
+        HVX_VectorPair v0_1_p = Q6_W_vshuff_VVR(v1, v0, -1); // zip even:odd:...
+        r.v[i*2+0] = Q6_Vb_vsub_VbVb(Q6_V_lo_W(v0_1_p), i8);
+        r.v[i*2+1] = Q6_Vb_vsub_VbVb(Q6_V_hi_W(v0_1_p), i8);
+    }
+
+    return r;
+}
+
+static inline HVX_Vector_x8 hvx_vec_load_mxfp4x4x8_full(const uint8_t * restrict ptr) {
     const HVX_Vector * restrict vptr = (const HVX_Vector *) ptr;
 
     HVX_Vector v0_1 = vptr[0];  // first 256 elements (128 bytes)
@@ -144,7 +178,41 @@ static inline HVX_Vector_x8 hvx_vec_load_mxfp4x4x8(const uint8_t * restrict ptr)
     return r;
 }
 
-static inline HVX_Vector_x8 hvx_vec_load_q8x4x8(const uint8_t * restrict ptr) {
+static inline HVX_Vector_x8 hvx_vec_load_mxfp4x4x8_partial(const uint8_t * restrict ptr, uint32_t n) {
+    const HVX_Vector * restrict vptr = (const HVX_Vector *) ptr;
+
+    const uint32_t qk   = QK_Q4_0x4x2; // 256
+    const uint32_t nb   = n / qk;
+    const uint32_t nloe = n % qk;
+
+    const HVX_Vector mask_h4 = Q6_Vb_vsplat_R(0x0F);
+    const HVX_Vector lut     = *(const HVX_Vector *) kvalues_mxfp4_lut;
+
+    HVX_Vector_x8 r;
+    uint32_t i = 0;
+
+    #pragma unroll(2)
+    for (i=0; i < nb; i++) {
+        HVX_Vector v = vptr[i];                    // 256 elements (128 bytes)
+        HVX_Vector v0 = Q6_V_vand_VV(v, mask_h4);  // & 0x0F : first  128 elements
+        HVX_Vector v1 = Q6_Vub_vlsr_VubR(v, 4);    // >> 4   : second 128 elements
+        r.v[i*2+0] = Q6_Vb_vlut32_VbVbI(v0, lut, 0);
+        r.v[i*2+1] = Q6_Vb_vlut32_VbVbI(v1, lut, 0);
+    }
+
+    if (nloe) {
+        HVX_Vector v = vptr[i];                    // 256 elements (128 bytes)
+        HVX_Vector v0 = Q6_V_vand_VV(v, mask_h4);  // & 0x0F : even 128 elements
+        HVX_Vector v1 = Q6_Vub_vlsr_VubR(v, 4);    // >> 4   : odd  128 elements
+        HVX_VectorPair v0_1_p = Q6_W_vshuff_VVR(v1, v0, -1); // zip even:odd:...
+        r.v[i*2+0] = Q6_Vb_vlut32_VbVbI(Q6_V_lo_W(v0_1_p), lut, 0);
+        r.v[i*2+1] = Q6_Vb_vlut32_VbVbI(Q6_V_hi_W(v0_1_p), lut, 0);
+    }
+
+    return r;
+}
+
+static inline HVX_Vector_x8 hvx_vec_load_q8x4x8_full(const uint8_t * restrict ptr) {
     const HVX_Vector * restrict vptr = (const HVX_Vector *) ptr;
 
     HVX_Vector v0 = vptr[0];  // first  128 vals
@@ -160,6 +228,10 @@ static inline HVX_Vector_x8 hvx_vec_load_q8x4x8(const uint8_t * restrict ptr) {
     return r;
 }
 
+static inline HVX_Vector_x8 hvx_vec_load_q8x4x8_partial(const uint8_t * restrict ptr, uint32_t nloe) {
+    return hvx_vec_load_q8x4x8_full(ptr);
+}
+
 // Reduce multiply 1024 x 1024 int8 elements (32x q4/8 blocks in 8x HVX vectors).
 // Accumulate each block into a single int32 value.
 // Return a single HVX vector with 32x int32 accumulators.
@@ -167,14 +239,14 @@ static inline HVX_Vector_x8 hvx_vec_load_q8x4x8(const uint8_t * restrict ptr) {
 // if() checks are optimized out at compile time -- make sure to pass N as a constexpr.
 
 static inline HVX_Vector hvx_vec_rmpy_x8_n(HVX_Vector_x8 x, HVX_Vector_x8 y, unsigned int n) {
-    HVX_Vector r0 = Q6_V_vsplat_R(0);
-    HVX_Vector r1 = Q6_V_vsplat_R(0);
-    HVX_Vector r2 = Q6_V_vsplat_R(0);
-    HVX_Vector r3 = Q6_V_vsplat_R(0);
-    HVX_Vector r4 = Q6_V_vsplat_R(0);
-    HVX_Vector r5 = Q6_V_vsplat_R(0);
-    HVX_Vector r6 = Q6_V_vsplat_R(0);
-    HVX_Vector r7 = Q6_V_vsplat_R(0);
+    HVX_Vector r0 = Q6_V_vzero();
+    HVX_Vector r1 = Q6_V_vzero();
+    HVX_Vector r2 = Q6_V_vzero();
+    HVX_Vector r3 = Q6_V_vzero();
+    HVX_Vector r4 = Q6_V_vzero();
+    HVX_Vector r5 = Q6_V_vzero();
+    HVX_Vector r6 = Q6_V_vzero();
+    HVX_Vector r7 = Q6_V_vzero();
 
