[PATCH] D57553: [Fixed Point Arithmetic] Avoid resizing for types with the same width

[Leonard Chan via Phabricator via cfe-commits]

leonardchan updated this revision to Diff 184888.
leonardchan retitled this revision from "[Fixed Point Arithmetic] Check against source value when converting during saturation" to "[Fixed Point Arithmetic] Avoid resizing for types with the same width".
leonardchan edited the summary of this revision.

Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57553/new/

https://reviews.llvm.org/D57553

Files:
  clang/lib/CodeGen/CGExprScalar.cpp
  clang/test/Frontend/fixed_point_conversions.c


Index: clang/test/Frontend/fixed_point_conversions.c
===================================================================
--- clang/test/Frontend/fixed_point_conversions.c
+++ clang/test/Frontend/fixed_point_conversions.c
@@ -186,14 +186,12 @@
   // Accum to Fract, increasing scale
   sat_lf = sat_a;
   // DEFAULT:      [[OLD_ACCUM:%[0-9a-z]+]] = load i32, i32* %sat_a, align 4
-  // DEFAULT-NEXT: [[ACCUM:%[0-9a-z]+]] = sext i32 [[OLD_ACCUM]] to i48
-  // DEFAULT-NEXT: [[FRACT:%[0-9a-z]+]] = shl i48 [[ACCUM]], 16
-  // DEFAULT-NEXT: [[USE_MAX:%[0-9a-z]+]] = icmp sgt i48 [[FRACT]], 2147483647
-  // DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = select i1 [[USE_MAX]], i48 2147483647, i48 [[FRACT]]
-  // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i48 [[RESULT]], -2147483648
-  // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MIN]], i48 -2147483648, i48 [[RESULT]]
-  // DEFAULT-NEXT: [[RESULT_TRUNC:%[0-9a-z]+]] = trunc i48 [[RESULT2]] to i32
-  // DEFAULT-NEXT: store i32 [[RESULT_TRUNC]], i32* %sat_lf, align 4
+  // DEFAULT-NEXT: [[FRACT:%[0-9a-z]+]] = shl i32 [[OLD_ACCUM]], 16
+  // DEFAULT-NEXT: [[USE_MAX:%[0-9a-z]+]] = icmp sgt i32 [[FRACT]], 2147483647
+  // DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = select i1 [[USE_MAX]], i32 2147483647, i32 [[FRACT]]
+  // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[RESULT]], -2147483648
+  // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MIN]], i32 -2147483648, i32 [[RESULT]]
+  // DEFAULT-NEXT: store i32 [[RESULT2]], i32* %sat_lf, align 4
 
   // Signed to unsigned, decreasing scale
   _Sat _Accum sat_a2;
@@ -218,12 +216,10 @@
   // Signed to unsigned, increasing scale
   sat_ua = sat_a;
   // DEFAULT:      [[OLD_ACCUM:%[0-9a-z]+]] = load i32, i32* %sat_a, align 4
-  // DEFAULT-NEXT: [[ACCUM_EXT:%[0-9a-z]+]] = sext i32 [[OLD_ACCUM]] to i33
-  // DEFAULT-NEXT: [[ACCUM:%[0-9a-z]+]] = shl i33 [[ACCUM_EXT]], 1
-  // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i33 [[ACCUM]], 0
-  // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MIN]], i33 0, i33 [[ACCUM]]
-  // DEFAULT-NEXT: [[RESULT_TRUNC:%[0-9a-z]+]] = trunc i33 [[RESULT2]] to i32
-  // DEFAULT-NEXT: store i32 [[RESULT_TRUNC]], i32* %sat_ua, align 4
+  // DEFAULT-NEXT: [[ACCUM:%[0-9a-z]+]] = shl i32 [[OLD_ACCUM]], 1
+  // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[ACCUM]], 0
+  // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MIN]], i32 0, i32 [[ACCUM]]
+  // DEFAULT-NEXT: store i32 [[RESULT2]], i32* %sat_ua, align 4
   // SAME:      [[ACCUM:%[0-9a-z]+]] = load i32, i32* %sat_a, align 4
   // SAME-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[ACCUM]], 0
   // SAME-NEXT: [[RESULT:%[0-9a-z]+]] = select i1 [[USE_MIN]], i32 0, i32 [[ACCUM]]
Index: clang/lib/CodeGen/CGExprScalar.cpp
===================================================================
--- clang/lib/CodeGen/CGExprScalar.cpp
+++ clang/lib/CodeGen/CGExprScalar.cpp
@@ -1481,9 +1481,14 @@
     // Adjust the number of fractional bits.
     if (DstScale > SrcScale) {
       // Compare to DstWidth to prevent resizing twice.
-      ResultWidth = std::max(SrcWidth + DstScale - SrcScale, DstWidth);
-      llvm::Type *UpscaledTy = Builder.getIntNTy(ResultWidth);
-      Result = Builder.CreateIntCast(Result, UpscaledTy, SrcIsSigned, "resize");
+      if (ResultWidth != DstWidth) {
+        // No rescaling is needed if both sides have the same resulting width.
+        // This would end up with a needless int cast.
+        ResultWidth = std::max(SrcWidth + DstScale - SrcScale, DstWidth);
+        llvm::Type *UpscaledTy = Builder.getIntNTy(ResultWidth);
+        Result =
+            Builder.CreateIntCast(Result, UpscaledTy, SrcIsSigned, "resize");
+      }
       Result = Builder.CreateShl(Result, DstScale - SrcScale, "upscale");
     } else if (DstScale < SrcScale) {
       Result = SrcIsSigned ?


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D57553.184888.patch
Type: text/x-patch
Size: 3849 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20190202/35ccd5ad/attachment-0001.bin>