[llvm-branch-commits] [compiler-rt] c288715 - [compiler-rt] [builtins] Use _Float16 on extendhfsf2, truncdfhf2 __truncsfhf2 if available
Adhemerval Zanella via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Thu Dec 3 11:15:06 PST 2020
Author: Adhemerval Zanella
Date: 2020-12-03T16:08:55-03:00
New Revision: c288715e952fe0e179d645a76b0f518e2403a42b
URL: https://github.com/llvm/llvm-project/commit/c288715e952fe0e179d645a76b0f518e2403a42b
DIFF: https://github.com/llvm/llvm-project/commit/c288715e952fe0e179d645a76b0f518e2403a42b.diff
LOG: [compiler-rt] [builtins] Use _Float16 on extendhfsf2, truncdfhf2 __truncsfhf2 if available
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
Reviewed By: MaskRay
Differential Revision: https://reviews.llvm.org/D92241
Added:
Modified:
compiler-rt/cmake/builtin-config-ix.cmake
compiler-rt/lib/builtins/CMakeLists.txt
compiler-rt/lib/builtins/extendhfsf2.c
compiler-rt/lib/builtins/fp_extend.h
compiler-rt/lib/builtins/fp_trunc.h
compiler-rt/lib/builtins/truncdfhf2.c
compiler-rt/lib/builtins/truncsfhf2.c
compiler-rt/test/builtins/CMakeLists.txt
compiler-rt/test/builtins/Unit/extendhfsf2_test.c
compiler-rt/test/builtins/Unit/fp_test.h
compiler-rt/test/builtins/Unit/truncdfhf2_test.c
compiler-rt/test/builtins/Unit/truncsfhf2_test.c
Removed:
################################################################################
diff --git a/compiler-rt/cmake/builtin-config-ix.cmake b/compiler-rt/cmake/builtin-config-ix.cmake
index 2eeedd49e392..ad3b98799c5c 100644
--- a/compiler-rt/cmake/builtin-config-ix.cmake
+++ b/compiler-rt/cmake/builtin-config-ix.cmake
@@ -22,6 +22,13 @@ int foo(int x, int y) {
}
")
+builtin_check_c_compiler_source(COMPILER_RT_HAS_FLOAT16
+"
+_Float16 foo(_Float16 x) {
+ return x;
+}
+"
+)
builtin_check_c_compiler_source(COMPILER_RT_HAS_ASM_LSE
"
diff --git a/compiler-rt/lib/builtins/CMakeLists.txt b/compiler-rt/lib/builtins/CMakeLists.txt
index 7f3df6ff548d..f7a9b233d7c7 100644
--- a/compiler-rt/lib/builtins/CMakeLists.txt
+++ b/compiler-rt/lib/builtins/CMakeLists.txt
@@ -658,6 +658,8 @@ if (APPLE)
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
diff --git a/compiler-rt/lib/builtins/extendhfsf2.c b/compiler-rt/lib/builtins/extendhfsf2.c
index 7c1a76eb5851..0159ab09d3eb 100644
--- a/compiler-rt/lib/builtins/extendhfsf2.c
+++ b/compiler-rt/lib/builtins/extendhfsf2.c
@@ -12,15 +12,15 @@
// 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
diff --git a/compiler-rt/lib/builtins/fp_extend.h b/compiler-rt/lib/builtins/fp_extend.h
index fb512672e35e..aad4436730dd 100644
--- a/compiler-rt/lib/builtins/fp_extend.h
+++ b/compiler-rt/lib/builtins/fp_extend.h
@@ -40,7 +40,11 @@ static __inline int src_rep_t_clz(src_rep_t a) {
}
#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;
diff --git a/compiler-rt/lib/builtins/fp_trunc.h b/compiler-rt/lib/builtins/fp_trunc.h
index aca4c9b6e677..00595edd5e01 100644
--- a/compiler-rt/lib/builtins/fp_trunc.h
+++ b/compiler-rt/lib/builtins/fp_trunc.h
@@ -50,7 +50,11 @@ typedef uint32_t dst_rep_t;
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;
diff --git a/compiler-rt/lib/builtins/truncdfhf2.c b/compiler-rt/lib/builtins/truncdfhf2.c
index 90c418a4387f..24c6e62f715f 100644
--- a/compiler-rt/lib/builtins/truncdfhf2.c
+++ b/compiler-rt/lib/builtins/truncdfhf2.c
@@ -10,11 +10,11 @@
#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
diff --git a/compiler-rt/lib/builtins/truncsfhf2.c b/compiler-rt/lib/builtins/truncsfhf2.c
index 1f17194c38e5..379e7cb6f784 100644
--- a/compiler-rt/lib/builtins/truncsfhf2.c
+++ b/compiler-rt/lib/builtins/truncsfhf2.c
@@ -12,15 +12,15 @@
// 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
diff --git a/compiler-rt/test/builtins/CMakeLists.txt b/compiler-rt/test/builtins/CMakeLists.txt
index e3796f840a64..31d16312dd18 100644
--- a/compiler-rt/test/builtins/CMakeLists.txt
+++ b/compiler-rt/test/builtins/CMakeLists.txt
@@ -44,6 +44,11 @@ foreach(arch ${BUILTIN_TEST_ARCH})
string(REPLACE ";" " " BUILTINS_TEST_TARGET_CFLAGS "${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.