     HVX_VectorPair p3;
     HVX_VectorPair p2;
@@ -213,15 +285,42 @@ static inline HVX_Vector hvx_vec_rmpy_x8_n(HVX_Vector_x8 x, HVX_Vector_x8 y, uns
 }
 
 static inline HVX_Vector hvx_vec_rmpy_x8_full(HVX_Vector_x8 x, HVX_Vector_x8 y) {
-    return hvx_vec_rmpy_x8_n(x, y, 1024);
+    HVX_Vector r0 = Q6_Vw_vrmpy_VbVb(x.v[0], y.v[0]);
+    HVX_Vector r1 = Q6_Vw_vrmpy_VbVb(x.v[1], y.v[1]);
+    HVX_Vector r2 = Q6_Vw_vrmpy_VbVb(x.v[2], y.v[2]);
+    HVX_Vector r3 = Q6_Vw_vrmpy_VbVb(x.v[3], y.v[3]);
+    HVX_Vector r4 = Q6_Vw_vrmpy_VbVb(x.v[4], y.v[4]);
+    HVX_Vector r5 = Q6_Vw_vrmpy_VbVb(x.v[5], y.v[5]);
+    HVX_Vector r6 = Q6_Vw_vrmpy_VbVb(x.v[6], y.v[6]);
+    HVX_Vector r7 = Q6_Vw_vrmpy_VbVb(x.v[7], y.v[7]);
+
+    HVX_VectorPair p0 = Q6_W_vdeal_VVR(r1, r0, -4);
+    HVX_VectorPair p1 = Q6_W_vdeal_VVR(r3, r2, -4);
+    HVX_VectorPair p2 = Q6_W_vdeal_VVR(r5, r4, -4);
+    HVX_VectorPair p3 = Q6_W_vdeal_VVR(r7, r6, -4);
+
+    r0 = Q6_Vw_vadd_VwVw(Q6_V_lo_W(p0), Q6_V_hi_W(p0));
+    r1 = Q6_Vw_vadd_VwVw(Q6_V_lo_W(p1), Q6_V_hi_W(p1));
+    r2 = Q6_Vw_vadd_VwVw(Q6_V_lo_W(p2), Q6_V_hi_W(p2));
+    r3 = Q6_Vw_vadd_VwVw(Q6_V_lo_W(p3), Q6_V_hi_W(p3));
+
+    p0 = Q6_W_vdeal_VVR(r1, r0, -4);
+    p1 = Q6_W_vdeal_VVR(r3, r2, -4);
+
+    r0 = Q6_Vw_vadd_VwVw(Q6_V_lo_W(p0), Q6_V_hi_W(p0));
+    r1 = Q6_Vw_vadd_VwVw(Q6_V_lo_W(p1), Q6_V_hi_W(p1));
+
+    p0 = Q6_W_vdeal_VVR(r1, r0, -4);
+    r0 = Q6_Vw_vadd_VwVw(Q6_V_lo_W(p0), Q6_V_hi_W(p0));
+
+    return r0;
 }
 
-// Handle most common cases of tensors not multiple of 1024.
-static inline HVX_Vector hvx_vec_rmpy_x8_nloe(HVX_Vector_x8 x, HVX_Vector_x8 y, unsigned int n) {
-    if (n <= 256) { return hvx_vec_rmpy_x8_n(x, y, 256); };
-    if (n <= 512) { return hvx_vec_rmpy_x8_n(x, y, 512); };
-    if (n <= 768) { return hvx_vec_rmpy_x8_n(x, y, 768); };
-    return hvx_vec_rmpy_x8_n(x, y, 1024);
+static inline HVX_Vector hvx_vec_rmpy_x8_partial(HVX_Vector_x8 x, HVX_Vector_x8 y, unsigned int n) {
+    if (n >= 512)
+        return hvx_vec_rmpy_x8_full(x, y);
+
+    return hvx_vec_rmpy_x8_partial(x, y, 512);
 }
 
 static void vec_dot_q4x4x2_q8x4x2_1x1(const int n, float * restrict s0, const void * restrict vx0, const void * restrict vy0) {
@@ -246,7 +345,7 @@ static void vec_dot_q4x4x2_q8x4x2_1x1(const int n, float * restrict s0, const vo
     const uint8_t * restrict y_d = ((const uint8_t *) vy0 + y_qrow_size);     // then scales
 
     // Row sum (sf)
-    HVX_Vector r0_sum = Q6_V_vsplat_R(0);
+    HVX_Vector r0_sum = Q6_V_vzero();
 
     // Multiply and accumulate into int32.
     // Compute combined scale (fp32).
@@ -257,12 +356,12 @@ static void vec_dot_q4x4x2_q8x4x2_1x1(const int n, float * restrict s0, const vo
 
     uint32_t i = 0;
     for (; i < nb; i++) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_q4x4x8(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_full(y_q    + i * y_qblk_size);
+        HVX_Vector_x8 r0_q = hvx_vec_load_q4x4x8_full(r0_x_q + i * x_qblk_size);
 
         HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r0_q, vy_q));
 
-        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d + i * y_dblk_size));
+        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d    + i * y_dblk_size));
         HVX_Vector r0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
 
         HVX_Vector r0_dd = Q6_Vsf_equals_Vqf32(Q6_V_lo_W(Q6_Wqf32_vmpy_VhfVhf(r0_d, vy_d)));
@@ -272,19 +371,19 @@ static void vec_dot_q4x4x2_q8x4x2_1x1(const int n, float * restrict s0, const vo
         r0_sum = Q6_Vsf_equals_Vqf32(Q6_Vqf32_vadd_Vqf32Vsf(r0_fa, r0_sum));
     }
 
-    // Process leftovers, we still load full 4x4x2 block but zero out unused scales/blocks
+    // Process leftovers
     if (nloe) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_q4x4x8(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_partial(y_q    + i * y_qblk_size, nloe);
+        HVX_Vector_x8 r0_q = hvx_vec_load_q4x4x8_partial(r0_x_q + i * x_qblk_size, nloe);
 
