[X86][BF16] Add libcall for FP128 -> BF16 #115825
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-llvm-ir Author: Feng Zou (fzou1) ChangesThis is to fix #115710. Full diff: https://github.com/llvm/llvm-project/pull/115825.diff 5 Files Affected:
diff --git a/compiler-rt/lib/builtins/CMakeLists.txt b/compiler-rt/lib/builtins/CMakeLists.txt
index 9a0a50ee7003f1..c8595b97b337db 100644
--- a/compiler-rt/lib/builtins/CMakeLists.txt
+++ b/compiler-rt/lib/builtins/CMakeLists.txt
@@ -194,6 +194,7 @@ set(BF16_SOURCES
truncdfbf2.c
truncxfbf2.c
truncsfbf2.c
+ trunctfbf2.c
)
set(GENERIC_TF_SOURCES
diff --git a/compiler-rt/lib/builtins/trunctfbf2.c b/compiler-rt/lib/builtins/trunctfbf2.c
new file mode 100644
index 00000000000000..3d47b13bdf5c2c
--- /dev/null
+++ b/compiler-rt/lib/builtins/trunctfbf2.c
@@ -0,0 +1,18 @@
+//===--------- lib/trunctfbf2.c - quad -> bfloat 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 QUAD_PRECISION
+#include "fp_lib.h"
+
+#if defined(CRT_HAS_TF_MODE) && defined(__x86_64__)
+#define SRC_QUAD
+#define DST_BFLOAT
+#include "fp_trunc_impl.inc"
+
+COMPILER_RT_ABI dst_t __trunctfbf2(src_t a) { return __truncXfYf2__(a); }
+
+#endif
\ No newline at end of file
diff --git a/llvm/include/llvm/IR/RuntimeLibcalls.def b/llvm/include/llvm/IR/RuntimeLibcalls.def
index 9c56cf098ff774..13a27b58b9cd78 100644
--- a/llvm/include/llvm/IR/RuntimeLibcalls.def
+++ b/llvm/include/llvm/IR/RuntimeLibcalls.def
@@ -383,6 +383,7 @@ HANDLE_LIBCALL(FPROUND_PPCF128_F16, "__trunctfhf2")
HANDLE_LIBCALL(FPROUND_F32_BF16, "__truncsfbf2")
HANDLE_LIBCALL(FPROUND_F64_BF16, "__truncdfbf2")
HANDLE_LIBCALL(FPROUND_F80_BF16, "__truncxfbf2")
+HANDLE_LIBCALL(FPROUND_F128_BF16, "__trunctfbf2")
HANDLE_LIBCALL(FPROUND_F64_F32, "__truncdfsf2")
HANDLE_LIBCALL(FPROUND_F80_F32, "__truncxfsf2")
HANDLE_LIBCALL(FPROUND_F128_F32, "__trunctfsf2")
diff --git a/llvm/lib/CodeGen/TargetLoweringBase.cpp b/llvm/lib/CodeGen/TargetLoweringBase.cpp
index 231de6bba5e5b8..392cfbdd21273d 100644
--- a/llvm/lib/CodeGen/TargetLoweringBase.cpp
+++ b/llvm/lib/CodeGen/TargetLoweringBase.cpp
@@ -171,6 +171,8 @@ RTLIB::Libcall RTLIB::getFPROUND(EVT OpVT, EVT RetVT) {
return FPROUND_F64_BF16;
if (OpVT == MVT::f80)
return FPROUND_F80_BF16;
+ if (OpVT == MVT::f128)
+ return FPROUND_F128_BF16;
} else if (RetVT == MVT::f32) {
if (OpVT == MVT::f64)
return FPROUND_F64_F32;
diff --git a/llvm/test/CodeGen/X86/bfloat.ll b/llvm/test/CodeGen/X86/bfloat.ll
index 3144fd56d9ccf3..27348dd31958f2 100644
--- a/llvm/test/CodeGen/X86/bfloat.ll
+++ b/llvm/test/CodeGen/X86/bfloat.ll
@@ -1975,3 +1975,25 @@ define bfloat @PR108936(x86_fp80 %0) nounwind {
%2 = fptrunc x86_fp80 %0 to bfloat
ret bfloat %2
}
+
+define bfloat @PR115710(fp128 %0) nounwind {
+; X86-LABEL: PR115710:
+; X86: # %bb.0:
+; X86-NEXT: subl $28, %esp
+; X86-NEXT: vmovaps {{[0-9]+}}(%esp), %xmm0
+; X86-NEXT: vmovups %xmm0, (%esp)
+; X86-NEXT: calll __trunctfbf2
+; X86-NEXT: # kill: def $ax killed $ax def $eax
+; X86-NEXT: vmovw %eax, %xmm0
+; X86-NEXT: addl $28, %esp
+; X86-NEXT: retl
+;
+; CHECK-LABEL: PR115710:
+; CHECK: # %bb.0:
+; CHECK-NEXT: pushq %rax
+; CHECK-NEXT: callq __trunctfbf2@PLT
+; CHECK-NEXT: popq %rax
+; CHECK-NEXT: retq
+ %2 = fptrunc fp128 %0 to bfloat
+ ret bfloat %2
+}
|
|
@llvm/pr-subscribers-backend-x86 Author: Feng Zou (fzou1) ChangesThis is to fix #115710. Full diff: https://github.com/llvm/llvm-project/pull/115825.diff 5 Files Affected:
diff --git a/compiler-rt/lib/builtins/CMakeLists.txt b/compiler-rt/lib/builtins/CMakeLists.txt
index 9a0a50ee7003f1..c8595b97b337db 100644
--- a/compiler-rt/lib/builtins/CMakeLists.txt
+++ b/compiler-rt/lib/builtins/CMakeLists.txt
@@ -194,6 +194,7 @@ set(BF16_SOURCES
