[x265] [PATCH] analysis: avoid redundant rect/amp mode analysis based on split block rdCost and mvCost for rd-5/6

ashok at multicorewareinc.com ashok at multicorewareinc.com
Thu Oct 15 17:01:31 CEST 2015


# HG changeset patch
# User Ashok Kumar Mishra<ashok at multicorewareinc.com>
# Date 1444824873 -19800
#      Wed Oct 14 17:44:33 2015 +0530
# Node ID f3963e7e75b8dcb599250c082357e08fd32191a5
# Parent  b6156a08b1def3584647f26096866c1a0c11e54a
analysis: avoid redundant rect/amp mode analysis based on split block rdCost and mvCost for rd-5/6
The analysis order for rect modes(first Nx2N, then 2NxN) is changed based on the rd cost of split blocks
to get better PSNR and SSIM.

diff -r b6156a08b1de -r f3963e7e75b8 source/common/param.cpp
--- a/source/common/param.cpp	Fri Oct 09 20:45:59 2015 +0530
+++ b/source/common/param.cpp	Wed Oct 14 17:44:33 2015 +0530
@@ -160,6 +160,7 @@
     param->searchRange = 57;
     param->maxNumMergeCand = 2;
     param->limitReferences = 0;
+    param->limitRectAmp = 0;    
     param->bEnableWeightedPred = 1;
     param->bEnableWeightedBiPred = 0;
     param->bEnableEarlySkip = 0;
@@ -648,6 +649,7 @@
     }
     OPT("ref") p->maxNumReferences = atoi(value);
     OPT("limit-refs") p->limitReferences = atoi(value);
+    OPT("limit-rect-amp") p->limitRectAmp = atoi(value);
     OPT("weightp") p->bEnableWeightedPred = atobool(value);
     OPT("weightb") p->bEnableWeightedBiPred = atobool(value);
     OPT("cbqpoffs") p->cbQpOffset = atoi(value);
@@ -1041,6 +1043,8 @@
           "subme must be greater than or equal to 0");
     CHECK(param->limitReferences > 3,
           "limitReferences must be 0, 1, 2 or 3");
+    CHECK(param->limitRectAmp > 1,
+          "limitRectAmp must be 0, 1");
     CHECK(param->frameNumThreads < 0 || param->frameNumThreads > X265_MAX_FRAME_THREADS,
           "frameNumThreads (--frame-threads) must be [0 .. X265_MAX_FRAME_THREADS)");
     CHECK(param->cbQpOffset < -12, "Min. Chroma Cb QP Offset is -12");
@@ -1434,6 +1438,7 @@
     s += sprintf(s, " b-adapt=%d", p->bFrameAdaptive);
     s += sprintf(s, " ref=%d", p->maxNumReferences);
     s += sprintf(s, " limit-refs=%d", p->limitReferences);
+    s += sprintf(s, " limit-rect-amp=%d", p->limitRectAmp);
     BOOL(p->bEnableWeightedPred, "weightp");
     BOOL(p->bEnableWeightedBiPred, "weightb");
     s += sprintf(s, " aq-mode=%d", p->rc.aqMode);
diff -r b6156a08b1de -r f3963e7e75b8 source/encoder/analysis.cpp
--- a/source/encoder/analysis.cpp	Fri Oct 09 20:45:59 2015 +0530
+++ b/source/encoder/analysis.cpp	Wed Oct 14 17:44:33 2015 +0530
@@ -1172,7 +1172,7 @@
     return refMask;
 }
 