-        HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r0_q, vy_q, nloe));
+        HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r0_q, vy_q, nloe));
 
-        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d + i * y_dblk_size));
+        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d    + i * y_dblk_size));
         HVX_Vector r0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
 
         HVX_Vector r0_dd = Q6_Vsf_equals_Vqf32(Q6_V_lo_W(Q6_Wqf32_vmpy_VhfVhf(r0_d, vy_d)));
 
-        // Zero out unused scales
+        // Zero out unused elements
         HVX_VectorPred bmask = Q6_Q_vsetq_R(nloe / 8);
         r0_dd                = Q6_V_vand_QV(bmask, r0_dd);
         r0_ia                = Q6_V_vand_QV(bmask, r0_ia);
@@ -326,8 +425,8 @@ static void vec_dot_q4x4x2_q8x4x2_2x1(const int n, float * restrict s0,
     const uint8_t * restrict y_d = ((const uint8_t *) vy0 + y_qrow_size);     // then scales
 
     // Row sum (sf)
-    HVX_Vector r0_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r1_sum = Q6_V_vsplat_R(0);
+    HVX_Vector r0_sum = Q6_V_vzero();
+    HVX_Vector r1_sum = Q6_V_vzero();
 
     // Multiply and accumulate into int32.
     // Compute combined scale (fp32).
@@ -338,14 +437,14 @@ static void vec_dot_q4x4x2_q8x4x2_2x1(const int n, float * restrict s0,
 
     uint32_t i = 0;
     for (; i < nb; i++) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_q4x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q = hvx_vec_load_q4x4x8(r1_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_full(y_q    + i * y_qblk_size);
+        HVX_Vector_x8 r0_q = hvx_vec_load_q4x4x8_full(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 r1_q = hvx_vec_load_q4x4x8_full(r1_x_q + i * x_qblk_size);
 
         HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r0_q, vy_q));
         HVX_Vector r1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r1_q, vy_q));
 
-        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d + i * y_dblk_size));
+        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d    + i * y_dblk_size));
         HVX_Vector r0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
         HVX_Vector r1_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r1_x_d + i * x_dblk_size));
 
@@ -359,23 +458,23 @@ static void vec_dot_q4x4x2_q8x4x2_2x1(const int n, float * restrict s0,
         r1_sum = Q6_Vsf_equals_Vqf32(Q6_Vqf32_vadd_Vqf32Vsf(r1_fa, r1_sum));
     }
 
-    // Process leftovers, we still load full 4x4x2 block but zero out unused scales/blocks
+    // Process leftovers
     if (nloe) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_q4x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q = hvx_vec_load_q4x4x8(r1_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_partial(y_q    + i * y_qblk_size, nloe);
+        HVX_Vector_x8 r0_q = hvx_vec_load_q4x4x8_partial(r0_x_q + i * x_qblk_size, nloe);
+        HVX_Vector_x8 r1_q = hvx_vec_load_q4x4x8_partial(r1_x_q + i * x_qblk_size, nloe);
 
-        HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r0_q, vy_q, nloe));
-        HVX_Vector r1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r1_q, vy_q, nloe));
+        HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r0_q, vy_q, nloe));
+        HVX_Vector r1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r1_q, vy_q, nloe));
 
-        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d + i * y_dblk_size));
+        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d    + i * y_dblk_size));
         HVX_Vector r0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
         HVX_Vector r1_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r1_x_d + i * x_dblk_size));
 
         HVX_Vector r0_dd = Q6_Vsf_equals_Vqf32(Q6_V_lo_W(Q6_Wqf32_vmpy_VhfVhf(r0_d, vy_d)));
         HVX_Vector r1_dd = Q6_Vsf_equals_Vqf32(Q6_V_lo_W(Q6_Wqf32_vmpy_VhfVhf(r1_d, vy_d)));
 
-        // Zero out unused scales
+        // Zero out unused elements
         HVX_VectorPred bmask = Q6_Q_vsetq_R(nloe / 8);
         r0_dd                = Q6_V_vand_QV(bmask, r0_dd);
         r1_dd                = Q6_V_vand_QV(bmask, r1_dd);
@@ -423,10 +522,10 @@ static void vec_dot_q4x4x2_q8x4x2_2x2(const int n, float * restrict s0, float *
     const uint8_t * restrict y1_d = ((const uint8_t *) vy1) + y_qrow_size;    // then scales
 
     // Row sums (sf) - 4 accumulators for 2×2 tile
-    HVX_Vector r0_c0_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r0_c1_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r1_c0_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r1_c1_sum = Q6_V_vsplat_R(0);
+    HVX_Vector r0_c0_sum = Q6_V_vzero();
+    HVX_Vector r0_c1_sum = Q6_V_vzero();
+    HVX_Vector r1_c0_sum = Q6_V_vzero();
+    HVX_Vector r1_c1_sum = Q6_V_vzero();
 
     const uint32_t nb   = n / qk;  // num full blocks
     const uint32_t nloe = n % qk;  // num leftover elements
@@ -434,12 +533,12 @@ static void vec_dot_q4x4x2_q8x4x2_2x2(const int n, float * restrict s0, float *
     uint32_t i = 0;
     for (; i < nb; i++) {
         // Load src1 columns (reused across both src0 rows)
-        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8(y0_q + i * y_qblk_size);
-        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8(y1_q + i * y_qblk_size);
+        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8_full(y0_q + i * y_qblk_size);
+        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8_full(y1_q + i * y_qblk_size);
 
         // Load src0 rows (reused across both src1 columns)
-        HVX_Vector_x8 r0_q = hvx_vec_load_q4x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q = hvx_vec_load_q4x4x8(r1_x_q + i * x_qblk_size);
+        HVX_Vector_x8 r0_q = hvx_vec_load_q4x4x8_full(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 r1_q = hvx_vec_load_q4x4x8_full(r1_x_q + i * x_qblk_size);
 
