[mlir][AMDGPU] Add better load/store lowering for full mask

mlir/lib/Dialect/AMDGPU/Transforms/MaskedloadToLoad.cpp

@@ -61,6 +61,36 @@ static Value createVectorLoadForMaskedLoad(OpBuilder &builder, Location loc,
   return res;
 }
 
+/// Check if the given value comes from a:
+///
+/// arith.select %cond, TRUE/FALSE, TRUE/FALSE
+///
+/// i.e the condition is either always true or it's always false.
+///
+/// Returns the condition to use for scf.if (condition) { true } else { false }.
+static FailureOr<Value> matchFullSelect(OpBuilder &b, Value val) {
+  auto selectOp = val.getDefiningOp<arith::SelectOp>();
+  if (!selectOp)
+    return failure();
+  std::optional<int64_t> trueInt = getConstantIntValue(selectOp.getTrueValue());
+  std::optional<int64_t> falseInt =
+      getConstantIntValue(selectOp.getFalseValue());
+  if (!trueInt || !falseInt)
+    return failure();
+  // getConstantIntValue returns -1 for "true" for bools.
+  if (trueInt.value() == -1 && falseInt.value() == 0)
+    return selectOp.getCondition();
+
+  if (trueInt.value() == 0 && falseInt.value() == -1) {
+    Value cond = selectOp.getCondition();
+    Value one = b.create<arith::ConstantIntOp>(cond.getLoc(), /*value=*/true,
+                                               /*width=*/1);
+    Value inverse = b.create<arith::XOrIOp>(cond.getLoc(), cond, one);
+    return inverse;
+  }
+  return failure();
+}
+
 static constexpr char kMaskedloadNeedsMask[] =
     "amdgpu.buffer_maskedload_needs_mask";
 
@@ -78,6 +108,16 @@ struct MaskedLoadLowering final : OpRewritePattern<vector::MaskedLoadOp> {
       return failure();
     }
 
+    // Check if this is either a full inbounds load or an empty, oob load. If
+    // so, take the fast path and don't generate a if condition, because we know
+    // doing the oob load is always safe.
+    if (succeeded(matchFullSelect(rewriter, maskedOp.getMask()))) {
+      Value load =
+          createVectorLoadForMaskedLoad(rewriter, maskedOp.getLoc(), maskedOp);
+      rewriter.replaceOp(maskedOp, load);
+      return success();
+    }
+
     Location loc = maskedOp.getLoc();
     Value src = maskedOp.getBase();
 
@@ -148,11 +188,64 @@ struct MaskedLoadLowering final : OpRewritePattern<vector::MaskedLoadOp> {
   }
 };
 
+struct FullMaskedLoadToConditionalLoad
+    : OpRewritePattern<vector::MaskedLoadOp> {
+  using OpRewritePattern::OpRewritePattern;
+
+public:
+  LogicalResult matchAndRewrite(vector::MaskedLoadOp loadOp,
+                                PatternRewriter &rewriter) const override {
+    FailureOr<Value> maybeCond = matchFullSelect(rewriter, loadOp.getMask());
+    if (failed(maybeCond)) {
+      return failure();
+    }
+
+    Value cond = maybeCond.value();
+    auto trueBuilder = [&](OpBuilder &builder, Location loc) {
+      Value res = createVectorLoadForMaskedLoad(builder, loc, loadOp);
+      rewriter.create<scf::YieldOp>(loc, res);
+    };
+    auto falseBuilder = [&](OpBuilder &builder, Location loc) {
+      rewriter.create<scf::YieldOp>(loc, loadOp.getPassThru());
+    };
+    auto ifOp = rewriter.create<scf::IfOp>(loadOp.getLoc(), cond, trueBuilder,
+                                           falseBuilder);
+    rewriter.replaceOp(loadOp, ifOp);
+    return success();
+  }
+};
+
+struct FullMaskedStoreToConditionalStore
+    : OpRewritePattern<vector::MaskedStoreOp> {
+  using OpRewritePattern::OpRewritePattern;
+
+public:
+  LogicalResult matchAndRewrite(vector::MaskedStoreOp storeOp,
+                                PatternRewriter &rewriter) const override {
+    FailureOr<Value> maybeCond = matchFullSelect(rewriter, storeOp.getMask());
+    if (failed(maybeCond)) {
+      return failure();
+    }
+    Value cond = maybeCond.value();
+
+    auto trueBuilder = [&](OpBuilder &builder, Location loc) {
+      rewriter.create<vector::StoreOp>(loc, storeOp.getValueToStore(),
+                                       storeOp.getBase(), storeOp.getIndices());
+      rewriter.create<scf::YieldOp>(loc);
+    };
+    auto ifOp = rewriter.create<scf::IfOp>(storeOp.getLoc(), cond, trueBuilder);
+    rewriter.replaceOp(storeOp, ifOp);
+    return success();
+  }
+};
+
 } // namespace
 
