leonardchan created this revision.
leonardchan added reviewers: rjmccall, ebevhan, bjope.
leonardchan added a project: clang.
When converting to a saturating fixed point type, compare against the source
value instead of our container value. This allows us to not create a container,
and save up to 2 instructions from extending/truncating to this container size.
These can be seen in conversions between fixed point types of the same width,
but different scale or different sign.
Repository:
rC Clang
https://reviews.llvm.org/D57553
Files:
clang/lib/CodeGen/CGExprScalar.cpp
clang/test/Frontend/fixed_point_add.c
clang/test/Frontend/fixed_point_conversions.c
clang/test/Frontend/fixed_point_sub.c
Index: clang/test/Frontend/fixed_point_sub.c
===================================================================
--- clang/test/Frontend/fixed_point_sub.c
+++ clang/test/Frontend/fixed_point_sub.c
@@ -332,11 +332,11 @@
// CHECK-NEXT: [[I_EXT:%[a-z0-9]+]] = sext i32 [[I]] to i39
// CHECK-NEXT: [[I:%[a-z0-9]+]] = shl i39 [[I_EXT]], 7
// CHECK-NEXT: [[SUM:%[0-9]+]] = call i39 @llvm.ssub.sat.i39(i39 [[SA_SAT_EXT]], i39 [[I]])
+ // CHECK-NEXT: [[RES:%[a-z0-9]+]] = trunc i39 [[SUM]] to i16
// CHECK-NEXT: [[USE_MAX:%[0-9]+]] = icmp sgt i39 [[SUM]], 32767
- // CHECK-NEXT: [[RES:%[a-z0-9]+]] = select i1 [[USE_MAX]], i39 32767, i39 [[SUM]]
- // CHECK-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i39 [[RES]], -32768
- // CHECK-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MIN]], i39 -32768, i39 [[RES]]
- // CHECK-NEXT: [[RES3:%[a-z0-9]+]] = trunc i39 [[RES2]] to i16
+ // CHECK-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MAX]], i16 32767, i16 [[RES]]
+ // CHECK-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i39 [[SUM]], -32768
+ // CHECK-NEXT: [[RES3:%[a-z0-9]+]] = select i1 [[USE_MIN]], i16 -32768, i16 [[RES2]]
// CHECK-NEXT: store i16 [[RES3]], i16* %sa_sat, align 2
sa_sat = sa_sat - i;
@@ -346,11 +346,11 @@
// CHECK-NEXT: [[I_EXT:%[a-z0-9]+]] = zext i32 [[I]] to i40
// CHECK-NEXT: [[I:%[a-z0-9]+]] = shl i40 [[I_EXT]], 7
// CHECK-NEXT: [[SUM:%[0-9]+]] = call i40 @llvm.ssub.sat.i40(i40 [[SA_SAT_EXT]], i40 [[I]])
+ // CHECK-NEXT: [[RES:%[a-z0-9]+]] = trunc i40 [[SUM]] to i16
// CHECK-NEXT: [[USE_MAX:%[0-9]+]] = icmp sgt i40 [[SUM]], 32767
- // CHECK-NEXT: [[RES:%[a-z0-9]+]] = select i1 [[USE_MAX]], i40 32767, i40 [[SUM]]
- // CHECK-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i40 [[RES]], -32768
- // CHECK-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MIN]], i40 -32768, i40 [[RES]]
- // CHECK-NEXT: [[RES3:%[a-z0-9]+]] = trunc i40 [[RES2]] to i16
+ // CHECK-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MAX]], i16 32767, i16 [[RES]]
+ // CHECK-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i40 [[SUM]], -32768
+ // CHECK-NEXT: [[RES3:%[a-z0-9]+]] = select i1 [[USE_MIN]], i16 -32768, i16 [[RES2]]
// CHECK-NEXT: store i16 [[RES3]], i16* %sa_sat, align 2
sa_sat = sa_sat - ui;
@@ -371,20 +371,20 @@