-uint32_t Analysis::compressInterCU_rd5_6(const CUData& parentCTU, const CUGeom& cuGeom, uint32_t &zOrder, int32_t qp)
+SplitData Analysis::compressInterCU_rd5_6(const CUData& parentCTU, const CUGeom& cuGeom, uint32_t &zOrder, int32_t qp)
 {
     uint32_t depth = cuGeom.depth;
     ModeDepth& md = m_modeDepth[depth];
@@ -1207,7 +1207,13 @@
 
     bool foundSkip = false;
     bool splitIntra = true;
-    uint32_t splitRefs[4] = { 0, 0, 0, 0 };
+
+    SplitData splitData[4];
+    splitData[0].initSplitCUData();
+    splitData[1].initSplitCUData();
+    splitData[2].initSplitCUData();
+    splitData[3].initSplitCUData();
+
     /* Step 1. Evaluate Merge/Skip candidates for likely early-outs */
     if (mightNotSplit)
     {
@@ -1244,7 +1250,7 @@
                 if (m_slice->m_pps->bUseDQP && nextDepth <= m_slice->m_pps->maxCuDQPDepth)
                     nextQP = setLambdaFromQP(parentCTU, calculateQpforCuSize(parentCTU, childGeom));
 
-                splitRefs[subPartIdx] = compressInterCU_rd5_6(parentCTU, childGeom, zOrder, nextQP);
+                splitData[subPartIdx] = compressInterCU_rd5_6(parentCTU, childGeom, zOrder, nextQP);
 
                 // Save best CU and pred data for this sub CU
                 splitIntra |= nd.bestMode->cu.isIntra(0);
@@ -1271,7 +1277,7 @@
     /* Split CUs
      *   0  1
      *   2  3 */
-    uint32_t allSplitRefs = splitRefs[0] | splitRefs[1] | splitRefs[2] | splitRefs[3];
+    uint32_t allSplitRefs = splitData[0].splitRefs | splitData[1].splitRefs | splitData[2].splitRefs | splitData[3].splitRefs;
     /* Step 3. Evaluate ME (2Nx2N, rect, amp) and intra modes at current depth */
     if (mightNotSplit)
     {
@@ -1290,7 +1296,7 @@
             {
                 CUData& cu = md.pred[PRED_2Nx2N].cu;
                 uint32_t refMask = cu.getBestRefIdx(0);
-                allSplitRefs = splitRefs[0] = splitRefs[1] = splitRefs[2] = splitRefs[3] = refMask;
+                allSplitRefs = splitData[0].splitRefs = splitData[1].splitRefs = splitData[2].splitRefs = splitData[3].splitRefs = refMask;
             }
 
             if (m_slice->m_sliceType == B_SLICE)
@@ -1306,22 +1312,80 @@
 
             if (m_param->bEnableRectInter)
             {
-                refMasks[0] = splitRefs[0] | splitRefs[2]; /* left */
-                refMasks[1] = splitRefs[1] | splitRefs[3]; /* right */
-                md.pred[PRED_Nx2N].cu.initSubCU(parentCTU, cuGeom, qp);
-                checkInter_rd5_6(md.pred[PRED_Nx2N], cuGeom, SIZE_Nx2N, refMasks);
-                checkBestMode(md.pred[PRED_Nx2N], cuGeom.depth);
+                uint64_t splitCost = splitData[0].rdCost + splitData[1].rdCost + splitData[2].rdCost + splitData[3].rdCost;
+                ModeDepth& md = m_modeDepth[depth];
+                uint32_t threshold_2NxN, threshold_Nx2N;
 