         // Compute 4 dot products: r0×c0, r0×c1, r1×c0, r1×c1
         HVX_Vector r0_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r0_q, vy0_q));
@@ -448,8 +547,8 @@ static void vec_dot_q4x4x2_q8x4x2_2x2(const int n, float * restrict s0, float *
         HVX_Vector r1_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r1_q, vy1_q));
 
         // Load scales
-        HVX_Vector vy0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y0_d + i * y_dblk_size));
-        HVX_Vector vy1_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y1_d + i * y_dblk_size));
+        HVX_Vector vy0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y0_d   + i * y_dblk_size));
+        HVX_Vector vy1_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y1_d   + i * y_dblk_size));
         HVX_Vector r0_d  = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
         HVX_Vector r1_d  = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r1_x_d + i * x_dblk_size));
 
@@ -473,18 +572,18 @@ static void vec_dot_q4x4x2_q8x4x2_2x2(const int n, float * restrict s0, float *
 
     // Process leftovers
     if (nloe) {
-        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8(y0_q + i * y_qblk_size);
-        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8(y1_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_q4x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q = hvx_vec_load_q4x4x8(r1_x_q + i * x_qblk_size);
-
-        HVX_Vector r0_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r0_q, vy0_q, nloe));
-        HVX_Vector r0_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r0_q, vy1_q, nloe));
-        HVX_Vector r1_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r1_q, vy0_q, nloe));
-        HVX_Vector r1_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r1_q, vy1_q, nloe));
-
-        HVX_Vector vy0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y0_d + i * y_dblk_size));
-        HVX_Vector vy1_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y1_d + i * y_dblk_size));
+        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8_partial(y0_q   + i * y_qblk_size, nloe);
+        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8_partial(y1_q   + i * y_qblk_size, nloe);
+        HVX_Vector_x8 r0_q  = hvx_vec_load_q4x4x8_partial(r0_x_q + i * x_qblk_size, nloe);
+        HVX_Vector_x8 r1_q  = hvx_vec_load_q4x4x8_partial(r1_x_q + i * x_qblk_size, nloe);
+
+        HVX_Vector r0_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r0_q, vy0_q, nloe));
+        HVX_Vector r0_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r0_q, vy1_q, nloe));
+        HVX_Vector r1_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r1_q, vy0_q, nloe));
+        HVX_Vector r1_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r1_q, vy1_q, nloe));
+
+        HVX_Vector vy0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y0_d   + i * y_dblk_size));
+        HVX_Vector vy1_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y1_d   + i * y_dblk_size));
         HVX_Vector r0_d  = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
         HVX_Vector r1_d  = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r1_x_d + i * x_dblk_size));
 
@@ -545,7 +644,7 @@ static void vec_dot_q8x4x2_q8x4x2_1x1(const int n, float * restrict s0, const vo
     const uint8_t * restrict y_d = ((const uint8_t *) vy0 + y_qrow_size);    // then scales
 
     // Row sum (sf)
-    HVX_Vector r0_sum = Q6_V_vsplat_R(0);
+    HVX_Vector r0_sum = Q6_V_vzero();
 
     // Multiply and accumulate into int32.
     // Compute combined scale (fp32).
@@ -556,12 +655,12 @@ static void vec_dot_q8x4x2_q8x4x2_1x1(const int n, float * restrict s0, const vo
 
     uint32_t i = 0;
     for (; i < nb; i++) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_q8x4x8(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_full(y_q    + i * y_qblk_size);
+        HVX_Vector_x8 r0_q = hvx_vec_load_q8x4x8_full(r0_x_q + i * x_qblk_size);
 
         HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r0_q, vy_q));
 
-        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d + i * y_dblk_size));
+        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d    + i * y_dblk_size));
         HVX_Vector r0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
 
         HVX_Vector r0_dd = Q6_Vsf_equals_Vqf32(Q6_V_lo_W(Q6_Wqf32_vmpy_VhfVhf(r0_d, vy_d)));
@@ -571,19 +670,19 @@ static void vec_dot_q8x4x2_q8x4x2_1x1(const int n, float * restrict s0, const vo
         r0_sum = Q6_Vsf_equals_Vqf32(Q6_Vqf32_vadd_Vqf32Vsf(r0_fa, r0_sum));
     }
 
-    // Process leftovers, we still load full 4x4x2 block but zero out unused scales/blocks
+    // Process leftovers
     if (nloe) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_q8x4x8(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_partial(y_q    + i * y_qblk_size, nloe);
+        HVX_Vector_x8 r0_q = hvx_vec_load_q8x4x8_partial(r0_x_q + i * x_qblk_size, nloe);
 
-        HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r0_q, vy_q, nloe));
+        HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r0_q, vy_q, nloe));
 
-        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d + i * y_dblk_size));
+        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d    + i * y_dblk_size));
         HVX_Vector r0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
 
         HVX_Vector r0_dd = Q6_Vsf_equals_Vqf32(Q6_V_lo_W(Q6_Wqf32_vmpy_VhfVhf(r0_d, vy_d)));
 
-        // Zero out unused scales
+        // Zero out unused elements
         HVX_VectorPred bmask = Q6_Q_vsetq_R(nloe / 8);
         r0_dd                = Q6_V_vand_QV(bmask, r0_dd);
         r0_ia                = Q6_V_vand_QV(bmask, r0_ia);
@@ -625,8 +724,8 @@ static void vec_dot_q8x4x2_q8x4x2_2x1(const int n, float * restrict s0,
     const uint8_t * restrict y_d = ((const uint8_t *) vy0 + y_qrow_size);     // then scales
 