truncdfbf2.c
truncxfbf2.c
truncsfbf2.c
+ trunctfbf2.c
)
set(GENERIC_TF_SOURCES
diff --git a/compiler-rt/lib/builtins/trunctfbf2.c b/compiler-rt/lib/builtins/trunctfbf2.c
new file mode 100644
index 00000000000000..3d47b13bdf5c2c
--- /dev/null
+++ b/compiler-rt/lib/builtins/trunctfbf2.c
@@ -0,0 +1,18 @@
+//===--------- lib/trunctfbf2.c - quad -> bfloat 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 QUAD_PRECISION
+#include "fp_lib.h"
+
+#if defined(CRT_HAS_TF_MODE) && defined(__x86_64__)
+#define SRC_QUAD
+#define DST_BFLOAT
+#include "fp_trunc_impl.inc"
+
+COMPILER_RT_ABI dst_t __trunctfbf2(src_t a) { return __truncXfYf2__(a); }
+
+#endif
\ No newline at end of file
diff --git a/llvm/include/llvm/IR/RuntimeLibcalls.def b/llvm/include/llvm/IR/RuntimeLibcalls.def
index 9c56cf098ff774..13a27b58b9cd78 100644
--- a/llvm/include/llvm/IR/RuntimeLibcalls.def
+++ b/llvm/include/llvm/IR/RuntimeLibcalls.def
@@ -383,6 +383,7 @@ HANDLE_LIBCALL(FPROUND_PPCF128_F16, "__trunctfhf2")
HANDLE_LIBCALL(FPROUND_F32_BF16, "__truncsfbf2")
HANDLE_LIBCALL(FPROUND_F64_BF16, "__truncdfbf2")
HANDLE_LIBCALL(FPROUND_F80_BF16, "__truncxfbf2")
+HANDLE_LIBCALL(FPROUND_F128_BF16, "__trunctfbf2")
HANDLE_LIBCALL(FPROUND_F64_F32, "__truncdfsf2")
HANDLE_LIBCALL(FPROUND_F80_F32, "__truncxfsf2")
HANDLE_LIBCALL(FPROUND_F128_F32, "__trunctfsf2")
diff --git a/llvm/lib/CodeGen/TargetLoweringBase.cpp b/llvm/lib/CodeGen/TargetLoweringBase.cpp
index 231de6bba5e5b8..392cfbdd21273d 100644
--- a/llvm/lib/CodeGen/TargetLoweringBase.cpp
+++ b/llvm/lib/CodeGen/TargetLoweringBase.cpp
@@ -171,6 +171,8 @@ RTLIB::Libcall RTLIB::getFPROUND(EVT OpVT, EVT RetVT) {
return FPROUND_F64_BF16;
if (OpVT == MVT::f80)
return FPROUND_F80_BF16;
+ if (OpVT == MVT::f128)
+ return FPROUND_F128_BF16;
} else if (RetVT == MVT::f32) {
if (OpVT == MVT::f64)
return FPROUND_F64_F32;
diff --git a/llvm/test/CodeGen/X86/bfloat.ll b/llvm/test/CodeGen/X86/bfloat.ll
index 3144fd56d9ccf3..27348dd31958f2 100644
--- a/llvm/test/CodeGen/X86/bfloat.ll
+++ b/llvm/test/CodeGen/X86/bfloat.ll
@@ -1975,3 +1975,25 @@ define bfloat @PR108936(x86_fp80 %0) nounwind {
%2 = fptrunc x86_fp80 %0 to bfloat
ret bfloat %2
}
+
+define bfloat @PR115710(fp128 %0) nounwind {
+; X86-LABEL: PR115710:
+; X86: # %bb.0:
+; X86-NEXT: subl $28, %esp
+; X86-NEXT: vmovaps {{[0-9]+}}(%esp), %xmm0
+; X86-NEXT: vmovups %xmm0, (%esp)
+; X86-NEXT: calll __trunctfbf2
+; X86-NEXT: # kill: def $ax killed $ax def $eax
+; X86-NEXT: vmovw %eax, %xmm0
+; X86-NEXT: addl $28, %esp
+; X86-NEXT: retl
+;
+; CHECK-LABEL: PR115710:
+; CHECK: # %bb.0:
+; CHECK-NEXT: pushq %rax
+; CHECK-NEXT: callq __trunctfbf2@PLT
+; CHECK-NEXT: popq %rax
+; CHECK-NEXT: retq
+ %2 = fptrunc fp128 %0 to bfloat
+ ret bfloat %2
+}
|
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/92/builds/9549 Here is the relevant piece of the build log for the reference |
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/64/builds/1434 Here is the relevant piece of the build log for the reference |
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/24/builds/2621 Here is the relevant piece of the build log for the reference |
Groverkss
pushed a commit
to iree-org/llvm-project
that referenced
this pull request
Nov 15, 2024
topperc
reviewed
Dec 11, 2024
| ; X86-NEXT: subl $28, %esp | ||
| ; X86-NEXT: vmovaps {{[0-9]+}}(%esp), %xmm0 | ||
| ; X86-NEXT: vmovups %xmm0, (%esp) | ||
| ; X86-NEXT: calll __trunctfbf2 |
There was a problem hiding this comment.
The result from __trunctfbf2 should be in xmm0 not eax right?
There was a problem hiding this comment.
Right. I didn't notice the problem..
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is to fix #115710.