[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-30 Thread Phoebe Wang via Phabricator via cfe-commits 
This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGabeeae570eff: [X86] Support `_Float16` on SSE2 and up 
(authored by pengfei).

Changed prior to commit:
  https://reviews.llvm.org/D128571?vs=441272=441315#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

Files:
  clang/docs/LanguageExtensions.rst
  clang/docs/ReleaseNotes.rst
  clang/lib/Basic/Targets/X86.cpp
  clang/test/CodeGen/X86/Float16-arithmetic.c
  clang/test/CodeGen/X86/Float16-complex.c
  clang/test/CodeGen/X86/avx512fp16-complex.c
  clang/test/Sema/Float16.c
  clang/test/Sema/conversion-target-dep.c
  clang/test/SemaCXX/Float16.cpp
  compiler-rt/test/builtins/CMakeLists.txt

Index: compiler-rt/test/builtins/CMakeLists.txt
===
--- compiler-rt/test/builtins/CMakeLists.txt
+++ compiler-rt/test/builtins/CMakeLists.txt
@@ -44,9 +44,17 @@
 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}")
+  if(APPLE)
+# TODO: Support the new ABI on Apple platforms.
+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()
+  else()
+if (${arch} MATCHES "arm|aarch64|arm64|i?86|x86_64|AMD64" AND COMPILER_RT_HAS_FLOAT16)
+  list(APPEND BUILTINS_TEST_TARGET_CFLAGS -DCOMPILER_RT_HAS_FLOAT16)
+  string(REPLACE ";" " " BUILTINS_TEST_TARGET_CFLAGS "${BUILTINS_TEST_TARGET_CFLAGS}")
+endif()
   endif()
 
   if(COMPILER_RT_ENABLE_CET)
Index: clang/test/SemaCXX/Float16.cpp
===
--- clang/test/SemaCXX/Float16.cpp
+++ clang/test/SemaCXX/Float16.cpp
@@ -1,4 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/Sema/conversion-target-dep.c
===
--- clang/test/Sema/conversion-target-dep.c
+++ clang/test/Sema/conversion-target-dep.c
@@ -6,7 +6,7 @@
 
 long double ld;
 double d;
-_Float16 f16; // x86-error {{_Float16 is not supported on this target}}
+_Float16 f16;
 
 int main(void) {
   ld = d; // x86-warning {{implicit conversion increases floating-point precision: 'double' to 'long double'}}
Index: clang/test/Sema/Float16.c
===
--- clang/test/Sema/Float16.c
+++ clang/test/Sema/Float16.c
@@ -1,5 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc -target-feature +avx512fp16 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/CodeGen/X86/Float16-complex.c
===
--- clang/test/CodeGen/X86/Float16-complex.c
+++ clang/test/CodeGen/X86/Float16-complex.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -target-feature +avx512fp16 -o - | FileCheck %s --check-prefix=X86
+// RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -o - | FileCheck %s --check-prefix=X86
 
 _Float16 _Complex add_half_rr(_Float16 a, _Float16 b) {
   // X86-LABEL: @add_half_rr(
Index: clang/test/CodeGen/X86/Float16-arithmetic.c
===
--- /dev/null
+++ clang/test/CodeGen/X86/Float16-arithmetic.c
@@ -0,0 +1,112 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm -o - %s | FileCheck %s
+
+

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-30 Thread Phoebe Wang via Phabricator via cfe-commits 
pengfei added inline comments.



Comment at: clang/lib/Basic/Targets/X86.cpp:357
 
+// Turn on _float16 for x86 (feature sse2)
+HasFloat16 = SSELevel >= SSE2;

MaskRay wrote:
> MaskRay wrote:
> > `_Float16`
> > 
> > `for x86` convey no extra information since this file is for x86.
> Thinking again: The comment just repeats what the code does. So it can be 
> deleted.
Yeah, I had the same feeling when updating. Will delete, thanks! :)


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-30 Thread Fangrui Song via Phabricator via cfe-commits 
MaskRay accepted this revision.
MaskRay added inline comments.
This revision is now accepted and ready to land.



Comment at: clang/lib/Basic/Targets/X86.cpp:357
 
+// Turn on _float16 for x86 (feature sse2)
+HasFloat16 = SSELevel >= SSE2;

MaskRay wrote:
> `_Float16`
> 
> `for x86` convey no extra information since this file is for x86.
Thinking again: The comment just repeats what the code does. So it can be 
deleted.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-30 Thread Phoebe Wang via Phabricator via cfe-commits 
pengfei updated this revision to Diff 441272.
pengfei added a comment.