diff --git a/compiler-rt/test/builtins/Unit/extendhfsf2_test.c b/compiler-rt/test/builtins/Unit/extendhfsf2_test.c
index 9a5258b2b46f..86150e8fb0d7 100644
--- a/compiler-rt/test/builtins/Unit/extendhfsf2_test.c
+++ b/compiler-rt/test/builtins/Unit/extendhfsf2_test.c
@@ -5,99 +5,83 @@
#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;
}
diff --git a/compiler-rt/test/builtins/Unit/fp_test.h b/compiler-rt/test/builtins/Unit/fp_test.h
index 59d4ae5cf9db..7c5d5111f4e7 100644
--- a/compiler-rt/test/builtins/Unit/fp_test.h
+++ b/compiler-rt/test/builtins/Unit/fp_test.h
@@ -3,13 +3,25 @@
#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)
@@ -36,9 +48,15 @@ static inline long double fromRep128(uint64_t hi, uint64_t lo)
}
#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)
@@ -64,7 +82,7 @@ static inline __uint128_t toRep128(long double x)
}
#endif
-static inline int compareResultH(uint16_t result,
+static inline int compareResultH(TYPE_FP16 result,
uint16_t expected)
{
uint16_t rep = toRep16(result);
@@ -199,7 +217,7 @@ static inline char *expectedStr(enum EXPECTED_RESULT expected)
return "";
}
-static inline uint16_t makeQNaN16(void)
+static inline TYPE_FP16 makeQNaN16(void)
{
return fromRep16(0x7e00U);
}
@@ -221,7 +239,7 @@ static inline long double makeQNaN128(void)
}
#endif
-static inline uint16_t makeNaN16(uint16_t rand)
+static inline TYPE_FP16 makeNaN16(uint16_t rand)
{
return fromRep16(0x7c00U | (rand & 0x7fffU));
}
@@ -243,7 +261,7 @@ static inline long double makeNaN128(uint64_t rand)
}
#endif
-static inline uint16_t makeInf16(void)
+static inline TYPE_FP16 makeInf16(void)
{
return fromRep16(0x7c00U);
}
diff --git a/compiler-rt/test/builtins/Unit/truncdfhf2_test.c b/compiler-rt/test/builtins/Unit/truncdfhf2_test.c
index 74e975eef60b..1990ec9503a7 100644
--- a/compiler-rt/test/builtins/Unit/truncdfhf2_test.c
+++ b/compiler-rt/test/builtins/Unit/truncdfhf2_test.c
@@ -5,16 +5,16 @@
#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;
}
diff --git a/compiler-rt/test/builtins/Unit/truncsfhf2_test.c b/compiler-rt/test/builtins/Unit/truncsfhf2_test.c
index 7fcccf1a4e69..c7c8063d5218 100644
--- a/compiler-rt/test/builtins/Unit/truncsfhf2_test.c
+++ b/compiler-rt/test/builtins/Unit/truncsfhf2_test.c
@@ -5,16 +5,16 @@
#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;
}
More information about the llvm-branch-commits
mailing list