[compiler-rt] [builtins] Use _Float16 on extendhfsf2, truncdfhf2 __truncsfhf2 if available

[zatrazz]

Summary

On AArch64 it allows use the native FP16 ABI (although libcalls are
not emitted for fptrunc/fpext lowering), while on other architectures
the expected current semantic is preserved (arm for instance).

For testing the _Float16 usage is enabled by architecture base,
currently only for arm, aarch64, and arm64.

This re-enabled revert done by https://reviews.llvm.org/rGb534beabeed3ba1777cd0ff9ce552d077e496726

[MaskRay]

Is https://reviews.llvm.org/D91733#2407055 resolved?

[zatrazz]

In D92241#2421377, @MaskRay wrote:

Is https://reviews.llvm.org/D91733#2407055 resolved?

That is my aim by changing how the tests are built by enabling _Float16 per architecture bases with:

if (${arch} MATCHES "arm|aarch64|arm64" AND COMPILER_RT_HAS_FLOAT16)
  list(APPEND BUILTINS_TEST_TARGET_CFLAGS -DCOMPILER_RT_HAS_FLOAT16)
  string(REPLACE ";" " " BUILTINS_TEST_TARGET_CFLAGS "${BUILTINS_TEST_TARGET_CFLAGS}")
endif()

On compiler-rt/test/builtins/CMakeLists.txt (I am assuming the tests are always built with the resulting
built clang). Do you see another case where I should handle as well?

compiler-rt/cmake/builtin-config-ix.cmake

 builtin_check_c_compiler_source(COMPILER_RT_HAS_ATOMIC_KEYWORD
 "
 int foo(int x, int y) {
  _Atomic int result = x * y;
  return result;
 }
 ")
 
+builtin_check_c_compiler_source(COMPILER_RT_HAS_FLOAT16
+"
+_Float16 foo(_Float16 x) {
+ return x;
+}
+"
+)
 
 set(ARM64 aarch64)
 set(ARM32 arm armhf armv6m armv7m armv7em armv7 armv7s armv7k)
 set(HEXAGON hexagon)
 set(X86 i386)
 set(X86_64 x86_64)
 set(MIPS32 mips mipsel)
 set(MIPS64 mips64 mips64el)

compiler-rt/lib/builtins/CMakeLists.txt

 
 if (APPLE)
   add_subdirectory(Darwin-excludes)
   add_subdirectory(macho_embedded)
   darwin_add_builtin_libraries(${BUILTIN_SUPPORTED_OS})
 else ()
   set(BUILTIN_CFLAGS "")
 
+  append_list_if(COMPILER_RT_HAS_FLOAT16 -DCOMPILER_RT_HAS_FLOAT16 BUILTIN_CFLAGS)
+
   append_list_if(COMPILER_RT_HAS_STD_C11_FLAG -std=c11 BUILTIN_CFLAGS)
 
   # These flags would normally be added to CMAKE_C_FLAGS by the llvm
   # cmake step. Add them manually if this is a standalone build.
   if(COMPILER_RT_STANDALONE_BUILD)
     if(COMPILER_RT_BUILTINS_ENABLE_PIC)
       append_list_if(COMPILER_RT_HAS_FPIC_FLAG -fPIC BUILTIN_CFLAGS)
     endif()

compiler-rt/lib/builtins/extendhfsf2.c

 //===-- lib/extendhfsf2.c - half -> single conversion -------------*- C -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #define SRC_HALF
 #define DST_SINGLE
 #include "fp_extend_impl.inc"
 
 // Use a forwarding definition and noinline to implement a poor man's alias,
 // as there isn't a good cross-platform way of defining one.
-COMPILER_RT_ABI NOINLINE float __extendhfsf2(uint16_t a) {
+COMPILER_RT_ABI NOINLINE float __extendhfsf2(src_t a) {
   return __extendXfYf2__(a);
 }
 
-COMPILER_RT_ABI float __gnu_h2f_ieee(uint16_t a) { return __extendhfsf2(a); }
+COMPILER_RT_ABI float __gnu_h2f_ieee(src_t a) { return __extendhfsf2(a); }
 