-                refMasks[0] = splitRefs[0] | splitRefs[1]; /* top */
-                refMasks[1] = splitRefs[2] | splitRefs[3]; /* bot */
-                md.pred[PRED_2NxN].cu.initSubCU(parentCTU, cuGeom, qp);
-                checkInter_rd5_6(md.pred[PRED_2NxN], cuGeom, SIZE_2NxN, refMasks);
-                checkBestMode(md.pred[PRED_2NxN], cuGeom.depth);
+                if (m_slice->m_sliceType == P_SLICE)
+                {
+                    threshold_2NxN = splitData[0].mvCost[0] + splitData[1].mvCost[0];
+                    threshold_Nx2N = splitData[0].mvCost[0] + splitData[2].mvCost[0];
+                }
+                else
+                {
+                    threshold_2NxN = (splitData[0].mvCost[0] + splitData[1].mvCost[0] 
+                                    + splitData[0].mvCost[1] + splitData[1].mvCost[1] + 1) >> 1;
+                    threshold_Nx2N = (splitData[0].mvCost[0] + splitData[2].mvCost[0] 
+                                    + splitData[0].mvCost[1] + splitData[2].mvCost[1] + 1) >> 1;
+                }
+
+                int try_2NxN_first = threshold_2NxN < threshold_Nx2N;
+                if (try_2NxN_first && splitCost < md.bestMode->rdCost + threshold_2NxN)
+                {
+                    refMasks[0] = splitData[0].splitRefs | splitData[1].splitRefs; /* top */
+                    refMasks[1] = splitData[2].splitRefs | splitData[3].splitRefs; /* bot */
+                    md.pred[PRED_2NxN].cu.initSubCU(parentCTU, cuGeom, qp);
+                    checkInter_rd5_6(md.pred[PRED_2NxN], cuGeom, SIZE_2NxN, refMasks);
+                    checkBestMode(md.pred[PRED_2NxN], cuGeom.depth);
+                }
+
+                if (splitCost < md.bestMode->rdCost + threshold_Nx2N)
+                {
+                    refMasks[0] = splitData[0].splitRefs | splitData[2].splitRefs; /* left */
+                    refMasks[1] = splitData[1].splitRefs | splitData[3].splitRefs; /* right */
+                    md.pred[PRED_Nx2N].cu.initSubCU(parentCTU, cuGeom, qp);
+                    checkInter_rd5_6(md.pred[PRED_Nx2N], cuGeom, SIZE_Nx2N, refMasks);
+                    checkBestMode(md.pred[PRED_Nx2N], cuGeom.depth);
+                }
+
+                if (!try_2NxN_first && splitCost < md.bestMode->rdCost + threshold_2NxN)
+                {
+                    refMasks[0] = splitData[0].splitRefs | splitData[1].splitRefs; /* top */
+                    refMasks[1] = splitData[2].splitRefs | splitData[3].splitRefs; /* bot */
+                    md.pred[PRED_2NxN].cu.initSubCU(parentCTU, cuGeom, qp);
+                    checkInter_rd5_6(md.pred[PRED_2NxN], cuGeom, SIZE_2NxN, refMasks);
+                    checkBestMode(md.pred[PRED_2NxN], cuGeom.depth);
+                }
             }
 
             // Try AMP (SIZE_2NxnU, SIZE_2NxnD, SIZE_nLx2N, SIZE_nRx2N)
             if (m_slice->m_sps->maxAMPDepth > depth)
             {
+                uint64_t splitCost = splitData[0].rdCost + splitData[1].rdCost + splitData[2].rdCost + splitData[3].rdCost;
+                ModeDepth& md = m_modeDepth[depth];
+                uint32_t threshold_2NxnU, threshold_2NxnD, threshold_nLx2N, threshold_nRx2N;
+
+                if (m_slice->m_sliceType == P_SLICE)
+                {
+                    threshold_2NxnU = splitData[0].mvCost[0] + splitData[1].mvCost[0];
+                    threshold_2NxnD = splitData[2].mvCost[0] + splitData[3].mvCost[0];
+
+                    threshold_nLx2N = splitData[0].mvCost[0] + splitData[2].mvCost[0];
+                    threshold_nRx2N = splitData[1].mvCost[0] + splitData[3].mvCost[0];
+                }
+                else
+                {
+                    threshold_2NxnU = (splitData[0].mvCost[0] + splitData[1].mvCost[0] 
+                                       + splitData[0].mvCost[1] + splitData[1].mvCost[1] + 1) >> 1;
+                    threshold_2NxnD = (splitData[2].mvCost[0] + splitData[3].mvCost[0] 
+                                       + splitData[2].mvCost[1] + splitData[3].mvCost[1] + 1) >> 1;
+
+                    threshold_nLx2N = (splitData[0].mvCost[0] + splitData[2].mvCost[0] 
+                                       + splitData[0].mvCost[1] + splitData[2].mvCost[1] + 1) >> 1;
+                    threshold_nRx2N = (splitData[1].mvCost[0] + splitData[3].mvCost[0] 
+                                       + splitData[1].mvCost[1] + splitData[3].mvCost[1] + 1) >> 1;
+                }
+
                 bool bHor = false, bVer = false;
                 if (md.bestMode->cu.m_partSize[0] == SIZE_2NxN)
                     bHor = true;
@@ -1335,31 +1399,64 @@
 
