dnn:rvv: restore the fixed block size C0 == 8

#29304 made the net-wide block size follow the RVV vector width
(defaultC0 = max(8, vlanes())), so the blocked memory layout of every tensor
depended on the host's VLEN and on the LMUL of the universal intrinsics in core.
The same model gets a different layout on a 128-, 256- or 1024-bit machine.

Restore the fixed default of 8, which is the mainstream, well-tested setting on
every platform. C0/K0 become compile-time constants again on RVV as they already
were elsewhere, so the runtime block-size plumbing and the vlanes()-based scratch
sizing are dropped, and getConvFunc_ no longer advertises block sizes the kernels
cannot handle.

The blocked kernels currently require C0 == vlanes(), which this alone does not
satisfy; the next commit removes that requirement.

modules/dnn/src/layers/cpu_kernels/conv2_depthwise.simd.hpp

@@ -38,14 +38,7 @@ static void depthwiseConv32f(const void* inp__, const void* residual__,
     parallel_for_(Range(0, NC1), [&](const Range& range)
     {
         constexpr int MAX_CONV_DIMS = ConvState::MAX_CONV_DIMS;
-#if CV_SIMD_SCALABLE
-        // RVV: universal intrinsics use LMUL=2, so the float vector width tracks
-        // the hardware VLEN at runtime. The block size C0 == defaultC0 == vlanes()
-        // (e.g. 16 at VLEN=256), so read it at runtime instead of fixing it to 8 (#28852).
-        const int C0 = (int)cs.inpshape.back();
-#else
         constexpr int C0 = 8;
-#endif
 
         CV_Assert(cs.nspatialdims <= MAX_CONV_DIMS && MAX_CONV_DIMS == 3);
         CV_Assert(C0 == cs.inpshape.back());
@@ -80,14 +73,7 @@ static void depthwiseConv32f(const void* inp__, const void* residual__,
         const float* activParams = cs.activParams.data();
         ActivationFunc activation = cs.activation;
         float maxval = FLT_MAX, defaultAlpha = 0.f;
-#if CV_SIMD_SCALABLE
-        // C0 is runtime on RVV; size scratch by the compile-time upper bound.
-        float scalebuf[VTraits<v_float32>::max_nlanes];
-        float biasbuf[VTraits<v_float32>::max_nlanes];
-        float alphabuf[VTraits<v_float32>::max_nlanes];
-#else
         float scalebuf[C0], biasbuf[C0], alphabuf[C0];
-#endif
         if (fastActivation == FAST_ACTIV_CLIP) {
             CV_Assert(cs.activParams.size() == 2u);
             maxval = activParams[1];

modules/dnn/src/layers/cpu_kernels/conv2_kernels.simd.hpp

@@ -2202,17 +2202,11 @@ static void conv32fC8(const void* inp__, const void* residual__, void* out__,
 
     parallel_for_(Range(0, total_tasks_gen), [&](const Range& range) {
         constexpr int SPAT_BLOCK_SIZE = 10;
-#if CV_SIMD_SCALABLE
-        // RVV: block size follows the runtime vector width (defaultC0 = vlanes(), LMUL=2).
-        const int C0 = (int)inpshape.back();
-        int C0shift = 0; while ((1 << C0shift) < C0) C0shift++;
-        const int K0 = C0, K0shift = C0shift;
-        constexpr int C0BUF = VTraits<v_float32>::max_nlanes;  // compile-time scratch bound
-#else
+        // The block size is a fixed property of the blocked layout on every platform,
+        // so C0/K0 are compile-time constants here (#29454).
         constexpr int C0shift = 3, K0shift = C0shift;
         constexpr int C0 = 1 << C0shift, K0 = C0;
         constexpr int C0BUF = K0;
-#endif
 
         CV_Assert_N(inpshape.back() == C0, outshape.back() == K0);
 
@@ -2557,16 +2551,9 @@ static void conv32fC8(const void* inp__, const void* residual__, void* out__,
 cv::dnn::ConvFunc getConvFunc_(int depth, int C0)
 {
     ConvFunc func = nullptr;
-#if CV_SIMD_SCALABLE
-    // RVV: block size follows the runtime vector width; accept the supported pow2 widths.
-    if (depth == CV_32F && (C0 == 8 || C0 == 16 || C0 == 32 || C0 == 64)) {
-        func = conv32fC8;
-    }
-#else
     if (depth == CV_32F && C0 == 8) {
         func = conv32fC8;
     }
-#endif
     return func;
 }
 

modules/dnn/src/net_impl.cpp

@@ -5,7 +5,6 @@
 #include "precomp.hpp"
 
 #include "net_impl.hpp"
-#include "opencv2/core/hal/intrin.hpp"
 
 #ifdef HAVE_ONNXRUNTIME
 #include <onnxruntime_cxx_api.h>
@@ -74,14 +73,10 @@ Net::Impl::Impl()
     // onnx_opset = 0;
 
     accuracy = CV_32F;
+    // The block size is a network-wide memory-layout contract, so it must not depend
+    // on the SIMD width of the host: C0 == 8 is the mainstream, well-tested setting.
+    // (Deriving it from vlanes() made the layout hardware-dependent; see #29454.)
     defaultC0 = DEFAULT_C0;
-#if CV_SIMD_SCALABLE
-    // RVV: the universal intrinsics use LMUL=2, so the float vector width is
-    // (VLEN/32)*2 (16 at VLEN=256). The blocked-layout kernels fill a full
-    // vector per channel block, so the net-wide block size must match that
-    // width rather than the fixed default of 8 (#28852).
-    defaultC0 = std::max((int)DEFAULT_C0, VTraits<v_float32>::vlanes());
-#endif
     enableFP16 = haveFP16 = false;
     // FP16 is not ready yet in the new DNN engine
     // Ticket: https://github.com/opencv/opencv/issues/26196

modules/dnn/src/net_impl2.cpp

@@ -5,7 +5,6 @@
 #include "precomp.hpp"
 
 #include "net_impl.hpp"
-#include "opencv2/core/hal/intrin.hpp"
 
 #include <limits>
 
@@ -546,16 +545,6 @@ void Net::Impl::prepareForInference()
 #endif
 
     if (!prepared) {
-#if CV_SIMD_SCALABLE
-        // RVV (#28852): keep quantized graphs at C0=8. The int8 kernels are hardwired to
-        // C0=8 (VNNI/NEON weight packing + per-channel quantization) and run scalar on RVV,
-        // so a wider block gives no benefit and breaks them. Only fp32 graphs use the wider
-        // vlanes()-based defaultC0. Signed-int8 (CV_8S) args are the quantization signature
-        // (uint8 image inputs are CV_8U, so they don't trigger this).
-        for (const ArgData& a : args) {
-            if (a.type == CV_8S) { defaultC0 = 8; break; }
-        }
-#endif
         fuseQDQ();
         constFold();
         fuseBN();