 #if defined(__ARM_EABI__)
 #if defined(COMPILER_RT_ARMHF_TARGET)
-AEABI_RTABI float __aeabi_h2f(uint16_t a) { return __extendhfsf2(a); }
+AEABI_RTABI float __aeabi_h2f(src_t a) { return __extendhfsf2(a); }
 #else
 COMPILER_RT_ALIAS(__extendhfsf2, __aeabi_h2f)
 #endif
 #endif

compiler-rt/lib/builtins/fp_extend.h

 //===-lib/fp_extend.h - low precision -> high precision conversion -*- C
 //-*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
#else
   if (a & REP_C(0xffffffff00000000))
     return __builtin_clz(a >> 32);
   else
     return 32 + __builtin_clz(a & REP_C(0xffffffff));
 #endif
 }
 
 #elif defined SRC_HALF
+#ifdef COMPILER_RT_HAS_FLOAT16
+typedef _Float16 src_t;
+#else
 typedef uint16_t src_t;
+#endif
 typedef uint16_t src_rep_t;
 #define SRC_REP_C UINT16_C
 static const int srcSigBits = 10;
 #define src_rep_t_clz __builtin_clz
 
 #else
 #error Source should be half, single, or double precision!
 #endif // end source precision
 
 #if defined DST_SINGLE
 typedef float dst_t;
 typedef uint32_t dst_rep_t;
 #define DST_REP_C UINT32_C
 static const int dstSigBits = 23;
 
 #elif defined DST_DOUBLE
 typedef double dst_t;
 typedef uint64_t dst_rep_t;
 #define DST_REP_C UINT64_C
 static const int dstSigBits = 52;
 
 #elif defined DST_QUAD
 typedef long double dst_t;
 typedef __uint128_t dst_rep_t;
 #define DST_REP_C (__uint128_t)
 static const int dstSigBits = 112;
 
 #else
 #error Destination should be single, double, or quad precision!
 #endif // end destination precision
 
 // End of specialization parameters.  Two helper routines for conversion to and
 // from the representation of floating-point data as integer values follow.
 
 static __inline src_rep_t srcToRep(src_t x) {
   const union {
     src_t f;
     src_rep_t i;
   } rep = {.f = x};
   return rep.i;
 }
 
 static __inline dst_t dstFromRep(dst_rep_t x) {
   const union {
     dst_t f;
     dst_rep_t i;
   } rep = {.i = x};
   return rep.f;
 }
 // End helper routines.  Conversion implementation follows.
 
 #endif // FP_EXTEND_HEADER

compiler-rt/lib/builtins/fp_trunc.h

 //=== lib/fp_trunc.h - high precision -> low precision conversion *- C -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //

 
 #elif defined SRC_QUAD
 typedef long double src_t;
 typedef __uint128_t src_rep_t;
 #define SRC_REP_C (__uint128_t)
 static const int srcSigBits = 112;
 
 #else
 #error Source should be double precision or quad precision!
 #endif // end source precision
 
 #if defined DST_DOUBLE
 typedef double dst_t;
 typedef uint64_t dst_rep_t;
 #define DST_REP_C UINT64_C
 static const int dstSigBits = 52;
 
 #elif defined DST_SINGLE
 typedef float dst_t;
 typedef uint32_t dst_rep_t;
 #define DST_REP_C UINT32_C
 static const int dstSigBits = 23;
 
 #elif defined DST_HALF
+#ifdef COMPILER_RT_HAS_FLOAT16
+typedef _Float16 dst_t;
+#else
 typedef uint16_t dst_t;
+#endif
 typedef uint16_t dst_rep_t;
 #define DST_REP_C UINT16_C
 static const int dstSigBits = 10;
 
 #else
 #error Destination should be single precision or double precision!
 #endif // end destination precision
 
 // End of specialization parameters.  Two helper routines for conversion to and
 // from the representation of floating-point data as integer values follow.
 