Address review comments. Thanks @MaskRay !


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

Files:
  clang/docs/LanguageExtensions.rst
  clang/docs/ReleaseNotes.rst
  clang/lib/Basic/Targets/X86.cpp
  clang/test/CodeGen/X86/Float16-arithmetic.c
  clang/test/CodeGen/X86/Float16-complex.c
  clang/test/CodeGen/X86/avx512fp16-complex.c
  clang/test/Sema/Float16.c
  clang/test/Sema/conversion-target-dep.c
  clang/test/SemaCXX/Float16.cpp
  compiler-rt/test/builtins/CMakeLists.txt

Index: compiler-rt/test/builtins/CMakeLists.txt
===
--- compiler-rt/test/builtins/CMakeLists.txt
+++ compiler-rt/test/builtins/CMakeLists.txt
@@ -44,9 +44,17 @@
 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}")
+  if(APPLE)
+# TODO: Support the new ABI on Apple platforms.
+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()
+  else()
+if (${arch} MATCHES "arm|aarch64|arm64|i?86|x86_64|AMD64" AND COMPILER_RT_HAS_FLOAT16)
+  list(APPEND BUILTINS_TEST_TARGET_CFLAGS -DCOMPILER_RT_HAS_FLOAT16)
+  string(REPLACE ";" " " BUILTINS_TEST_TARGET_CFLAGS "${BUILTINS_TEST_TARGET_CFLAGS}")
+endif()
   endif()
 
   if(COMPILER_RT_ENABLE_CET)
Index: clang/test/SemaCXX/Float16.cpp
===
--- clang/test/SemaCXX/Float16.cpp
+++ clang/test/SemaCXX/Float16.cpp
@@ -1,4 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/Sema/conversion-target-dep.c
===
--- clang/test/Sema/conversion-target-dep.c
+++ clang/test/Sema/conversion-target-dep.c
@@ -6,7 +6,7 @@
 
 long double ld;
 double d;
-_Float16 f16; // x86-error {{_Float16 is not supported on this target}}
+_Float16 f16;
 
 int main(void) {
   ld = d; // x86-warning {{implicit conversion increases floating-point precision: 'double' to 'long double'}}
Index: clang/test/Sema/Float16.c
===
--- clang/test/Sema/Float16.c
+++ clang/test/Sema/Float16.c
@@ -1,5 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc -target-feature +avx512fp16 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/CodeGen/X86/Float16-complex.c
===
--- clang/test/CodeGen/X86/Float16-complex.c
+++ clang/test/CodeGen/X86/Float16-complex.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -target-feature +avx512fp16 -o - | FileCheck %s --check-prefix=X86
+// RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -o - | FileCheck %s --check-prefix=X86
 
 _Float16 _Complex add_half_rr(_Float16 a, _Float16 b) {
   // X86-LABEL: @add_half_rr(
Index: clang/test/CodeGen/X86/Float16-arithmetic.c
===
--- /dev/null
+++ clang/test/CodeGen/X86/Float16-arithmetic.c
@@ -0,0 +1,112 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm -o - %s | FileCheck %s
+
+
+// CHECK-LABEL: @add1(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:[[A_ADDR:%.*]] = alloca half, align 2
+// CHECK-NEXT:[[B_ADDR:%.*]] = alloca half, align 2
+// CHECK-NEXT:store half

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-30 Thread Fangrui Song via Phabricator via cfe-commits 
MaskRay added inline comments.



Comment at: clang/lib/Basic/Targets/X86.cpp:357
 
+// Turn on _float16 for x86 (feature sse2)
+HasFloat16 = SSELevel >= SSE2;

`_Float16`

`for x86` convey no extra information since this file is for x86.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-29 Thread Fangrui Song via Phabricator via cfe-commits 
MaskRay requested changes to this revision.
MaskRay added inline comments.
This revision now requires changes to proceed.
Herald added a subscriber: StephenFan.



Comment at: clang/test/CodeGen/X86/Float16-arithmetic.c:1
+// RUN: %clang_cc1 -triple  x86_64-unknown-unknown \
+// RUN: -emit-llvm -o - %s  | FileCheck %s --check-prefixes=CHECK

Use one line for RUN. This isn't long. Delete excess spaces.

`x86_64-unknown-unknown` can be simplified as `x86_64`



Comment at: clang/test/CodeGen/X86/Float16-arithmetic.c:2
+// RUN: %clang_cc1 -triple  x86_64-unknown-unknown \
+// RUN: -emit-llvm -o - %s  | FileCheck %s --check-prefixes=CHECK
+

Delete `--check-prefixes=CHECK`. This is the default.