                 if (bHor)
                 {
-                    refMasks[0] = splitRefs[0] | splitRefs[1]; /* 25% top */
-                    refMasks[1] = allSplitRefs;                /* 75% bot */
-                    md.pred[PRED_2NxnU].cu.initSubCU(parentCTU, cuGeom, qp);
-                    checkInter_rd5_6(md.pred[PRED_2NxnU], cuGeom, SIZE_2NxnU, refMasks);
-                    checkBestMode(md.pred[PRED_2NxnU], cuGeom.depth);
+                    int try_2NxnD_first = threshold_2NxnD < threshold_2NxnU;
+                    if (try_2NxnD_first && splitCost < md.bestMode->rdCost + threshold_2NxnD)
+                    {
+                        refMasks[0] = allSplitRefs;                                    /* 75% top */
+                        refMasks[1] = splitData[2].splitRefs | splitData[3].splitRefs; /* 25% bot */
+                        md.pred[PRED_2NxnD].cu.initSubCU(parentCTU, cuGeom, qp);
+                        checkInter_rd5_6(md.pred[PRED_2NxnD], cuGeom, SIZE_2NxnD, refMasks);
+                        checkBestMode(md.pred[PRED_2NxnD], cuGeom.depth);
+                    }
 
-                    refMasks[0] = allSplitRefs;                /* 75% top */
-                    refMasks[1] = splitRefs[2] | splitRefs[3]; /* 25% bot */
-                    md.pred[PRED_2NxnD].cu.initSubCU(parentCTU, cuGeom, qp);
-                    checkInter_rd5_6(md.pred[PRED_2NxnD], cuGeom, SIZE_2NxnD, refMasks);
-                    checkBestMode(md.pred[PRED_2NxnD], cuGeom.depth);
+                    if (splitCost < md.bestMode->rdCost + threshold_2NxnU)
+                    {
+                        refMasks[0] = splitData[0].splitRefs | splitData[1].splitRefs; /* 25% top */
+                        refMasks[1] = allSplitRefs;                                    /* 75% bot */
+                        md.pred[PRED_2NxnU].cu.initSubCU(parentCTU, cuGeom, qp);
+                        checkInter_rd5_6(md.pred[PRED_2NxnU], cuGeom, SIZE_2NxnU, refMasks);
+                        checkBestMode(md.pred[PRED_2NxnU], cuGeom.depth);
+                    }
+
+                    if (!try_2NxnD_first && splitCost < md.bestMode->rdCost + threshold_2NxnD)
+                    {
+                        refMasks[0] = allSplitRefs;                                    /* 75% top */
+                        refMasks[1] = splitData[2].splitRefs | splitData[3].splitRefs; /* 25% bot */
+                        md.pred[PRED_2NxnD].cu.initSubCU(parentCTU, cuGeom, qp);
+                        checkInter_rd5_6(md.pred[PRED_2NxnD], cuGeom, SIZE_2NxnD, refMasks);
+                        checkBestMode(md.pred[PRED_2NxnD], cuGeom.depth);
+                    }
                 }
+
                 if (bVer)
                 {
-                    refMasks[0] = splitRefs[0] | splitRefs[2]; /* 25% left */
-                    refMasks[1] = allSplitRefs;                /* 75% right */
-                    md.pred[PRED_nLx2N].cu.initSubCU(parentCTU, cuGeom, qp);
-                    checkInter_rd5_6(md.pred[PRED_nLx2N], cuGeom, SIZE_nLx2N, refMasks);
-                    checkBestMode(md.pred[PRED_nLx2N], cuGeom.depth);
+                    int try_nRx2N_first = threshold_nRx2N < threshold_nLx2N;
+                    if (try_nRx2N_first && splitCost < md.bestMode->rdCost + threshold_nRx2N)
+                    {
+                        refMasks[0] = allSplitRefs;                                    /* 75% left  */
+                        refMasks[1] = splitData[1].splitRefs | splitData[3].splitRefs; /* 25% right */
+                        md.pred[PRED_nRx2N].cu.initSubCU(parentCTU, cuGeom, qp);
+                        checkInter_rd5_6(md.pred[PRED_nRx2N], cuGeom, SIZE_nRx2N, refMasks);
+                        checkBestMode(md.pred[PRED_nRx2N], cuGeom.depth);
+                    }
 
