arsenm updated this revision to Diff 546814.
arsenm marked an inline comment as done.
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D156743/new/
https://reviews.llvm.org/D156743
Files:
clang/lib/Headers/opencl-c-base.h
clang/lib/Headers/opencl-c.h
clang/lib/Sema/OpenCLBuiltins.td
clang/test/CodeGenOpenCL/sqrt-fpmath.cl
Index: clang/test/CodeGenOpenCL/sqrt-fpmath.cl
===================================================================
--- /dev/null
+++ clang/test/CodeGenOpenCL/sqrt-fpmath.cl
@@ -0,0 +1,201 @@
+// Test that float variants of sqrt are emitted as available_externally inline
+// definitions that call the sqrt intrinsic with appropriate !fpmath metadata
+// depending on -cl-fp32-correctly-rounded-divide-sqrt
+
+// Test with -fdeclare-opencl-builtins
+// RUN: %clang_cc1 -disable-llvm-passes -triple amdgcn-unknown-unknown -fdeclare-opencl-builtins -finclude-default-header -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,DEFAULT %s
+// RUN: %clang_cc1 -disable-llvm-passes -triple amdgcn-unknown-unknown -fdeclare-opencl-builtins -finclude-default-header -cl-fp32-correctly-rounded-divide-sqrt -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,CORRECTLYROUNDED %s
+
+// RUN: %clang_cc1 -disable-llvm-passes -triple amdgcn-unknown-unknown -fdeclare-opencl-builtins -finclude-default-header -cl-unsafe-math-optimizations -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,DEFAULT-UNSAFE %s
+// RUN: %clang_cc1 -disable-llvm-passes -triple amdgcn-unknown-unknown -fdeclare-opencl-builtins -finclude-default-header -cl-fp32-correctly-rounded-divide-sqrt -cl-unsafe-math-optimizations -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,CORRECTLYROUNDED-UNSAFE %s
+
+// Test without -fdeclare-opencl-builtins
+// RUN: %clang_cc1 -disable-llvm-passes -triple amdgcn-unknown-unknown -finclude-default-header -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,DEFAULT %s
+// RUN: %clang_cc1 -disable-llvm-passes -triple amdgcn-unknown-unknown -finclude-default-header -cl-fp32-correctly-rounded-divide-sqrt -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,CORRECTLYROUNDED %s
+
+// RUN: %clang_cc1 -disable-llvm-passes -triple amdgcn-unknown-unknown -finclude-default-header -cl-unsafe-math-optimizations -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,DEFAULT-UNSAFE %s
+// RUN: %clang_cc1 -disable-llvm-passes -triple amdgcn-unknown-unknown -finclude-default-header -cl-fp32-correctly-rounded-divide-sqrt -cl-unsafe-math-optimizations -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,CORRECTLYROUNDED-UNSAFE %s
+
+#pragma OPENCL EXTENSION cl_khr_fp16 : enable
+
+// CHECK-LABEL: define {{.*}} float @call_sqrt_f32(
+// CHECK: call {{.*}} float @_Z4sqrtf(float noundef %{{.+}}) #{{[0-9]+$}}
+float call_sqrt_f32(float x) {
+ return sqrt(x);
+}
+
+// CHECK-LABEL: define available_externally float @_Z4sqrtf(float noundef %__x)
+// DEFAULT: call float @llvm.sqrt.f32(float %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED: call float @llvm.sqrt.f32(float %{{.+}}){{$}}
+
+// DEFAULT-UNSAFE: call reassoc nsz arcp contract afn float @llvm.sqrt.f32(float %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED-UNSAFE: call reassoc nsz arcp contract afn float @llvm.sqrt.f32(float %{{.+}}){{$}}
+
+// CHECK-LABEL: define {{.*}} <2 x float> @call_sqrt_v2f32(
+// CHECK: call {{.*}} <2 x float> @_Z4sqrtDv2_f(<2 x float> noundef %{{.*}}) #{{[0-9]+$}}
+float2 call_sqrt_v2f32(float2 x) {
+ return sqrt(x);