 void mlir::amdgpu::populateAmdgpuMaskedloadToLoadPatterns(
     RewritePatternSet &patterns, PatternBenefit benefit) {
-  patterns.add<MaskedLoadLowering>(patterns.getContext(), benefit);
+  patterns.add<MaskedLoadLowering, FullMaskedLoadToConditionalLoad,
+               FullMaskedStoreToConditionalStore>(patterns.getContext(),
+                                                  benefit);
 }
 
 struct AmdgpuMaskedloadToLoadPass final

mlir/test/Dialect/AMDGPU/maskedload-to-load.mlir

@@ -114,3 +114,28 @@ func.func @transfer_scalar(%mem : memref<8x8xf32, #amdgpu.address_space<fat_raw_
 // CHECK: %[[IF:.*]] = scf.if
 // CHECK: %[[LOAD:.*]] = vector.load %[[ARG0]][%[[ARG1]], %[[ARG1]]]
 // CHECK: %[[SELECT:.*]] = arith.select %arg2, %[[LOAD]], %[[ARG3]]
+
+// -----
+
+func.func @transfer_to_maskedload_fatrawbuffer(%mem : memref<8x8xf32, #amdgpu.address_space<fat_raw_buffer>>, %idx : index, %mask : vector<4xi1>, %passthru : vector<4xf32>) -> vector<4xf32> {
+  %res = vector.maskedload %mem[%idx, %idx], %mask, %passthru : memref<8x8xf32, #amdgpu.address_space<fat_raw_buffer>>, vector<4xi1>, vector<4xf32> into vector<4xf32>
+  return %res : vector<4xf32>
+}
+
+// -----
+
+func.func @full_select_maskedload_fatrawbuffer_to_load(%mem : memref<8x8xf16, #amdgpu.address_space<fat_raw_buffer>>, %idx : index, %cond : i1, %passthru : vector<4xf16>) -> vector<4xf16> {
+  %true = arith.constant dense<true> : vector<4xi1>
+  %false = arith.constant dense<false> : vector<4xi1>
+  %mask = arith.select %cond, %true, %false : vector<4xi1>
+  %res = vector.maskedload %mem[%idx, %idx], %mask, %passthru : memref<8x8xf16, #amdgpu.address_space<fat_raw_buffer>>, vector<4xi1>, vector<4xf16> into vector<4xf16>
+  return %res : vector<4xf16>
+}
+
+func.func @full_select_maskedload_to_load(%mem : memref<8x8xf16>, %idx : index, %cond : i1, %passthru : vector<4xf16>) -> vector<4xf16> {
+  %true = arith.constant dense<true> : vector<4xi1>
+  %false = arith.constant dense<false> : vector<4xi1>
+  %mask = arith.select %cond, %true, %false : vector<4xi1>
+  %res = vector.maskedload %mem[%idx, %idx], %mask, %passthru : memref<8x8xf16>, vector<4xi1>, vector<4xf16> into vector<4xf16>
+  return %res : vector<4xf16>
+}