 static __inline src_rep_t srcToRep(src_t x) {
   const union {
     src_t f;
     src_rep_t i;
   } rep = {.f = x};
   return rep.i;
 }
 
 static __inline dst_t dstFromRep(dst_rep_t x) {
   const union {
     dst_t f;
     dst_rep_t i;
   } rep = {.i = x};
   return rep.f;
 }
 
 #endif // FP_TRUNC_HEADER

compiler-rt/lib/builtins/truncdfhf2.c

 //===-- lib/truncdfhf2.c - double -> half conversion --------------*- C -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #define SRC_DOUBLE
 #define DST_HALF
 #include "fp_trunc_impl.inc"
 
-COMPILER_RT_ABI uint16_t __truncdfhf2(double a) { return __truncXfYf2__(a); }
+COMPILER_RT_ABI dst_t __truncdfhf2(double a) { return __truncXfYf2__(a); }
 
 #if defined(__ARM_EABI__)
 #if defined(COMPILER_RT_ARMHF_TARGET)
-AEABI_RTABI uint16_t __aeabi_d2h(double a) { return __truncdfhf2(a); }
+AEABI_RTABI dst_t __aeabi_d2h(double a) { return __truncdfhf2(a); }
 #else
 COMPILER_RT_ALIAS(__truncdfhf2, __aeabi_d2h)
 #endif
 #endif

compiler-rt/lib/builtins/truncsfhf2.c

 //===-- lib/truncsfhf2.c - single -> half conversion --------------*- C -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #define SRC_SINGLE
 #define DST_HALF
 #include "fp_trunc_impl.inc"
 
 // Use a forwarding definition and noinline to implement a poor man's alias,
 // as there isn't a good cross-platform way of defining one.
-COMPILER_RT_ABI NOINLINE uint16_t __truncsfhf2(float a) {
+COMPILER_RT_ABI NOINLINE dst_t __truncsfhf2(float a) {
   return __truncXfYf2__(a);
 }
 
-COMPILER_RT_ABI uint16_t __gnu_f2h_ieee(float a) { return __truncsfhf2(a); }
+COMPILER_RT_ABI dst_t __gnu_f2h_ieee(float a) { return __truncsfhf2(a); }
 
 #if defined(__ARM_EABI__)
 #if defined(COMPILER_RT_ARMHF_TARGET)
-AEABI_RTABI uint16_t __aeabi_f2h(float a) { return __truncsfhf2(a); }
+AEABI_RTABI dst_t __aeabi_f2h(float a) { return __truncsfhf2(a); }
 #else
 COMPILER_RT_ALIAS(__truncsfhf2, __aeabi_f2h)
 #endif
 #endif

compiler-rt/test/builtins/CMakeLists.txt

if (${arch} STREQUAL "armhf")
     string(REPLACE ";" " " BUILTINS_TEST_TARGET_CFLAGS "${BUILTINS_TEST_TARGET_CFLAGS}")
   endif()
 
   if (${arch} STREQUAL "riscv32")
     list(APPEND BUILTINS_TEST_TARGET_CFLAGS -fforce-enable-int128)
     string(REPLACE ";" " " BUILTINS_TEST_TARGET_CFLAGS "${BUILTINS_TEST_TARGET_CFLAGS}")
   endif()
 
+  if (${arch} MATCHES "arm|aarch64|arm64" AND COMPILER_RT_HAS_FLOAT16)
+    list(APPEND BUILTINS_TEST_TARGET_CFLAGS -DCOMPILER_RT_HAS_FLOAT16)
+    string(REPLACE ";" " " BUILTINS_TEST_TARGET_CFLAGS "${BUILTINS_TEST_TARGET_CFLAGS}")
+  endif()
+
   # Compute builtins available in library and add them as lit features.
   if(APPLE)
     # TODO: Support other Apple platforms.
     set(BUILTIN_LIB_TARGET_NAME "clang_rt.builtins_${arch}_osx")
   else()
     set(BUILTIN_LIB_TARGET_NAME "clang_rt.builtins-${arch}")
   endif()
   if (NOT TARGET "${BUILTIN_LIB_TARGET_NAME}")

compiler-rt/test/builtins/Unit/extendhfsf2_test.c

 // RUN: %clang_builtins %s %librt -o %t && %run %t
 // REQUIRES: librt_has_extendhfsf2
 