     // Row sum (qf32)
-    HVX_Vector r0_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r1_sum = Q6_V_vsplat_R(0);
+    HVX_Vector r0_sum = Q6_V_vzero();
+    HVX_Vector r1_sum = Q6_V_vzero();
 
     // Multiply and accumulate into int32.
     // Compute combined scale (fp32).
@@ -637,14 +736,14 @@ static void vec_dot_q8x4x2_q8x4x2_2x1(const int n, float * restrict s0,
 
     uint32_t i = 0;
     for (; i < nb; i++) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_q8x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q = hvx_vec_load_q8x4x8(r1_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_full(y_q    + i * y_qblk_size);
+        HVX_Vector_x8 r0_q = hvx_vec_load_q8x4x8_full(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 r1_q = hvx_vec_load_q8x4x8_full(r1_x_q + i * x_qblk_size);
 
         HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r0_q, vy_q));
         HVX_Vector r1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r1_q, vy_q));
 
-        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d + i * y_dblk_size));
+        HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d    + i * y_dblk_size));
         HVX_Vector r0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
         HVX_Vector r1_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r1_x_d + i * x_dblk_size));
 
@@ -658,14 +757,14 @@ static void vec_dot_q8x4x2_q8x4x2_2x1(const int n, float * restrict s0,
         r1_sum = Q6_Vsf_equals_Vqf32(Q6_Vqf32_vadd_Vqf32Vsf(r1_fa, r1_sum));
     }
 
-    // Process leftovers, we still load full 4x4x2 block but zero out unused scales/blocks
+    // Process leftovers
     if (nloe) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_q8x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q = hvx_vec_load_q8x4x8(r1_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_partial(y_q    + i * y_qblk_size, nloe);
+        HVX_Vector_x8 r0_q = hvx_vec_load_q8x4x8_partial(r0_x_q + i * x_qblk_size, nloe);
+        HVX_Vector_x8 r1_q = hvx_vec_load_q8x4x8_partial(r1_x_q + i * x_qblk_size, nloe);
 
-        HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r0_q, vy_q, nloe));
-        HVX_Vector r1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r1_q, vy_q, nloe));
+        HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r0_q, vy_q, nloe));
+        HVX_Vector r1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r1_q, vy_q, nloe));
 
         HVX_Vector vy_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y_d + i * y_dblk_size));
         HVX_Vector r0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
@@ -674,7 +773,7 @@ static void vec_dot_q8x4x2_q8x4x2_2x1(const int n, float * restrict s0,
         HVX_Vector r0_dd = Q6_Vsf_equals_Vqf32(Q6_V_lo_W(Q6_Wqf32_vmpy_VhfVhf(r0_d, vy_d)));
         HVX_Vector r1_dd = Q6_Vsf_equals_Vqf32(Q6_V_lo_W(Q6_Wqf32_vmpy_VhfVhf(r1_d, vy_d)));
 
-        // Zero out unused scales
+        // Zero out unused elements
         HVX_VectorPred bmask = Q6_Q_vsetq_R(nloe / 8);
         r0_dd                = Q6_V_vand_QV(bmask, r0_dd);
         r1_dd                = Q6_V_vand_QV(bmask, r1_dd);
@@ -722,10 +821,10 @@ static void vec_dot_q8x4x2_q8x4x2_2x2(const int n, float * restrict s0, float *
     const uint8_t * restrict y1_d = ((const uint8_t *) vy1) + y_qrow_size;    // then scales
 
     // Row sums (sf) - 4 accumulators for 2×2 tile
-    HVX_Vector r0_c0_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r0_c1_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r1_c0_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r1_c1_sum = Q6_V_vsplat_R(0);
+    HVX_Vector r0_c0_sum = Q6_V_vzero();
+    HVX_Vector r0_c1_sum = Q6_V_vzero();
+    HVX_Vector r1_c0_sum = Q6_V_vzero();
+    HVX_Vector r1_c1_sum = Q6_V_vzero();
 
     const uint32_t nb   = n / qk;  // num full blocks
     const uint32_t nloe = n % qk;  // num leftover elements
@@ -733,12 +832,12 @@ static void vec_dot_q8x4x2_q8x4x2_2x2(const int n, float * restrict s0, float *
     uint32_t i = 0;
     for (; i < nb; i++) {
         // Load src1 columns (reused across both src0 rows)
-        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8(y0_q + i * y_qblk_size);
-        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8(y1_q + i * y_qblk_size);
+        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8_full(y0_q + i * y_qblk_size);
+        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8_full(y1_q + i * y_qblk_size);
 
         // Load src0 rows (reused across both src1 columns)
-        HVX_Vector_x8 r0_q = hvx_vec_load_q8x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q = hvx_vec_load_q8x4x8(r1_x_q + i * x_qblk_size);
+        HVX_Vector_x8 r0_q = hvx_vec_load_q8x4x8_full(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 r1_q = hvx_vec_load_q8x4x8_full(r1_x_q + i * x_qblk_size);
 
         // Compute 4 dot products: r0×c0, r0×c1, r1×c0, r1×c1
         HVX_Vector r0_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r0_q, vy0_q));
@@ -747,8 +846,8 @@ static void vec_dot_q8x4x2_q8x4x2_2x2(const int n, float * restrict s0, float *
         HVX_Vector r1_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r1_q, vy1_q));
 
         // Load scales
-        HVX_Vector vy0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y0_d + i * y_dblk_size));
-        HVX_Vector vy1_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y1_d + i * y_dblk_size));
+        HVX_Vector vy0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y0_d   + i * y_dblk_size));
+        HVX_Vector vy1_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y1_d   + i * y_dblk_size));
         HVX_Vector r0_d  = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
         HVX_Vector r1_d  = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r1_x_d + i * x_dblk_size));
 
@@ -772,18 +871,18 @@ static void vec_dot_q8x4x2_q8x4x2_2x2(const int n, float * restrict s0, float *
 