// SIGNED-NEXT: [[I_RESIZE:%[a-z0-9]+]] = sext i32 [[I]] to i40
// SIGNED-NEXT: [[I_UPSCALE:%[a-z0-9]+]] = shl i40 [[I_RESIZE]], 8
// SIGNED-NEXT: [[SUM:%[0-9]+]] = call i40 @llvm.usub.sat.i40(i40 [[USA_SAT_RESIZE]], i40 [[I_UPSCALE]])
+ // SIGNED-NEXT: [[RES:%[a-z0-9]+]] = trunc i40 [[SUM]] to i16
// SIGNED-NEXT: [[USE_MAX:%[0-9]+]] = icmp sgt i40 [[SUM]], 65535
- // SIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = select i1 [[USE_MAX]], i40 65535, i40 [[SUM]]
- // SIGNED-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i40 [[RESULT]], 0
- // SIGNED-NEXT: [[RESULT2:%[a-z0-9]+]] = select i1 [[USE_MIN]], i40 0, i40 [[RESULT]]
- // SIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = trunc i40 [[RESULT2]] to i16
+ // SIGNED-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MAX]], i16 -1, i16 [[RES]]
+ // SIGNED-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i40 [[SUM]], 0
+ // SIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = select i1 [[USE_MIN]], i16 0, i16 [[RES2]]
// UNSIGNED-NEXT: [[USA_SAT_RESIZE:%[a-z0-9]+]] = zext i16 [[USA_SAT]] to i39
// UNSIGNED-NEXT: [[I_RESIZE:%[a-z0-9]+]] = sext i32 [[I]] to i39
// UNSIGNED-NEXT: [[I_UPSCALE:%[a-z0-9]+]] = shl i39 [[I_RESIZE]], 7
// UNSIGNED-NEXT: [[SUM:%[0-9]+]] = call i39 @llvm.usub.sat.i39(i39 [[USA_SAT_RESIZE]], i39 [[I_UPSCALE]])
+ // UNSIGNED-NEXT: [[RES:%[a-z0-9]+]] = trunc i39 [[SUM]] to i16
// UNSIGNED-NEXT: [[USE_MAX:%[0-9]+]] = icmp sgt i39 [[SUM]], 32767
- // UNSIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = select i1 [[USE_MAX]], i39 32767, i39 [[SUM]]
- // UNSIGNED-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i39 [[RESULT]], 0
- // UNSIGNED-NEXT: [[RESULT2:%[a-z0-9]+]] = select i1 [[USE_MIN]], i39 0, i39 [[RESULT]]
- // UNSIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = trunc i39 [[RESULT2]] to i16
+ // UNSIGNED-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MAX]], i16 32767, i16 [[RES]]
+ // UNSIGNED-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i39 [[SUM]], 0
+ // UNSIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = select i1 [[USE_MIN]], i16 0, i16 [[RES2]]
// CHECK-NEXT: store i16 [[RESULT]], i16* %usa_sat, align 2
usa_sat = usa_sat - i;
}
Index: clang/test/Frontend/fixed_point_conversions.c
===================================================================
--- clang/test/Frontend/fixed_point_conversions.c
+++ clang/test/Frontend/fixed_point_conversions.c
@@ -155,75 +155,76 @@
sat_sa = sat_a;
// DEFAULT: [[OLD_ACCUM:%[0-9a-z]+]] = load i32, i32* %sat_a, align 4
// DEFAULT-NEXT: [[ACCUM:%[0-9a-z]+]] = ashr i32 [[OLD_ACCUM]], 8
- // DEFAULT-NEXT: [[USE_MAX:%[0-9a-z]+]] = icmp sgt i32 [[ACCUM]], 32767
- // DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = select i1 [[USE_MAX]], i32 32767, i32 [[ACCUM]]
- // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[RESULT]], -32768
- // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MIN]], i32 -32768, i32 [[RESULT]]
- // DEFAULT-NEXT: [[RESULT_TRUNC:%[0-9a-z]+]] = trunc i32 [[RESULT2]] to i16
