[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).

[ostannard]

LGTM

[wolfgangp]

Isn't COMPILER_RT_HAS_FLOAT16 generated using the host compiler? If so, using the same flag for a compiler_rt test could fail if the host compiler supports f16 and the target compiler does not.

[aeubanks]

This seems to have broken some tests on our Mac bots:
https://logs.chromium.org/logs/chromium/buildbucket/cr-buildbucket.appspot.com/8863040226745741728/+/steps/package_clang/0/stdout

FAIL: Builtins-x86_64-darwin :: truncsfhf2_test.c (195 of 208)
******************** TEST 'Builtins-x86_64-darwin :: truncsfhf2_test.c' FAILED ********************
Script:
--
: 'RUN: at line 1';       /opt/s/w/ir/cache/builder/src/third_party/llvm-bootstrap/./bin/clang   -gline-tables-only  -arch x86_64 -stdlib=libc++ -mmacosx-version-min=10.10 -isysroot /opt/s/w/ir/cache/osx_sdk/XCode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX10.15.sdk -DCOMPILER_RT_HAS_FLOAT16  -fno-builtin -I /opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/lib/builtins -nodefaultlibs /opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/truncsfhf2_test.c /opt/s/w/ir/cache/builder/src/third_party/llvm-bootstrap/./lib/clang/12.0.0/lib/darwin/libclang_rt.osx.a  -lSystem -o /opt/s/w/ir/cache/builder/src/third_party/llvm-bootstrap/projects/compiler-rt/test/builtins/Unit/X86_64DarwinConfig/Output/truncsfhf2_test.c.tmp &&  /opt/s/w/ir/cache/builder/src/third_party/llvm-bootstrap/projects/compiler-rt/test/builtins/Unit/X86_64DarwinConfig/Output/truncsfhf2_test.c.tmp
--
Exit Code: 1

Command Output (stderr):
--
In file included from /opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/truncsfhf2_test.c:6:
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:16:15: error: _Float16 is not supported on this target
static inline TYPE_FP16 fromRep16(uint16_t x)
              ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:7:19: note: expanded from macro 'TYPE_FP16'
#define TYPE_FP16 _Float16
                  ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:19:5: error: _Float16 is not supported on this target
    TYPE_FP16 ret;
    ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:7:19: note: expanded from macro 'TYPE_FP16'
#define TYPE_FP16 _Float16
                  ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:51:32: error: _Float16 is not supported on this target
static inline uint16_t toRep16(TYPE_FP16 x)
                               ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:7:19: note: expanded from macro 'TYPE_FP16'
#define TYPE_FP16 _Float16
                  ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:85:34: error: _Float16 is not supported on this target
static inline int compareResultH(TYPE_FP16 result,
                                 ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:7:19: note: expanded from macro 'TYPE_FP16'
#define TYPE_FP16 _Float16
                  ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:220:15: error: _Float16 is not supported on this target
static inline TYPE_FP16 makeQNaN16(void)
              ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:7:19: note: expanded from macro 'TYPE_FP16'
#define TYPE_FP16 _Float16
                  ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:242:15: error: _Float16 is not supported on this target
static inline TYPE_FP16 makeNaN16(uint16_t rand)
              ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:7:19: note: expanded from macro 'TYPE_FP16'
#define TYPE_FP16 _Float16
                  ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:264:15: error: _Float16 is not supported on this target
static inline TYPE_FP16 makeInf16(void)
              ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:7:19: note: expanded from macro 'TYPE_FP16'
#define TYPE_FP16 _Float16
                  ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/truncsfhf2_test.c:8:1: error: _Float16 is not supported on this target
TYPE_FP16 __truncsfhf2(float a);
^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:7:19: note: expanded from macro 'TYPE_FP16'
#define TYPE_FP16 _Float16
                  ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/truncsfhf2_test.c:12:5: error: _Float16 is not supported on this target
    TYPE_FP16 x = __truncsfhf2(a);
    ^
/opt/s/w/ir/cache/builder/src/third_party/llvm/compiler-rt/test/builtins/Unit/fp_test.h:7:19: note: expanded from macro 'TYPE_FP16'
#define TYPE_FP16 _Float16
                  ^
9 errors generated.

[zatrazz]

In D91733#2407055, @wolfgangp wrote:

Isn't COMPILER_RT_HAS_FLOAT16 generated using the host compiler? If so, using the same flag for a compiler_rt test could fail if the host compiler supports f16 and the target compiler does not.

Indeed and it seems to be for mac. I will work on a fix, sorry for take to long to notice the issue.

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

#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

compiler-rt/lib/builtins/fp_trunc.h

 
 #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
 

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

foreach(arch ${BUILTIN_TEST_ARCH})
   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()
 
   append_list_if(COMPILER_RT_HAS_FLOAT16 -DCOMPILER_RT_HAS_FLOAT16 BUILTINS_TEST_TARGET_CFLAGS)
+  string(REPLACE ";" " " BUILTINS_TEST_TARGET_CFLAGS "${BUILTINS_TEST_TARGET_CFLAGS}")
 
   # 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()

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/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()
 {