+}
+
+// CHECK-LABEL: define available_externally <2 x float> @_Z4sqrtDv2_f(<2 x float> noundef %__x)
+// DEFAULT: call <2 x float> @llvm.sqrt.v2f32(<2 x float> %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED: call <2 x float> @llvm.sqrt.v2f32(<2 x float> %{{.+}}){{$}}
+
+// DEFAULT-UNSAFE: call reassoc nsz arcp contract afn <2 x float> @llvm.sqrt.v2f32(<2 x float> %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED-UNSAFE: call reassoc nsz arcp contract afn <2 x float> @llvm.sqrt.v2f32(<2 x float> %{{.+}}){{$}}
+
+// CHECK-LABEL: define {{.*}} <3 x float> @call_sqrt_v3f32(
+// CHECK: call {{.*}} <3 x float> @_Z4sqrtDv3_f(<3 x float> noundef %{{.*}}) #{{[0-9]+$}}
+float3 call_sqrt_v3f32(float3 x) {
+ return sqrt(x);
+}
+
+// CHECK-LABEL: define available_externally <3 x float> @_Z4sqrtDv3_f(<3 x float> noundef %__x)
+// DEFAULT: call <3 x float> @llvm.sqrt.v3f32(<3 x float> %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED: call <3 x float> @llvm.sqrt.v3f32(<3 x float> %{{.+}}){{$}}
+
+// DEFAULT-UNSAFE: call reassoc nsz arcp contract afn <3 x float> @llvm.sqrt.v3f32(<3 x float> %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED-UNSAFE: call reassoc nsz arcp contract afn <3 x float> @llvm.sqrt.v3f32(<3 x float> %{{.+}}){{$}}
+
+
+// CHECK-LABEL: define {{.*}} <4 x float> @call_sqrt_v4f32(
+// CHECK: call {{.*}} <4 x float> @_Z4sqrtDv4_f(<4 x float> noundef %{{.*}}) #{{[0-9]+$}}
+float4 call_sqrt_v4f32(float4 x) {
+ return sqrt(x);
+}
+
+// CHECK-LABEL: define available_externally <4 x float> @_Z4sqrtDv4_f(<4 x float> noundef %__x)
+// DEFAULT: call <4 x float> @llvm.sqrt.v4f32(<4 x float> %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED: call <4 x float> @llvm.sqrt.v4f32(<4 x float> %{{.+}}){{$}}
+
+// DEFAULT-UNSAFE: call reassoc nsz arcp contract afn <4 x float> @llvm.sqrt.v4f32(<4 x float> %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED-UNSAFE: call reassoc nsz arcp contract afn <4 x float> @llvm.sqrt.v4f32(<4 x float> %{{.+}}){{$}}
+
+// CHECK-LABEL: define {{.*}} <8 x float> @call_sqrt_v8f32(
+// CHECK: call {{.*}} <8 x float> @_Z4sqrtDv8_f(<8 x float> noundef %{{.*}}) #{{[0-9]+$}}
+float8 call_sqrt_v8f32(float8 x) {
+ return sqrt(x);
+}
+
+// CHECK-LABEL: define available_externally <8 x float> @_Z4sqrtDv8_f(<8 x float> noundef %__x)
+// DEFAULT: call <8 x float> @llvm.sqrt.v8f32(<8 x float> %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED: call <8 x float> @llvm.sqrt.v8f32(<8 x float> %{{.+}}){{$}}
+
+// DEFAULT-UNSAFE: call reassoc nsz arcp contract afn <8 x float> @llvm.sqrt.v8f32(<8 x float> %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED-UNSAFE: call reassoc nsz arcp contract afn <8 x float> @llvm.sqrt.v8f32(<8 x float> %{{.+}}){{$}}
+
+
+// CHECK-LABEL: define {{.*}} <16 x float> @call_sqrt_v16f32(
+// CHECK: call {{.*}} <16 x float> @_Z4sqrtDv16_f(<16 x float> noundef %{{.*}}) #{{[0-9]+$}}
+float16 call_sqrt_v16f32(float16 x) {
+ return sqrt(x);
+}
+
+// CHECK-LABEL: define available_externally <16 x float> @_Z4sqrtDv16_f(<16 x float> noundef %__x)
+// DEFAULT: call <16 x float> @llvm.sqrt.v16f32(<16 x float> %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED: call <16 x float> @llvm.sqrt.v16f32(<16 x float> %{{.+}}){{$}}
+
+// DEFAULT-UNSAFE: call reassoc nsz arcp contract afn <16 x float> @llvm.sqrt.v16f32(<16 x float> %{{.+}}), !fpmath [[$FPMATH:![0-9]+]]{{$}}
+// CORRECTLYROUNDED-UNSAFE: call reassoc nsz arcp contract afn <16 x float> @llvm.sqrt.v16f32(<16 x float> %{{.+}}){{$}}