- // DEFAULT-NEXT: store i16 [[RESULT_TRUNC]], i16* %sat_sa, align 2
+ // DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = trunc i32 [[ACCUM]] to i16
+ // DEFAULT-NEXT: [[USE_MAX:%[0-9a-z]+]] = icmp sgt i32 [[OLD_ACCUM]], 8388352
+ // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MAX]], i16 32767, i16 [[RESULT]]
+ // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[OLD_ACCUM]], -8388608
+ // DEFAULT-NEXT: [[RESULT3:%[0-9a-z]+]] = select i1 [[USE_MIN]], i16 -32768, i16 [[RESULT2]]
+ // DEFAULT-NEXT: store i16 [[RESULT3]], i16* %sat_sa, align 2
// Accum to Fract, decreasing scale
sat_sf = sat_a;
// DEFAULT: [[OLD_ACCUM:%[0-9a-z]+]] = load i32, i32* %sat_a, align 4
// DEFAULT-NEXT: [[FRACT:%[0-9a-z]+]] = ashr i32 [[OLD_ACCUM]], 8
- // DEFAULT-NEXT: [[USE_MAX:%[0-9a-z]+]] = icmp sgt i32 [[FRACT]], 127
- // DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = select i1 [[USE_MAX]], i32 127, i32 [[FRACT]]
- // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[RESULT]], -128
- // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MIN]], i32 -128, i32 [[RESULT]]
- // DEFAULT-NEXT: [[RESULT_TRUNC:%[0-9a-z]+]] = trunc i32 [[RESULT2]] to i8
- // DEFAULT-NEXT: store i8 [[RESULT_TRUNC]], i8* %sat_sf, align 1
+ // DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = trunc i32 [[FRACT]] to i8
+ // DEFAULT-NEXT: [[USE_MAX:%[0-9a-z]+]] = icmp sgt i32 [[OLD_ACCUM]], 32512
+ // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MAX]], i8 127, i8 [[RESULT]]
+ // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[OLD_ACCUM]], -32768
+ // DEFAULT-NEXT: [[RESULT3:%[0-9a-z]+]] = select i1 [[USE_MIN]], i8 -128, i8 [[RESULT2]]
+ // DEFAULT-NEXT: store i8 [[RESULT3]], i8* %sat_sf, align 1
// Accum to Fract, same scale
sat_f = a;
// DEFAULT: [[ACCUM:%[0-9a-z]+]] = load i32, i32* %a, align 4
+ // DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = trunc i32 [[ACCUM]] to i16
// DEFAULT-NEXT: [[USE_MAX:%[0-9a-z]+]] = icmp sgt i32 [[ACCUM]], 32767
- // DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = select i1 [[USE_MAX]], i32 32767, i32 [[ACCUM]]
- // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[RESULT]], -32768
- // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MIN]], i32 -32768, i32 [[RESULT]]
- // DEFAULT-NEXT: [[RESULT_TRUNC:%[0-9a-z]+]] = trunc i32 [[RESULT2]] to i16
- // DEFAULT-NEXT: store i16 [[RESULT_TRUNC]], i16* %sat_f, align 2
+ // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MAX]], i16 32767, i16 [[RESULT]]
+ // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[ACCUM]], -32768
+ // DEFAULT-NEXT: [[RESULT3:%[0-9a-z]+]] = select i1 [[USE_MIN]], i16 -32768, i16 [[RESULT2]]
+ // DEFAULT-NEXT: store i16 [[RESULT3]], i16* %sat_f, align 2
- // Accum to Fract, increasing scale
+ // Accum to Fract, increasing scale, same size
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 [[OLD_ACCUM]], 32767
+ // DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = select i1 [[USE_MAX]], i32 2147483647, i32 [[FRACT]]
+ // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[OLD_ACCUM]], -32768
+ // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MIN]], i32 -2147483648, i32 [[RESULT]]
+ // DEFAULT-NEXT: store i32 [[RESULT2]], i32* %sat_lf, align 4
+
+ sat_a = sat_lf;
+ // DEFAULT: [[OLD_FRACT:%[0-9a-z]+]] = load i32, i32* %sat_lf, align 4
+ // DEFAULT-NEXT: [[ACCUM:%[0-9a-z]+]] = ashr i32 [[OLD_FRACT]], 16
+ // DEFAULT-NEXT: store i32 [[ACCUM]], i32* %sat_a, align 4
// Signed to unsigned, decreasing scale
_Sat _Accum sat_a2;
sat_usa = sat_a2;
// DEFAULT: [[OLD_ACCUM:%[0-9a-z]+]] = load i32, i32* %sat_a2, align 4
// DEFAULT-NEXT: [[ACCUM:%[0-9a-z]+]] = ashr i32 [[OLD_ACCUM]], 7
- // DEFAULT-NEXT: [[USE_MAX:%[0-9a-z]+]] = icmp sgt i32 [[ACCUM]], 65535
- // DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = select i1 [[USE_MAX]], i32 65535, i32 [[ACCUM]]
- // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[RESULT]], 0
- // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MIN]], i32 0, i32 [[RESULT]]
- // DEFAULT-NEXT: [[RESULT_TRUNC:%[0-9a-z]+]] = trunc i32 [[RESULT2]] to i16
- // DEFAULT-NEXT: store i16 [[RESULT_TRUNC]], i16* %sat_usa, align 2
+ // DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = trunc i32 [[ACCUM]] to i16
+ // DEFAULT-NEXT: [[USE_MAX:%[0-9a-z]+]] = icmp sgt i32 [[OLD_ACCUM]], 8388480
+ // DEFAULT-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MAX]], i16 -1, i16 [[RESULT]]
+ // DEFAULT-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[OLD_ACCUM]], 0
+ // DEFAULT-NEXT: [[RESULT3:%[0-9a-z]+]] = select i1 [[USE_MIN]], i16 0, i16 [[RESULT2]]
+ // DEFAULT-NEXT: store i16 [[RESULT3]], i16* %sat_usa, align 2
// SAME: [[OLD_ACCUM:%[0-9a-z]+]] = load i32, i32* %sat_a2, align 4
// SAME-NEXT: [[ACCUM:%[0-9a-z]+]] = ashr i32 [[OLD_ACCUM]], 8
- // SAME-NEXT: [[USE_MAX:%[0-9a-z]+]] = icmp sgt i32 [[ACCUM]], 32767
- // SAME-NEXT: [[RESULT:%[0-9a-z]+]] = select i1 [[USE_MAX]], i32 32767, i32 [[ACCUM]]
- // SAME-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[RESULT]], 0
- // SAME-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MIN]], i32 0, i32 [[RESULT]]
- // SAME-NEXT: [[RESULT_TRUNC:%[0-9a-z]+]] = trunc i32 [[RESULT2]] to i16
- // SAME-NEXT: store i16 [[RESULT_TRUNC]], i16* %sat_usa, align 2
-
- // Signed to unsigned, increasing scale
+ // SAME-NEXT: [[RESULT:%[0-9a-z]+]] = trunc i32 [[ACCUM]] to i16
+ // SAME-NEXT: [[USE_MAX:%[0-9a-z]+]] = icmp sgt i32 [[OLD_ACCUM]], 8388352
+ // SAME-NEXT: [[RESULT2:%[0-9a-z]+]] = select i1 [[USE_MAX]], i16 32767, i16 [[RESULT]]
+ // SAME-NEXT: [[USE_MIN:%[0-9a-z]+]] = icmp slt i32 [[OLD_ACCUM]], 0
+ // SAME-NEXT: [[RESULT3:%[0-9a-z]+]] = select i1 [[USE_MIN]], i16 0, i16 [[RESULT2]]
+ // SAME-NEXT: store i16 [[RESULT3]], i16* %sat_usa, align 2
+
+ // Signed to unsigned, increasing scale, same size
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 [[OLD_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]]
@@ -250,13 +251,13 @@
// DEFAULT: [[FRACT:%[0-9a-z]+]] = load i8, i8* %sat_sf, align 1