 #include <stdio.h>
 
 #include "fp_test.h"
 
-float __extendhfsf2(uint16_t a);
+float __extendhfsf2(TYPE_FP16 a);
 
-int test__extendhfsf2(uint16_t a, float expected)
+int test__extendhfsf2(TYPE_FP16 a, uint32_t expected)
 {
     float x = __extendhfsf2(a);
-    int ret = compareResultH(x, expected);
+    int ret = compareResultF(x, expected);
 
     if (ret){
         printf("error in test__extendhfsf2(%#.4x) = %f, "
-               "expected %f\n", a, x, expected);
+               "expected %f\n", toRep16(a), x, fromRep32(expected));
     }
     return ret;
 }
 
-char assumption_1[sizeof(__fp16) * CHAR_BIT == 16] = {0};
+char assumption_1[sizeof(TYPE_FP16) * CHAR_BIT == 16] = {0};
 
 int main()
 {
     // qNaN
-    if (test__extendhfsf2(UINT16_C(0x7e00),
-                          makeQNaN32()))
+    if (test__extendhfsf2(fromRep16(0x7e00),
+                          UINT32_C(0x7fc00000)))
         return 1;
     // NaN
-    if (test__extendhfsf2(UINT16_C(0x7e00),
-                          makeNaN32(UINT32_C(0x8000))))
+    if (test__extendhfsf2(fromRep16(0x7f80),
+                          UINT32_C(0x7ff00000)))
         return 1;
     // inf
-    if (test__extendhfsf2(UINT16_C(0x7c00),
-                          makeInf32()))
+    if (test__extendhfsf2(fromRep16(0x7c00),
+                          UINT32_C(0x7f800000)))
         return 1;
-    if (test__extendhfsf2(UINT16_C(0xfc00),
-                          -makeInf32()))
+    // -inf
+    if (test__extendhfsf2(fromRep16(0xfc00),
+                          UINT32_C(0xff800000)))
         return 1;
     // zero
-    if (test__extendhfsf2(UINT16_C(0x0),
-                          0.0f))
+    if (test__extendhfsf2(fromRep16(0x0),
+                          UINT32_C(0x00000000)))
         return 1;
-    if (test__extendhfsf2(UINT16_C(0x8000),
-                          -0.0f))
+    // -zero
+    if (test__extendhfsf2(fromRep16(0x8000),
+                          UINT32_C(0x80000000)))
         return 1;
-
-    if (test__extendhfsf2(UINT16_C(0x4248),
-                          3.1415926535f))
-        return 1;
-    if (test__extendhfsf2(UINT16_C(0xc248),
-                          -3.1415926535f))
+    if (test__extendhfsf2(fromRep16(0x4248),
+                          UINT32_C(0x40490000)))
         return 1;
-    if (test__extendhfsf2(UINT16_C(0x7c00),
-                          0x1.987124876876324p+100f))
+    if (test__extendhfsf2(fromRep16(0xc248),
+                          UINT32_C(0xc0490000)))
         return 1;
-    if (test__extendhfsf2(UINT16_C(0x6e62),
-                          0x1.988p+12f))
+    if (test__extendhfsf2(fromRep16(0x6e62),
+                          UINT32_C(0x45cc4000)))
         return 1;
-    if (test__extendhfsf2(UINT16_C(0x3c00),
-                          0x1.0p+0f))
+    if (test__extendhfsf2(fromRep16(0x3c00),
+                          UINT32_C(0x3f800000)))
         return 1;
-    if (test__extendhfsf2(UINT16_C(0x0400),
-                          0x1.0p-14f))
+    if (test__extendhfsf2(fromRep16(0x0400),
+                          UINT32_C(0x38800000)))
         return 1;
     // denormal
-    if (test__extendhfsf2(UINT16_C(0x0010),
-                          0x1.0p-20f))
-        return 1;
-    if (test__extendhfsf2(UINT16_C(0x0001),
-                          0x1.0p-24f))
+    if (test__extendhfsf2(fromRep16(0x0010),
+                          UINT32_C(0x35800000)))
         return 1;
-    if (test__extendhfsf2(UINT16_C(0x8001),
-                          -0x1.0p-24f))
+    if (test__extendhfsf2(fromRep16(0x0001),
+                          UINT32_C(0x33800000)))
         return 1;
-    if (test__extendhfsf2(UINT16_C(0x0001),
-                          0x1.5p-25f))
+    if (test__extendhfsf2(fromRep16(0x8001),
+                          UINT32_C(0xb3800000)))
         return 1;
-    // and back to zero
-    if (test__extendhfsf2(UINT16_C(0x0000),
-                          0x1.0p-25f))
-        return 1;
-    if (test__extendhfsf2(UINT16_C(0x8000),
-                          -0x1.0p-25f))
+    if (test__extendhfsf2(fromRep16(0x0001),
+                          UINT32_C(0x33800000)))
         return 1;
     // max (precise)
-    if (test__extendhfsf2(UINT16_C(0x7bff),
-                          65504.0f))
+    if (test__extendhfsf2(fromRep16(0x7bff),
+                          UINT32_C(0x477fe000)))
         return 1;
     // max (rounded)
-    if (test__extendhfsf2(UINT16_C(0x7bff),
-                          65504.0f))
-        return 1;
-    // max (to +inf)
-    if (test__extendhfsf2(UINT16_C(0x7c00),
-                          makeInf32()))
-        return 1;
-    if (test__extendhfsf2(UINT16_C(0xfc00),
-                          -makeInf32()))
+    if (test__extendhfsf2(fromRep16(0x7bff),
+                          UINT32_C(0x477fe000)))
         return 1;
     return 0;
 }