-                    refMasks[0] = allSplitRefs;                /* 75% left */
-                    refMasks[1] = splitRefs[1] | splitRefs[3]; /* 25% right */
-                    md.pred[PRED_nRx2N].cu.initSubCU(parentCTU, cuGeom, qp);
-                    checkInter_rd5_6(md.pred[PRED_nRx2N], cuGeom, SIZE_nRx2N, refMasks);
-                    checkBestMode(md.pred[PRED_nRx2N], cuGeom.depth);
+                    if (splitCost < md.bestMode->rdCost + threshold_nLx2N)
+                    {
+                        refMasks[0] = splitData[0].splitRefs | splitData[2].splitRefs; /* 25% left  */
+                        refMasks[1] = allSplitRefs;                                    /* 75% right */
+                        md.pred[PRED_nLx2N].cu.initSubCU(parentCTU, cuGeom, qp);
+                        checkInter_rd5_6(md.pred[PRED_nLx2N], cuGeom, SIZE_nLx2N, refMasks);
+                        checkBestMode(md.pred[PRED_nLx2N], cuGeom.depth);
+                    }
+
+                    if (!try_nRx2N_first && splitCost < md.bestMode->rdCost + threshold_nRx2N)
+                    {
+                        refMasks[0] = allSplitRefs;                                    /* 75% left  */
+                        refMasks[1] = splitData[1].splitRefs | splitData[3].splitRefs; /* 25% right */
+                        md.pred[PRED_nRx2N].cu.initSubCU(parentCTU, cuGeom, qp);
+                        checkInter_rd5_6(md.pred[PRED_nRx2N], cuGeom, SIZE_nRx2N, refMasks);
+                        checkBestMode(md.pred[PRED_nRx2N], cuGeom.depth);
+                    }
                 }
             }
 
@@ -1398,26 +1495,39 @@
         checkBestMode(md.pred[PRED_SPLIT], depth);
 
        /* determine which motion references the parent CU should search */
-    uint32_t refMask;
+    SplitData splitCUData;
     if (!(m_param->limitReferences & X265_REF_LIMIT_DEPTH))
-        refMask = 0;
+        splitCUData.splitRefs = 0;
     else if (md.bestMode == &md.pred[PRED_SPLIT])
-        refMask = allSplitRefs;
+        splitCUData.splitRefs = allSplitRefs;
     else
     {
         /* use best merge/inter mode, in case of intra use 2Nx2N inter references */
         CUData& cu = md.bestMode->cu.isIntra(0) ? md.pred[PRED_2Nx2N].cu : md.bestMode->cu;
         uint32_t numPU = cu.getNumPartInter(0);
-        refMask = 0;
+        splitCUData.splitRefs = 0;
         for (uint32_t puIdx = 0, subPartIdx = 0; puIdx < numPU; puIdx++, subPartIdx += cu.getPUOffset(puIdx, 0))
-            refMask |= cu.getBestRefIdx(subPartIdx);
+            splitCUData.splitRefs |= cu.getBestRefIdx(subPartIdx);
+    }
+
+    if (!m_param->limitRectAmp)
+    {
+        splitCUData.mvCost[0] = 0; // L0
+        splitCUData.mvCost[1] = 0; // L1
+        splitCUData.rdCost    = 0;
+    }
+    else
+    {
+        splitCUData.mvCost[0] = md.pred[PRED_2Nx2N].bestME[0][0].mvCost; // L0
+        splitCUData.mvCost[1] = md.pred[PRED_2Nx2N].bestME[0][1].mvCost; // L1
+        splitCUData.rdCost    = md.pred[PRED_2Nx2N].rdCost;
     }
 