// DEFAULT-NEXT: [[FRACT_EXT:%[0-9a-z]+]] = sext i8 [[FRACT]] to i32
// DEFAULT-NEXT: [[ACCUM:%[0-9a-z]+]] = shl i32 [[FRACT_EXT]], 9
- // DEFAULT-NEXT: [[IS_NEG:%[0-9a-z]+]] = icmp slt i32 [[ACCUM]], 0
+ // DEFAULT-NEXT: [[IS_NEG:%[0-9a-z]+]] = icmp slt i8 [[FRACT]], 0
// DEFAULT-NEXT: [[RESULT:%[0-9a-z]+]] = select i1 [[IS_NEG]], i32 0, i32 [[ACCUM]]
// DEFAULT-NEXT: store i32 [[RESULT]], i32* %sat_ua, align 4
// SAME: [[FRACT:%[0-9a-z]+]] = load i8, i8* %sat_sf, align 1
// SAME-NEXT: [[FRACT_EXT:%[0-9a-z]+]] = sext i8 [[FRACT]] to i32
// SAME-NEXT: [[ACCUM:%[0-9a-z]+]] = shl i32 [[FRACT_EXT]], 8
- // SAME-NEXT: [[IS_NEG:%[0-9a-z]+]] = icmp slt i32 [[ACCUM]], 0
+ // SAME-NEXT: [[IS_NEG:%[0-9a-z]+]] = icmp slt i8 [[FRACT]], 0
// SAME-NEXT: [[RESULT:%[0-9a-z]+]] = select i1 [[IS_NEG]], i32 0, i32 [[ACCUM]]
// SAME-NEXT: store i32 [[RESULT]], i32* %sat_ua, align 4
}
Index: clang/test/Frontend/fixed_point_add.c
===================================================================
--- clang/test/Frontend/fixed_point_add.c
+++ clang/test/Frontend/fixed_point_add.c
@@ -375,11 +375,11 @@
// CHECK-NEXT: [[I_EXT:%[a-z0-9]+]] = sext i32 [[I]] to i39
// CHECK-NEXT: [[I:%[a-z0-9]+]] = shl i39 [[I_EXT]], 7
// CHECK-NEXT: [[SUM:%[0-9]+]] = call i39 @llvm.sadd.sat.i39(i39 [[SA_SAT_EXT]], i39 [[I]])
+ // CHECK-NEXT: [[RES:%[a-z0-9]+]] = trunc i39 [[SUM]] to i16
// CHECK-NEXT: [[USE_MAX:%[0-9]+]] = icmp sgt i39 [[SUM]], 32767
- // CHECK-NEXT: [[RES:%[a-z0-9]+]] = select i1 [[USE_MAX]], i39 32767, i39 [[SUM]]
- // CHECK-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i39 [[RES]], -32768
- // CHECK-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MIN]], i39 -32768, i39 [[RES]]
- // CHECK-NEXT: [[RES3:%[a-z0-9]+]] = trunc i39 [[RES2]] to i16
+ // CHECK-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MAX]], i16 32767, i16 [[RES]]
+ // CHECK-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i39 [[SUM]], -32768
+ // CHECK-NEXT: [[RES3:%[a-z0-9]+]] = select i1 [[USE_MIN]], i16 -32768, i16 [[RES2]]
// CHECK-NEXT: store i16 [[RES3]], i16* %sa_sat, align 2
sa_sat = sa_sat + i;
@@ -389,11 +389,11 @@
// CHECK-NEXT: [[I_EXT:%[a-z0-9]+]] = zext i32 [[I]] to i40
// CHECK-NEXT: [[I:%[a-z0-9]+]] = shl i40 [[I_EXT]], 7
// CHECK-NEXT: [[SUM:%[0-9]+]] = call i40 @llvm.sadd.sat.i40(i40 [[SA_SAT_EXT]], i40 [[I]])
+ // CHECK-NEXT: [[RES:%[a-z0-9]+]] = trunc i40 [[SUM]] to i16
// CHECK-NEXT: [[USE_MAX:%[0-9]+]] = icmp sgt i40 [[SUM]], 32767
- // CHECK-NEXT: [[RES:%[a-z0-9]+]] = select i1 [[USE_MAX]], i40 32767, i40 [[SUM]]
- // CHECK-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i40 [[RES]], -32768
- // CHECK-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MIN]], i40 -32768, i40 [[RES]]
- // CHECK-NEXT: [[RES3:%[a-z0-9]+]] = trunc i40 [[RES2]] to i16
+ // CHECK-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MAX]], i16 32767, i16 [[RES]]
+ // CHECK-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i40 [[SUM]], -32768