     // Process leftovers
     if (nloe) {
-        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8(y0_q + i * y_qblk_size);
-        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8(y1_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q  = hvx_vec_load_q8x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q  = hvx_vec_load_q8x4x8(r1_x_q + i * x_qblk_size);
-
-        HVX_Vector r0_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r0_q, vy0_q, nloe));
-        HVX_Vector r0_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r0_q, vy1_q, nloe));
-        HVX_Vector r1_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r1_q, vy0_q, nloe));
-        HVX_Vector r1_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r1_q, vy1_q, nloe));
-
-        HVX_Vector vy0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y0_d + i * y_dblk_size));
-        HVX_Vector vy1_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y1_d + i * y_dblk_size));
+        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8_partial(y0_q   + i * y_qblk_size, nloe);
+        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8_partial(y1_q   + i * y_qblk_size, nloe);
+        HVX_Vector_x8 r0_q  = hvx_vec_load_q8x4x8_partial(r0_x_q + i * x_qblk_size, nloe);
+        HVX_Vector_x8 r1_q  = hvx_vec_load_q8x4x8_partial(r1_x_q + i * x_qblk_size, nloe);
+
+        HVX_Vector r0_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r0_q, vy0_q, nloe));
+        HVX_Vector r0_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r0_q, vy1_q, nloe));
+        HVX_Vector r1_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r1_q, vy0_q, nloe));
+        HVX_Vector r1_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r1_q, vy1_q, nloe));
+
+        HVX_Vector vy0_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y0_d   + i * y_dblk_size));
+        HVX_Vector vy1_d = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (y1_d   + i * y_dblk_size));
         HVX_Vector r0_d  = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r0_x_d + i * x_dblk_size));
         HVX_Vector r1_d  = Q6_Vh_vshuff_Vh(*(const HVX_UVector *) (r1_x_d + i * x_dblk_size));
 
@@ -792,7 +891,7 @@ static void vec_dot_q8x4x2_q8x4x2_2x2(const int n, float * restrict s0, float *
         HVX_Vector r1_c0_dd = Q6_Vsf_equals_Vqf32(Q6_V_lo_W(Q6_Wqf32_vmpy_VhfVhf(r1_d, vy0_d)));
         HVX_Vector r1_c1_dd = Q6_Vsf_equals_Vqf32(Q6_V_lo_W(Q6_Wqf32_vmpy_VhfVhf(r1_d, vy1_d)));
 
-        // Zero out unused scales
+        // Zero out unused elements
         HVX_VectorPred bmask = Q6_Q_vsetq_R(nloe / 8);
         r0_c0_dd = Q6_V_vand_QV(bmask, r0_c0_dd);
         r0_c1_dd = Q6_V_vand_QV(bmask, r0_c1_dd);
@@ -844,7 +943,7 @@ static void vec_dot_mxfp4x4x2_q8x4x2_1x1(const int n, float * restrict s0, const
     const uint8_t * restrict y_d = ((const uint8_t *) vy0 + y_qrow_size);    // then scales
 
     // Row sum (sf)
-    HVX_Vector r0_sum = Q6_V_vsplat_R(0);
+    HVX_Vector r0_sum = Q6_V_vzero();
 
     // Multiply and accumulate into int32.
     // Compute combined scale (fp32).
@@ -855,8 +954,8 @@ static void vec_dot_mxfp4x4x2_q8x4x2_1x1(const int n, float * restrict s0, const
 
     uint32_t i = 0;
     for (; i < nb; i++) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_mxfp4x4x8(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_full(   y_q    + i * y_qblk_size);
+        HVX_Vector_x8 r0_q = hvx_vec_load_mxfp4x4x8_full(r0_x_q + i * x_qblk_size);
 
         HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r0_q, vy_q));
 
@@ -887,12 +986,12 @@ static void vec_dot_mxfp4x4x2_q8x4x2_1x1(const int n, float * restrict s0, const
 
     // Process leftovers
     if (nloe) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_mxfp4x4x8(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_partial(   y_q    + i * y_qblk_size, nloe);
+        HVX_Vector_x8 r0_q = hvx_vec_load_mxfp4x4x8_partial(r0_x_q + i * x_qblk_size, nloe);
 
-        HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r0_q, vy_q));
+        HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r0_q, vy_q, nloe));
 
-        HVX_Vector vy_d = *(const HVX_UVector *) (y_d + i * y_dblk_size);
+        HVX_Vector vy_d = *(const HVX_UVector *) (y_d    + i * y_dblk_size);
         HVX_Vector r0_d = *(const HVX_UVector *) (r0_x_d + i * x_dblk_size);
 
         // Convert vy_d from fp16 to fp32 while applying 0.5 scaling which is used for e8m0 halving
@@ -954,8 +1053,8 @@ static void vec_dot_mxfp4x4x2_q8x4x2_2x1(const int n, float * restrict s0,
     const uint8_t * restrict y_d = ((const uint8_t *) vy0) + y_qrow_size;     // then scales
 
     // Row sum (sf)
-    HVX_Vector r0_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r1_sum = Q6_V_vsplat_R(0);
+    HVX_Vector r0_sum = Q6_V_vzero();
+    HVX_Vector r1_sum = Q6_V_vzero();
 
     // Multiply and accumulate into int32.
     // Compute combined scale (fp32).
@@ -966,9 +1065,9 @@ static void vec_dot_mxfp4x4x2_q8x4x2_2x1(const int n, float * restrict s0,
 
     uint32_t i = 0;
     for (; i < nb; i++) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_mxfp4x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q = hvx_vec_load_mxfp4x4x8(r1_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_full(   y_q    + i * y_qblk_size);
+        HVX_Vector_x8 r0_q = hvx_vec_load_mxfp4x4x8_full(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 r1_q = hvx_vec_load_mxfp4x4x8_full(r1_x_q + i * x_qblk_size);
 
         HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r0_q, vy_q));
         HVX_Vector r1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r1_q, vy_q));
@@ -1007,14 +1106,14 @@ static void vec_dot_mxfp4x4x2_q8x4x2_2x1(const int n, float * restrict s0,
 
     // Process leftovers
     if (nloe) {
-        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8(y_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q = hvx_vec_load_mxfp4x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q = hvx_vec_load_mxfp4x4x8(r1_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy_q = hvx_vec_load_q8x4x8_partial(   y_q    + i * y_qblk_size, nloe);
+        HVX_Vector_x8 r0_q = hvx_vec_load_mxfp4x4x8_partial(r0_x_q + i * x_qblk_size, nloe);
+        HVX_Vector_x8 r1_q = hvx_vec_load_mxfp4x4x8_partial(r1_x_q + i * x_qblk_size, nloe);
 
         HVX_Vector r0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r0_q, vy_q));
         HVX_Vector r1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r1_q, vy_q));
 
-        HVX_Vector vy_d = *(const HVX_UVector *) (y_d + i * y_dblk_size);
+        HVX_Vector vy_d = *(const HVX_UVector *) (y_d    + i * y_dblk_size);
         HVX_Vector r0_d = *(const HVX_UVector *) (r0_x_d + i * x_dblk_size);
         HVX_Vector r1_d = *(const HVX_UVector *) (r1_x_d + i * x_dblk_size);
 
@@ -1087,10 +1186,10 @@ static void vec_dot_mxfp4x4x2_q8x4x2_2x2(const int n, float * restrict s0, float
     const uint8_t * restrict y1_d = ((const uint8_t *) vy1) + y_qrow_size;    // then scales
 
     // Row sums (sf) - 4 accumulators for 2×2 tile
-    HVX_Vector r0_c0_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r0_c1_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r1_c0_sum = Q6_V_vsplat_R(0);
-    HVX_Vector r1_c1_sum = Q6_V_vsplat_R(0);
+    HVX_Vector r0_c0_sum = Q6_V_vzero();
+    HVX_Vector r0_c1_sum = Q6_V_vzero();
+    HVX_Vector r1_c0_sum = Q6_V_vzero();
+    HVX_Vector r1_c1_sum = Q6_V_vzero();
 
     const uint32_t nb   = n / qk;  // num full blocks
     const uint32_t nloe = n % qk;  // num leftover elements
@@ -1098,12 +1197,12 @@ static void vec_dot_mxfp4x4x2_q8x4x2_2x2(const int n, float * restrict s0, float
     uint32_t i = 0;
     for (; i < nb; i++) {
         // Load src1 columns (reused across both src0 rows)
-        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8(y0_q + i * y_qblk_size);
-        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8(y1_q + i * y_qblk_size);
+        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8_full(y0_q + i * y_qblk_size);
+        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8_full(y1_q + i * y_qblk_size);
 
         // Load src0 rows (reused across both src1 columns)
-        HVX_Vector_x8 r0_q = hvx_vec_load_mxfp4x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q = hvx_vec_load_mxfp4x4x8(r1_x_q + i * x_qblk_size);
+        HVX_Vector_x8 r0_q = hvx_vec_load_mxfp4x4x8_full(r0_x_q + i * x_qblk_size);
+        HVX_Vector_x8 r1_q = hvx_vec_load_mxfp4x4x8_full(r1_x_q + i * x_qblk_size);
 
         // Compute 4 dot products: r0×c0, r0×c1, r1×c0, r1×c1
         HVX_Vector r0_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_full(r0_q, vy0_q));
@@ -1157,15 +1256,15 @@ static void vec_dot_mxfp4x4x2_q8x4x2_2x2(const int n, float * restrict s0, float
 
     // Process leftovers
     if (nloe) {
-        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8(y0_q + i * y_qblk_size);
-        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8(y1_q + i * y_qblk_size);
-        HVX_Vector_x8 r0_q  = hvx_vec_load_mxfp4x4x8(r0_x_q + i * x_qblk_size);
-        HVX_Vector_x8 r1_q  = hvx_vec_load_mxfp4x4x8(r1_x_q + i * x_qblk_size);
+        HVX_Vector_x8 vy0_q = hvx_vec_load_q8x4x8_partial(   y0_q   + i * y_qblk_size, nloe);
+        HVX_Vector_x8 vy1_q = hvx_vec_load_q8x4x8_partial(   y1_q   + i * y_qblk_size, nloe);
+        HVX_Vector_x8 r0_q  = hvx_vec_load_mxfp4x4x8_partial(r0_x_q + i * x_qblk_size, nloe);
+        HVX_Vector_x8 r1_q  = hvx_vec_load_mxfp4x4x8_partial(r1_x_q + i * x_qblk_size, nloe);
 
-        HVX_Vector r0_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r0_q, vy0_q, nloe));
-        HVX_Vector r0_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r0_q, vy1_q, nloe));
-        HVX_Vector r1_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r1_q, vy0_q, nloe));
-        HVX_Vector r1_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_nloe(r1_q, vy1_q, nloe));
+        HVX_Vector r0_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r0_q, vy0_q, nloe));
+        HVX_Vector r0_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r0_q, vy1_q, nloe));
+        HVX_Vector r1_c0_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r1_q, vy0_q, nloe));
+        HVX_Vector r1_c1_ia = Q6_Vsf_equals_Vw(hvx_vec_rmpy_x8_partial(r1_q, vy1_q, nloe));
 