+
+
+// Not for f64
+// CHECK-LABEL: define {{.*}} double @call_sqrt_f64(
+// CHECK: call {{.*}} double @_Z4sqrtd(double noundef %{{.+}}) #{{[0-9]+$}}
+double call_sqrt_f64(double x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// Not for f64
+// CHECK-LABEL: define {{.*}} <2 x double> @call_sqrt_v2f64(
+// CHECK: call {{.*}} <2 x double> @_Z4sqrtDv2_d(<2 x double> noundef %{{.+}}) #{{[0-9]+$}}
+double2 call_sqrt_v2f64(double2 x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// CHECK-LABEL: define {{.*}} <3 x double> @call_sqrt_v3f64(
+// CHECK: call {{.*}} <3 x double> @_Z4sqrtDv3_d(<3 x double> noundef %{{.+}}) #{{[0-9]+$}}
+double3 call_sqrt_v3f64(double3 x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// CHECK-LABEL: define {{.*}} <4 x double> @call_sqrt_v4f64(
+// CHECK: call {{.*}} <4 x double> @_Z4sqrtDv4_d(<4 x double> noundef %{{.+}}) #{{[0-9]+$}}
+double4 call_sqrt_v4f64(double4 x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// CHECK-LABEL: define {{.*}} <8 x double> @call_sqrt_v8f64(
+// CHECK: call {{.*}} <8 x double> @_Z4sqrtDv8_d(<8 x double> noundef %{{.+}}) #{{[0-9]+$}}
+double8 call_sqrt_v8f64(double8 x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// CHECK-LABEL: define {{.*}} <16 x double> @call_sqrt_v16f64(
+// CHECK: call {{.*}} <16 x double> @_Z4sqrtDv16_d(<16 x double> noundef %{{.+}}) #{{[0-9]+$}}
+double16 call_sqrt_v16f64(double16 x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// Not for f16
+// CHECK-LABEL: define {{.*}} half @call_sqrt_f16(
+// CHECK: call {{.*}} half @_Z4sqrtDh(half noundef %{{.+}}) #{{[0-9]+$}}
+half call_sqrt_f16(half x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// CHECK-LABEL: define {{.*}} <2 x half> @call_sqrt_v2f16(
+// CHECK: call {{.*}} <2 x half> @_Z4sqrtDv2_Dh(<2 x half> noundef %{{.+}}) #{{[0-9]+$}}
+half2 call_sqrt_v2f16(half2 x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// CHECK-LABEL: define {{.*}} <3 x half> @call_sqrt_v3f16(
+// CHECK: call {{.*}} <3 x half> @_Z4sqrtDv3_Dh(<3 x half> noundef %{{.+}}) #{{[0-9]+$}}
+half3 call_sqrt_v3f16(half3 x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// CHECK-LABEL: define {{.*}} <4 x half> @call_sqrt_v4f16(
+// CHECK: call {{.*}} <4 x half> @_Z4sqrtDv4_Dh(<4 x half> noundef %{{.+}}) #{{[0-9]+$}}
+half4 call_sqrt_v4f16(half4 x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// CHECK-LABEL: define {{.*}} <8 x half> @call_sqrt_v8f16(
+// CHECK: call {{.*}} <8 x half> @_Z4sqrtDv8_Dh(<8 x half> noundef %{{.+}}) #{{[0-9]+$}}
+half8 call_sqrt_v8f16(half8 x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// CHECK-LABEL: define {{.*}} <16 x half> @call_sqrt_v16f16(
+// CHECK: call {{.*}} <16 x half> @_Z4sqrtDv16_Dh(<16 x half> noundef %{{.+}}) #{{[0-9]+$}}
+half16 call_sqrt_v16f16(half16 x) {
+ return sqrt(x);
+}
+
+// CHECK-NOT: define
+
+// DEFAULT: [[$FPMATH]] = !{float 3.000000e+00}
Index: clang/lib/Sema/OpenCLBuiltins.td
===================================================================
--- clang/lib/Sema/OpenCLBuiltins.td
+++ clang/lib/Sema/OpenCLBuiltins.td
@@ -563,12 +563,15 @@
"log", "log2", "log10", "log1p", "logb",
"rint", "round", "rsqrt",
"sin", "sinh", "sinpi",
- "sqrt",
"tan", "tanh", "tanpi",
"tgamma", "trunc",
"lgamma"] in {
def : Builtin<name, [FGenTypeN, FGenTypeN], Attr.Const>;
}
+
+// sqrt is handled in opencl-c-base.h to handle
+// -cl-fp32-correctly-rounded-divide-sqrt.
