[clang][codegen] Remove the insertion of `correctly-rounded-divide-sqrt-fp-math` fn-attr.

[hliao]

Summary

• -cl-fp32-correctly-rounded-divide-sqrt is already handled in a per-instruction manner by annotating the accuracy required. There's no need to add that fn-attr. So far, there's no in-tree backend handling that attr and that OpenCL specific option.
• In case that out-of-tree backends are broken, this change could be reverted if those backends could not be fixed.

[hliao]

Rebase

[bader]

You might need add [OpenCL] tag to the commit message.

clang/lib/CodeGen/CGCall.cpp

if (AttrOnCallSite) {
     FuncAttrs.addAttribute("unsafe-fp-math",
                            llvm::toStringRef(LangOpts.UnsafeFPMath));
     FuncAttrs.addAttribute("use-soft-float",
                            llvm::toStringRef(CodeGenOpts.SoftFloat));
     FuncAttrs.addAttribute("stack-protector-buffer-size",
                            llvm::utostr(CodeGenOpts.SSPBufferSize));
     FuncAttrs.addAttribute("no-signed-zeros-fp-math",
                            llvm::toStringRef(LangOpts.NoSignedZero));
-    if (getLangOpts().OpenCL) {
-      FuncAttrs.addAttribute(
-          "correctly-rounded-divide-sqrt-fp-math",
-          llvm::toStringRef(CodeGenOpts.CorrectlyRoundedDivSqrt));
-    }
 
     // TODO: Reciprocal estimate codegen options should apply to instructions?
     const std::vector<std::string> &Recips = CodeGenOpts.Reciprocals;
     if (!Recips.empty())
       FuncAttrs.addAttribute("reciprocal-estimates",
                              llvm::join(Recips, ","));
 
     if (!CodeGenOpts.PreferVectorWidth.empty() &&

clang/test/CodeGenOpenCL/amdgpu-attrs.cl

 // CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2"
 // CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
 // CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4"
 // CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
 
 // CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
 // CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="56" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
 
-// CHECK-DAG: attributes [[A_FUNCTION]] = {{.*}} "correctly-rounded-divide-sqrt-fp-math"="false"
+// CHECK-DAG: attributes [[A_FUNCTION]] = {{.*}}
 // CHECK-DAG: attributes [[DEFAULT_KERNEL_ATTRS]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="56"

clang/test/CodeGenOpenCL/fpmath.cl

 // RUN: %clang_cc1 %s -emit-llvm -o - -triple spir-unknown-unknown | FileCheck --check-prefix=CHECK --check-prefix=NODIVOPT %s
 // RUN: %clang_cc1 %s -emit-llvm -o - -triple spir-unknown-unknown -cl-fp32-correctly-rounded-divide-sqrt | FileCheck --check-prefix=CHECK --check-prefix=DIVOPT %s
 // RUN: %clang_cc1 %s -emit-llvm -o - -DNOFP64 -cl-std=CL1.2 -triple r600-unknown-unknown -target-cpu r600 -pedantic | FileCheck --check-prefix=CHECK-FLT %s
 // RUN: %clang_cc1 %s -emit-llvm -o - -DFP64 -cl-std=CL1.2 -triple spir-unknown-unknown -pedantic | FileCheck --check-prefix=CHECK-DBL %s
 
 typedef __attribute__(( ext_vector_type(4) )) float float4;
 
 float spscalardiv(float a, float b) {
   // CHECK: @spscalardiv
-  // CHECK: #[[ATTR:[0-9]+]]
   // CHECK: fdiv{{.*}},
   // NODIVOPT: !fpmath ![[MD:[0-9]+]]
   // DIVOPT-NOT: !fpmath ![[MD:[0-9]+]]
   return a / b;
 }
 
 float4 spvectordiv(float4 a, float4 b) {
   // CHECK: @spvectordiv
-  // CHECK: #[[ATTR2:[0-9]+]]
   // CHECK: fdiv{{.*}},
   // NODIVOPT: !fpmath ![[MD]]
   // DIVOPT-NOT: !fpmath ![[MD]]
   return a / b;
 }
 
 #if __OPENCL_C_VERSION__ >=120
 void printf(constant char* fmt, ...);
 
 void testdbllit(long *val) {
   // CHECK-FLT: float 2.000000e+01
   // CHECK-DBL: double 2.000000e+01
   printf("%f", 20.0);
 }
 
 #endif
 
 #ifndef NOFP64
 #pragma OPENCL EXTENSION cl_khr_fp64 : enable
 double dpscalardiv(double a, double b) {
   // CHECK: @dpscalardiv
-  // CHECK: #[[ATTR]]
   // CHECK-NOT: !fpmath
   return a / b;
 }
 #endif
 
-// CHECK: attributes #[[ATTR]] = {
-// NODIVOPT-SAME: "correctly-rounded-divide-sqrt-fp-math"="false"
-// DIVOPT-SAME: "correctly-rounded-divide-sqrt-fp-math"="true"
-// CHECK-SAME: }
-// CHECK: attributes #[[ATTR2]] = {
-// NODIVOPT-SAME: "correctly-rounded-divide-sqrt-fp-math"="false"
-// DIVOPT-SAME: "correctly-rounded-divide-sqrt-fp-math"="true"
-// CHECK-SAME: }
 // NODIVOPT: ![[MD]] = !{float 2.500000e+00}