compiler-rt/test/builtins/Unit/fp_test.h

 #include <stdlib.h>
 #include <limits.h>
 #include <string.h>
 #include <stdint.h>
 
+#ifdef COMPILER_RT_HAS_FLOAT16
+#define TYPE_FP16 _Float16
+#else
+#define TYPE_FP16 uint16_t
+#endif
+
 enum EXPECTED_RESULT {
     LESS_0, LESS_EQUAL_0, EQUAL_0, GREATER_0, GREATER_EQUAL_0, NEQUAL_0
 };
 
-static inline uint16_t fromRep16(uint16_t x)
+static inline TYPE_FP16 fromRep16(uint16_t x)
 {
+#ifdef COMPILER_RT_HAS_FLOAT16
+    TYPE_FP16 ret;
+    memcpy(&ret, &x, sizeof(ret));
+    return ret;
+#else
     return x;
+#endif
 }
 
 static inline float fromRep32(uint32_t x)
 {
     float ret;
     memcpy(&ret, &x, 4);
     return ret;
 }

 {
     __uint128_t x = ((__uint128_t)hi << 64) + lo;
     long double ret;
     memcpy(&ret, &x, 16);
     return ret;
 }
 #endif
 
-static inline uint16_t toRep16(uint16_t x)
+static inline uint16_t toRep16(TYPE_FP16 x)
 {
+#ifdef COMPILER_RT_HAS_FLOAT16
+    uint16_t ret;
+    memcpy(&ret, &x, sizeof(ret));
+    return ret;
+#else
     return x;
+#endif
 }
 
 static inline uint32_t toRep32(float x)
 {
     uint32_t ret;
     memcpy(&ret, &x, 4);
     return ret;
 }

 static inline __uint128_t toRep128(long double x)
 {
     __uint128_t ret;
     memcpy(&ret, &x, 16);
     return ret;
 }
 #endif
 