     /* Copy best data to encData CTU and recon */
     md.bestMode->cu.copyToPic(depth);
     md.bestMode->reconYuv.copyToPicYuv(*m_frame->m_reconPic, parentCTU.m_cuAddr, cuGeom.absPartIdx);
 
-    return refMask;
+    return splitCUData;
 }
 
 /* sets md.bestMode if a valid merge candidate is found, else leaves it NULL */
diff -r b6156a08b1de -r f3963e7e75b8 source/encoder/analysis.h
--- a/source/encoder/analysis.h	Fri Oct 09 20:45:59 2015 +0530
+++ b/source/encoder/analysis.h	Wed Oct 14 17:44:33 2015 +0530
@@ -41,6 +41,21 @@
 
 class Entropy;
 
+struct SplitData
+{
+    uint32_t splitRefs;
+    uint32_t mvCost[2];
+    uint64_t rdCost;
+
+    void initSplitCUData()
+    {
+        splitRefs = 0;
+        mvCost[0] = 0; // L0
+        mvCost[1] = 0; // L1
+        rdCost    = 0;
+    }
+};
+
 class Analysis : public Search
 {
 public:
@@ -117,7 +132,7 @@
     /* full analysis for a P or B slice CU */
     uint32_t compressInterCU_dist(const CUData& parentCTU, const CUGeom& cuGeom, int32_t qp);
     uint32_t compressInterCU_rd0_4(const CUData& parentCTU, const CUGeom& cuGeom, int32_t qp);
-    uint32_t compressInterCU_rd5_6(const CUData& parentCTU, const CUGeom& cuGeom, uint32_t &zOrder, int32_t qp);
+    SplitData compressInterCU_rd5_6(const CUData& parentCTU, const CUGeom& cuGeom, uint32_t &zOrder, int32_t qp);
 
     /* measure merge and skip */
     void checkMerge2Nx2N_rd0_4(Mode& skip, Mode& merge, const CUGeom& cuGeom);
diff -r b6156a08b1de -r f3963e7e75b8 source/encoder/search.cpp
--- a/source/encoder/search.cpp	Fri Oct 09 20:45:59 2015 +0530
+++ b/source/encoder/search.cpp	Wed Oct 14 17:44:33 2015 +0530
@@ -2186,19 +2186,21 @@
 
                     /* Get total cost of partition, but only include MV bit cost once */
                     bits += m_me.bitcost(outmv);
-                    uint32_t cost = (satdCost - m_me.mvcost(outmv)) + m_rdCost.getCost(bits);
+                    uint32_t mvCost = m_me.mvcost(outmv);
+                    uint32_t cost = (satdCost - mvCost) + m_rdCost.getCost(bits);
 
                     /* Refine MVP selection, updates: mvpIdx, bits, cost */
                     mvp = checkBestMVP(amvp, outmv, mvpIdx, bits, cost);
 