         HVX_Vector vy0_d = *(const HVX_UVector *) (y0_d   + i * y_dblk_size);
         HVX_Vector vy1_d = *(const HVX_UVector *) (y1_d   + i * y_dblk_size);
@@ -1234,7 +1333,7 @@ static void vec_dot_f16_f16_aa_1x1(const int n, float * restrict s, const void *
     uint32_t nvec = n / VLEN_FP16; // num full fp16 hvx vectors
     uint32_t nloe = n % VLEN_FP16; // leftover elements
 
-    HVX_VectorPair rsum_p = Q6_W_vcombine_VV(Q6_V_vsplat_R(0), Q6_V_vsplat_R(0));
+    HVX_VectorPair rsum_p = Q6_W_vzero();
 
     uint32_t i = 0;
 
@@ -1264,8 +1363,8 @@ static void vec_dot_f16_f16_aa_2x1(const int n, float * restrict s0,
     uint32_t nvec = n / VLEN_FP16;
     uint32_t nloe = n % VLEN_FP16;
 
-    HVX_VectorPair rsum0_p = Q6_W_vcombine_VV(Q6_V_vsplat_R(0), Q6_V_vsplat_R(0));
-    HVX_VectorPair rsum1_p = Q6_W_vcombine_VV(Q6_V_vsplat_R(0), Q6_V_vsplat_R(0));
+    HVX_VectorPair rsum0_p = Q6_W_vzero();
+    HVX_VectorPair rsum1_p = Q6_W_vzero();
 
     uint32_t i = 0;
 
@@ -1303,10 +1402,10 @@ static void vec_dot_f16_f16_aa_2x2(const int n, float * restrict s0, float * res
     uint32_t nloe = n % VLEN_FP16;
 
     // Row sums (sf) - 4 accumulators for 2×2 tile
-    HVX_VectorPair r0_c0_sum_p = Q6_W_vcombine_VV(Q6_V_vsplat_R(0), Q6_V_vsplat_R(0));
-    HVX_VectorPair r0_c1_sum_p = Q6_W_vcombine_VV(Q6_V_vsplat_R(0), Q6_V_vsplat_R(0));
-    HVX_VectorPair r1_c0_sum_p = Q6_W_vcombine_VV(Q6_V_vsplat_R(0), Q6_V_vsplat_R(0));
-    HVX_VectorPair r1_c1_sum_p = Q6_W_vcombine_VV(Q6_V_vsplat_R(0), Q6_V_vsplat_R(0));
+    HVX_VectorPair r0_c0_sum_p = Q6_W_vzero();
+    HVX_VectorPair r0_c1_sum_p = Q6_W_vzero();
+    HVX_VectorPair r1_c0_sum_p = Q6_W_vzero();
+    HVX_VectorPair r1_c1_sum_p = Q6_W_vzero();
 
     uint32_t i = 0;
 
@@ -1358,7 +1457,7 @@ static void vec_dot_f16_f16_uu_1x1(const int n, float * restrict s, const void *
     uint32_t nvec = n / VLEN_FP16; // num full fp16 hvx vectors
     uint32_t nloe = n % VLEN_FP16; // leftover elements
 
-    HVX_Vector rsum = Q6_V_vsplat_R(0);
+    HVX_Vector rsum = Q6_V_vzero();
 
     uint32_t i = 0;
 
@@ -1388,9 +1487,9 @@ static void vec_dot_f16_f32_uu_1x1(const int n, float * restrict s, const void *
     uint32_t nvec = n / VLEN_FP16; // num full fp16 hvx vectors
     uint32_t nloe = n % VLEN_FP16; // leftover elements
 
-    const HVX_Vector zero = Q6_V_vsplat_R(0);
+    const HVX_Vector zero = Q6_V_vzero();
 
-    HVX_Vector       rsum = Q6_V_vsplat_R(0);
+    HVX_Vector       rsum = Q6_V_vzero();
 
     uint32_t i = 0;
 
@@ -1973,7 +2072,7 @@ static inline void quantize_block_f32_q8x1(float * restrict x, uint8_t * restric
     assert((unsigned long) y_q % 128 == 0);
 
     HVX_Vector * vx = (HVX_Vector *) x;
-    HVX_Vector zero   = Q6_V_vsplat_R(0);
+    HVX_Vector zero   = Q6_V_vzero();
 
     // Use reduce max fp32 to find max(abs(e)) first
     HVX_Vector vmax0_sf = hvx_vec_reduce_max_f32(hvx_vec_abs_f32(vx[0]));
@@ -2034,7 +2133,7 @@ static inline void quantize_block_f32_q8x2(float * restrict x, uint8_t * restric
     HVX_Vector * vx = (HVX_Vector *) x;
 
     // Load and convert into QF32
-    HVX_Vector zero   = Q6_V_vsplat_R(0);
+    HVX_Vector zero   = Q6_V_vzero();
     HVX_Vector vx0_qf = Q6_Vqf32_vsub_VsfVsf(vx[0], zero);  // 32 elements
     HVX_Vector vx1_qf = Q6_Vqf32_vsub_VsfVsf(vx[1], zero);  // 32 elements
     HVX_Vector vx2_qf = Q6_Vqf32_vsub_VsfVsf(vx[2], zero);  // 32 elements
@@ -2077,7 +2176,7 @@ static inline void quantize_block_f32_q8x4(float * restrict x, uint8_t * restric
     HVX_Vector * vx = (HVX_Vector *) x;
 
     // Load and convert into QF32
-    HVX_Vector zero   = Q6_V_vsplat_R(0);
+    HVX_Vector zero   = Q6_V_vzero();
     HVX_Vector vx0_qf = Q6_Vqf32_vsub_VsfVsf(vx[0], zero);  // 32 elements
     HVX_Vector vx1_qf = Q6_Vqf32_vsub_VsfVsf(vx[1], zero);  // 32 elements
     HVX_Vector vx2_qf = Q6_Vqf32_vsub_VsfVsf(vx[2], zero);  // 32 elements