-static inline int compareResultH(uint16_t result,
+static inline int compareResultH(TYPE_FP16 result,
                                  uint16_t expected)
 {
     uint16_t rep = toRep16(result);
 
     if (rep == expected){
         return 0;
     }
     // test other possible NaN representation(signal NaN)
switch(expected){
         case GREATER_0:
             return ">0";
         default:
             return "";
     }
     return "";
 }
 
-static inline uint16_t makeQNaN16(void)
+static inline TYPE_FP16 makeQNaN16(void)
 {
     return fromRep16(0x7e00U);
 }
 
 static inline float makeQNaN32(void)
 {
     return fromRep32(0x7fc00000U);
 }
 
 static inline double makeQNaN64(void)
 {
     return fromRep64(0x7ff8000000000000UL);
 }
 
 #if __LDBL_MANT_DIG__ == 113
 static inline long double makeQNaN128(void)
 {
     return fromRep128(0x7fff800000000000UL, 0x0UL);
 }
 #endif
 
-static inline uint16_t makeNaN16(uint16_t rand)
+static inline TYPE_FP16 makeNaN16(uint16_t rand)
 {
     return fromRep16(0x7c00U | (rand & 0x7fffU));
 }
 
 static inline float makeNaN32(uint32_t rand)
 {
     return fromRep32(0x7f800000U | (rand & 0x7fffffU));
 }
 
 static inline double makeNaN64(uint64_t rand)
 {
     return fromRep64(0x7ff0000000000000UL | (rand & 0xfffffffffffffUL));
 }
 
 #if __LDBL_MANT_DIG__ == 113
 static inline long double makeNaN128(uint64_t rand)
 {
     return fromRep128(0x7fff000000000000UL | (rand & 0xffffffffffffUL), 0x0UL);
 }
 #endif
 
-static inline uint16_t makeInf16(void)
+static inline TYPE_FP16 makeInf16(void)
 {
     return fromRep16(0x7c00U);
 }
 
 static inline float makeInf32(void)
 {
     return fromRep32(0x7f800000U);
 }

compiler-rt/test/builtins/Unit/truncdfhf2_test.c

 // RUN: %clang_builtins %s %librt -o %t && %run %t
 // REQUIRES: librt_has_truncdfhf2
 
 #include <stdio.h>
 
 #include "fp_test.h"
 
-uint16_t __truncdfhf2(double a);
+TYPE_FP16 __truncdfhf2(double a);
 
 int test__truncdfhf2(double a, uint16_t expected)
 {
-    uint16_t x = __truncdfhf2(a);
+    TYPE_FP16 x = __truncdfhf2(a);
     int ret = compareResultH(x, expected);
 
     if (ret){
-        printf("error in test__truncdfhf2(%f) = %#.4x, "
-               "expected %#.4x\n", a, x, fromRep16(expected));
+        printf("error in test__truncdfhf2(%lf) = %#.4x, "
+               "expected %#.4x\n", a, toRep16(x), expected);
     }
     return ret;
 }
 
 char assumption_1[sizeof(__fp16) * CHAR_BIT == 16] = {0};
 
 int main()
 {

compiler-rt/test/builtins/Unit/truncsfhf2_test.c

 // RUN: %clang_builtins %s %librt -o %t && %run %t
 // REQUIRES: librt_has_truncsfhf2
 
 #include <stdio.h>
 
 #include "fp_test.h"
 
-uint16_t __truncsfhf2(float a);
+TYPE_FP16 __truncsfhf2(float a);
 
 int test__truncsfhf2(float a, uint16_t expected)
 {
-    uint16_t x = __truncsfhf2(a);
+    TYPE_FP16 x = __truncsfhf2(a);
     int ret = compareResultH(x, expected);
 
     if (ret){
         printf("error in test__truncsfhf2(%f) = %#.4x, "
-               "expected %#.4x\n", a, x, fromRep16(expected));
+               "expected %#.4x\n", a, toRep16(x), expected);
     }
     return ret;
 }
 
 char assumption_1[sizeof(__fp16) * CHAR_BIT == 16] = {0};
 
 int main()
 {