                     if (cost < bestME[list].cost)
                     {
-                        bestME[list].mv = outmv;
-                        bestME[list].mvp = mvp;
-                        bestME[list].mvpIdx = mvpIdx;
-                        bestME[list].ref = ref;
-                        bestME[list].cost = cost;
-                        bestME[list].bits = bits;
+                        bestME[list].mv      = outmv;
+                        bestME[list].mvp     = mvp;
+                        bestME[list].mvpIdx  = mvpIdx;
+                        bestME[list].ref     = ref;
+                        bestME[list].cost    = cost;
+                        bestME[list].bits    = bits;
+                        bestME[list].mvCost  = mvCost;
                     }
                 }
                 /* the second list ref bits start at bit 16 */
diff -r b6156a08b1de -r f3963e7e75b8 source/encoder/search.h
--- a/source/encoder/search.h	Fri Oct 09 20:45:59 2015 +0530
+++ b/source/encoder/search.h	Wed Oct 14 17:44:33 2015 +0530
@@ -85,8 +85,9 @@
     MV       mvp;
     int      mvpIdx;
     int      ref;
+    int      bits;
+    uint32_t mvCost;
     uint32_t cost;
-    int      bits;
 };
 
 struct Mode
diff -r b6156a08b1de -r f3963e7e75b8 source/x265.h
--- a/source/x265.h	Fri Oct 09 20:45:59 2015 +0530
+++ b/source/x265.h	Wed Oct 14 17:44:33 2015 +0530
@@ -822,6 +822,10 @@
      * 4 split CUs at the next lower CU depth.  The two flags may be combined */
     uint32_t  limitReferences;
 
+    /* Limit rectangular and asymetric motion partitions based on rdCost and mvCost
+    of the 4 split CUs at the next lower CU depth*/
+    uint32_t limitRectAmp;
+
     /* ME search method (DIA, HEX, UMH, STAR, FULL). The search patterns
      * (methods) are sorted in increasing complexity, with diamond being the
      * simplest and fastest and full being the slowest.  DIA, HEX, and UMH were
diff -r b6156a08b1de -r f3963e7e75b8 source/x265cli.h
--- a/source/x265cli.h	Fri Oct 09 20:45:59 2015 +0530
+++ b/source/x265cli.h	Wed Oct 14 17:44:33 2015 +0530
@@ -126,6 +126,7 @@
     { "b-pyramid",            no_argument, NULL, 0 },
     { "ref",            required_argument, NULL, 0 },
     { "limit-refs",     required_argument, NULL, 0 },
+    { "limit-rect-amp", required_argument, NULL, 0 },
     { "no-weightp",           no_argument, NULL, 0 },
     { "weightp",              no_argument, NULL, 'w' },
     { "no-weightb",           no_argument, NULL, 0 },
@@ -310,12 +311,13 @@
     H0("\nTemporal / motion search options:\n");
     H0("   --max-merge <1..5>            Maximum number of merge candidates. Default %d\n", param->maxNumMergeCand);
     H0("   --ref <integer>               max number of L0 references to be allowed (1 .. 16) Default %d\n", param->maxNumReferences);
-    H0("   --limit-refs <0|1|2|3>        limit references per depth (1) or CU (2) or both (3). Default %d\n", param->limitReferences);
+    H0("   --limit-refs <0|1|2|3>        Limit references per depth (1) or CU (2) or both (3). Default %d\n", param->limitReferences);
     H0("   --me <string>                 Motion search method dia hex umh star full. Default %d\n", param->searchMethod);
     H0("-m/--subme <integer>             Amount of subpel refinement to perform (0:least .. 7:most). Default %d \n", param->subpelRefine);
     H0("   --merange <integer>           Motion search range. Default %d\n", param->searchRange);
     H0("   --[no-]rect                   Enable rectangular motion partitions Nx2N and 2NxN. Default %s\n", OPT(param->bEnableRectInter));
     H0("   --[no-]amp                    Enable asymmetric motion partitions, requires --rect. Default %s\n", OPT(param->bEnableAMP));
+    H0("   --limit-rect-amp <0|1>        Limit rectangular and asymetirc motion partitions. Default %d\n", param->limitRectAmp);
     H1("   --[no-]temporal-mvp           Enable temporal MV predictors. Default %s\n", OPT(param->bEnableTemporalMvp));
     H0("\nSpatial / intra options:\n");
     H0("   --[no-]strong-intra-smoothing Enable strong intra smoothing for 32x32 blocks. Default %s\n", OPT(param->bEnableStrongIntraSmoothing));


More information about the x265-devel mailing list