+ // CHECK-NEXT: [[RES3:%[a-z0-9]+]] = select i1 [[USE_MIN]], i16 -32768, i16 [[RES2]]
// CHECK-NEXT: store i16 [[RES3]], i16* %sa_sat, align 2
sa_sat = sa_sat + ui;
@@ -414,20 +414,20 @@
// SIGNED-NEXT: [[I_RESIZE:%[a-z0-9]+]] = sext i32 [[I]] to i40
// SIGNED-NEXT: [[I_UPSCALE:%[a-z0-9]+]] = shl i40 [[I_RESIZE]], 8
// SIGNED-NEXT: [[SUM:%[0-9]+]] = call i40 @llvm.uadd.sat.i40(i40 [[USA_SAT_RESIZE]], i40 [[I_UPSCALE]])
+ // SIGNED-NEXT: [[RES:%[a-z0-9]+]] = trunc i40 [[SUM]] to i16
// SIGNED-NEXT: [[USE_MAX:%[0-9]+]] = icmp sgt i40 [[SUM]], 65535
- // SIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = select i1 [[USE_MAX]], i40 65535, i40 [[SUM]]
- // SIGNED-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i40 [[RESULT]], 0
- // SIGNED-NEXT: [[RESULT2:%[a-z0-9]+]] = select i1 [[USE_MIN]], i40 0, i40 [[RESULT]]
- // SIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = trunc i40 [[RESULT2]] to i16
+ // SIGNED-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MAX]], i16 -1, i16 [[RES]]
+ // SIGNED-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i40 [[SUM]], 0
+ // SIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = select i1 [[USE_MIN]], i16 0, i16 [[RES2]]
// UNSIGNED-NEXT: [[USA_SAT_RESIZE:%[a-z0-9]+]] = zext i16 [[USA_SAT]] to i39
// UNSIGNED-NEXT: [[I_RESIZE:%[a-z0-9]+]] = sext i32 [[I]] to i39
// UNSIGNED-NEXT: [[I_UPSCALE:%[a-z0-9]+]] = shl i39 [[I_RESIZE]], 7
// UNSIGNED-NEXT: [[SUM:%[0-9]+]] = call i39 @llvm.uadd.sat.i39(i39 [[USA_SAT_RESIZE]], i39 [[I_UPSCALE]])
+ // UNSIGNED-NEXT: [[RES:%[a-z0-9]+]] = trunc i39 [[SUM]] to i16
// UNSIGNED-NEXT: [[USE_MAX:%[0-9]+]] = icmp sgt i39 [[SUM]], 32767
- // UNSIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = select i1 [[USE_MAX]], i39 32767, i39 [[SUM]]
- // UNSIGNED-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i39 [[RESULT]], 0
- // UNSIGNED-NEXT: [[RESULT2:%[a-z0-9]+]] = select i1 [[USE_MIN]], i39 0, i39 [[RESULT]]
- // UNSIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = trunc i39 [[RESULT2]] to i16
+ // UNSIGNED-NEXT: [[RES2:%[a-z0-9]+]] = select i1 [[USE_MAX]], i16 32767, i16 [[RES]]
+ // UNSIGNED-NEXT: [[USE_MIN:%[0-9]+]] = icmp slt i39 [[SUM]], 0
+ // UNSIGNED-NEXT: [[RESULT:%[a-z0-9]+]] = select i1 [[USE_MIN]], i16 0, i16 [[RES2]]
// CHECK-NEXT: store i16 [[RESULT]], i16* %usa_sat, align 2
usa_sat = usa_sat + i;
}
Index: clang/lib/CodeGen/CGExprScalar.cpp
===================================================================
--- clang/lib/CodeGen/CGExprScalar.cpp
+++ clang/lib/CodeGen/CGExprScalar.cpp
@@ -1452,7 +1452,6 @@
using llvm::ConstantInt;
using llvm::Value;
- unsigned SrcWidth = SrcFPSema.getWidth();
unsigned DstWidth = DstFPSema.getWidth();
unsigned SrcScale = SrcFPSema.getScale();
unsigned DstScale = DstFPSema.getScale();
@@ -1462,58 +1461,56 @@
llvm::Type *DstIntTy = Builder.getIntNTy(DstWidth);
Value *Result = Src;
- unsigned ResultWidth = SrcWidth;
- if (!DstFPSema.isSaturated()) {
- // Downscale.
- if (DstScale < SrcScale)
- Result = SrcIsSigned ?