+
foreach name = ["nan"] in {
def : Builtin<name, [GenTypeFloatVecAndScalar, GenTypeUIntVecAndScalar], Attr.Const>;
def : Builtin<name, [GenTypeDoubleVecAndScalar, GenTypeULongVecAndScalar], Attr.Const>;
Index: clang/lib/Headers/opencl-c.h
===================================================================
--- clang/lib/Headers/opencl-c.h
+++ clang/lib/Headers/opencl-c.h
@@ -8496,32 +8496,6 @@
half16 __ovld __cnfn sinpi(half16);
#endif //cl_khr_fp16
-/**
- * Compute square root.
- */
-float __ovld __cnfn sqrt(float);
-float2 __ovld __cnfn sqrt(float2);
-float3 __ovld __cnfn sqrt(float3);
-float4 __ovld __cnfn sqrt(float4);
-float8 __ovld __cnfn sqrt(float8);
-float16 __ovld __cnfn sqrt(float16);
-#ifdef cl_khr_fp64
-double __ovld __cnfn sqrt(double);
-double2 __ovld __cnfn sqrt(double2);
-double3 __ovld __cnfn sqrt(double3);
-double4 __ovld __cnfn sqrt(double4);
-double8 __ovld __cnfn sqrt(double8);
-double16 __ovld __cnfn sqrt(double16);
-#endif //cl_khr_fp64
-#ifdef cl_khr_fp16
-half __ovld __cnfn sqrt(half);
-half2 __ovld __cnfn sqrt(half2);
-half3 __ovld __cnfn sqrt(half3);
-half4 __ovld __cnfn sqrt(half4);
-half8 __ovld __cnfn sqrt(half8);
-half16 __ovld __cnfn sqrt(half16);
-#endif //cl_khr_fp16
-
/**
* Compute tangent.
*/
Index: clang/lib/Headers/opencl-c-base.h
===================================================================
--- clang/lib/Headers/opencl-c-base.h
+++ clang/lib/Headers/opencl-c-base.h
@@ -819,6 +819,64 @@
#endif // cl_intel_device_side_avc_motion_estimation
+/**
+ * Compute square root.
+ *
+ * Provide inline implementations using the builtin so that we get appropriate
+ * !fpmath based on -cl-fp32-correctly-rounded-divide-sqrt, attached to
+ * llvm.sqrt. The implementation should still provide an external definition.
+ */
+#define __ovld __attribute__((overloadable))
+#define __cnfn __attribute__((const))
+
+inline float __ovld __cnfn sqrt(float __x) {
+ return __builtin_elementwise_sqrt(__x);
+}
+
+inline float2 __ovld __cnfn sqrt(float2 __x) {
+ return __builtin_elementwise_sqrt(__x);
+}
+
+inline float3 __ovld __cnfn sqrt(float3 __x) {
+ return __builtin_elementwise_sqrt(__x);
+}
+
+inline float4 __ovld __cnfn sqrt(float4 __x) {
+ return __builtin_elementwise_sqrt(__x);
+}
+
+inline float8 __ovld __cnfn sqrt(float8 __x) {
+ return __builtin_elementwise_sqrt(__x);
+}
+
+inline float16 __ovld __cnfn sqrt(float16 __x) {
+ return __builtin_elementwise_sqrt(__x);
+}
+
+// We only really want to define the float variants here. However bad things
+// seem to happen with -fdeclare-opencl-builtins and splitting the handling of
+// different overloads.
+
+#ifdef cl_khr_fp64
+double __ovld __cnfn sqrt(double);
+double2 __ovld __cnfn sqrt(double2);
+double3 __ovld __cnfn sqrt(double3);
+double4 __ovld __cnfn sqrt(double4);
+double8 __ovld __cnfn sqrt(double8);
+double16 __ovld __cnfn sqrt(double16);
+#endif //cl_khr_fp64
+#ifdef cl_khr_fp16
+half __ovld __cnfn sqrt(half);
+half2 __ovld __cnfn sqrt(half2);
+half3 __ovld __cnfn sqrt(half3);
+half4 __ovld __cnfn sqrt(half4);
+half8 __ovld __cnfn sqrt(half8);
+half16 __ovld __cnfn sqrt(half16);
+#endif //cl_khr_fp16
+
+#undef __cnfn
+#undef __ovld
+
// Disable any extensions we may have enabled previously.
#pragma OPENCL EXTENSION all : disable
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