- Builder.CreateAShr(Result, SrcScale - DstScale, "downscale") :
- Builder.CreateLShr(Result, SrcScale - DstScale, "downscale");
+ // Downscale.
+ if (DstScale < SrcScale)
+ Result = SrcIsSigned
+ ? Builder.CreateAShr(Result, SrcScale - DstScale, "downscale")
+ : Builder.CreateLShr(Result, SrcScale - DstScale, "downscale");
- // Resize.
- Result = Builder.CreateIntCast(Result, DstIntTy, SrcIsSigned, "resize");
+ // Resize.
+ Result = Builder.CreateIntCast(Result, DstIntTy, SrcIsSigned, "resize");
- // Upscale.
- if (DstScale > SrcScale)
- Result = Builder.CreateShl(Result, DstScale - SrcScale, "upscale");
- } else {
- // 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");
- Result = Builder.CreateShl(Result, DstScale - SrcScale, "upscale");
- } else if (DstScale < SrcScale) {
- Result = SrcIsSigned ?
- Builder.CreateAShr(Result, SrcScale - DstScale, "downscale") :
- Builder.CreateLShr(Result, SrcScale - DstScale, "downscale");
- }
+ // Upscale.
+ if (DstScale > SrcScale)
+ Result = Builder.CreateShl(Result, DstScale - SrcScale, "upscale");
+ if (DstFPSema.isSaturated()) {
// Handle saturation.
+ unsigned ResultWidth = Result->getType()->getIntegerBitWidth();
+
bool LessIntBits = DstFPSema.getIntegralBits() < SrcFPSema.getIntegralBits();
if (LessIntBits) {
- Value *Max = ConstantInt::get(
- CGF.getLLVMContext(),
- APFixedPoint::getMax(DstFPSema).getValue().extOrTrunc(ResultWidth));
- Value *TooHigh = SrcIsSigned ? Builder.CreateICmpSGT(Result, Max)
- : Builder.CreateICmpUGT(Result, Max);
- Result = Builder.CreateSelect(TooHigh, Max, Result, "satmax");
+ APFixedPoint FXMax = APFixedPoint::getMax(DstFPSema);
+
+ // This never overflows since the max is always positive and the semantics
+ // we convert to have more integral bits.
+ Value *MaxCmp = ConstantInt::get(CGF.getLLVMContext(),
+ FXMax.convert(SrcFPSema).getValue());
+
+ Value *Max = ConstantInt::get(CGF.getLLVMContext(),
+ FXMax.getValue().extOrTrunc(ResultWidth));
+ Value *TooHigh = SrcIsSigned ? Builder.CreateICmpSGT(Src, MaxCmp)
+ : Builder.CreateICmpUGT(Src, MaxCmp);
+ Result = Builder.CreateSelect(TooHigh, Max, Result);
}
+
// Cannot overflow min to dest type if src is unsigned since all fixed
// point types can cover the unsigned min of 0.
if (SrcIsSigned && (LessIntBits || !DstIsSigned)) {
- Value *Min = ConstantInt::get(
- CGF.getLLVMContext(),
- APFixedPoint::getMin(DstFPSema).getValue().extOrTrunc(ResultWidth));
- Value *TooLow = Builder.CreateICmpSLT(Result, Min);
- Result = Builder.CreateSelect(TooLow, Min, Result, "satmin");
+ APFixedPoint FXMin = APFixedPoint::getMin(DstFPSema);
+
+ // This never overflows since the min can always for in the range of
+ // values of the semantics we convert to.
+ Value *MinCmp = ConstantInt::get(CGF.getLLVMContext(),
+ FXMin.convert(SrcFPSema).getValue());
+
+ Value *Min = ConstantInt::get(CGF.getLLVMContext(),
+ FXMin.getValue().extOrTrunc(ResultWidth));
+ Value *TooLow = SrcIsSigned ? Builder.CreateICmpSLT(Src, MinCmp)
+ : Builder.CreateICmpULT(Src, MinCmp);
+ Result = Builder.CreateSelect(TooLow, Min, Result);
}
-
- // Resize the integer part to get the final destination size.
- if (ResultWidth != DstWidth)
- Result = Builder.CreateIntCast(Result, DstIntTy, SrcIsSigned, "resize");
}
return Result;
}
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