Comment at: clang/test/CodeGen/X86/Float16-arithmetic.c:4
+
+// CHECK-NOT: fpext
+// CHECK-NOT: fptrunc

The test only has negative patterns. Such a test is prone to be stale without 
being noticed.

Add some positive CHECK lines.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-29 Thread Phoebe Wang via Phabricator via cfe-commits 
pengfei updated this revision to Diff 441236.
pengfei added a comment.

Exclude the ABI change on Darwin platform. Will enable it by a followup.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

Files:
  clang/docs/LanguageExtensions.rst
  clang/docs/ReleaseNotes.rst
  clang/lib/Basic/Targets/X86.cpp
  clang/test/CodeGen/X86/Float16-arithmetic.c
  clang/test/CodeGen/X86/Float16-complex.c
  clang/test/CodeGen/X86/avx512fp16-complex.c
  clang/test/Sema/Float16.c
  clang/test/Sema/conversion-target-dep.c
  clang/test/SemaCXX/Float16.cpp
  compiler-rt/test/builtins/CMakeLists.txt

Index: compiler-rt/test/builtins/CMakeLists.txt
===
--- compiler-rt/test/builtins/CMakeLists.txt
+++ compiler-rt/test/builtins/CMakeLists.txt
@@ -44,9 +44,17 @@
 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}")
+  if(APPLE)
+# TODO: Support the new ABI on Apple platforms.
+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()
+  else()
+if (${arch} MATCHES "arm|aarch64|arm64|i?86|x86_64|AMD64" AND COMPILER_RT_HAS_FLOAT16)
+  list(APPEND BUILTINS_TEST_TARGET_CFLAGS -DCOMPILER_RT_HAS_FLOAT16)
+  string(REPLACE ";" " " BUILTINS_TEST_TARGET_CFLAGS "${BUILTINS_TEST_TARGET_CFLAGS}")
+endif()
   endif()
 
   if(COMPILER_RT_ENABLE_CET)
Index: clang/test/SemaCXX/Float16.cpp
===
--- clang/test/SemaCXX/Float16.cpp
+++ clang/test/SemaCXX/Float16.cpp
@@ -1,4 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/Sema/conversion-target-dep.c
===
--- clang/test/Sema/conversion-target-dep.c
+++ clang/test/Sema/conversion-target-dep.c
@@ -6,7 +6,7 @@
 
 long double ld;
 double d;
-_Float16 f16; // x86-error {{_Float16 is not supported on this target}}
+_Float16 f16;
 
 int main(void) {
   ld = d; // x86-warning {{implicit conversion increases floating-point precision: 'double' to 'long double'}}
Index: clang/test/Sema/Float16.c
===
--- clang/test/Sema/Float16.c
+++ clang/test/Sema/Float16.c
@@ -1,5 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc -target-feature +avx512fp16 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/CodeGen/X86/Float16-complex.c
===
--- clang/test/CodeGen/X86/Float16-complex.c
+++ clang/test/CodeGen/X86/Float16-complex.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -target-feature +avx512fp16 -o - | FileCheck %s --check-prefix=X86
+// RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -o - | FileCheck %s --check-prefix=X86
 
 _Float16 _Complex add_half_rr(_Float16 a, _Float16 b) {
   // X86-LABEL: @add_half_rr(
Index: clang/test/CodeGen/X86/Float16-arithmetic.c
===
--- /dev/null
+++ clang/test/CodeGen/X86/Float16-arithmetic.c
@@ -0,0 +1,29 @@
+// RUN: %clang_cc1 -triple  x86_64-unknown-unknown \
+// RUN: -emit-llvm -o - %s  | FileCheck %s --check-prefixes=CHECK
+
+// CHECK-NOT: fpext
+// CHECK-NOT: fptrunc
+
+_Float16 add1(_Float16 a, _Float16 b) {
+  return a + b;
+}
+
+_Float16 add2(_Float16 a, _Float16 b, _Float16 c) {
+  return a + b + c;
+}
+
+_Float16 div(_Float16

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-29 Thread Phoebe Wang via Phabricator via cfe-commits 
pengfei added a comment.

In D128571#3619438 , @pengfei wrote:

> In D128571#3619265 , @alexfh wrote:
>
>> @pengfei could you fix the Darwin tests as well? And a general comment 
>> regarding the ongoing `_Float16` effort: I think that this change should 
>> have been a part of https://reviews.llvm.org/D107082 to make it possible to 
>> build a consistently working toolchain. Thus, if this commit can't be landed 
>> in a reasonable time, I'd suggest reverting https://reviews.llvm.org/D107082.
>
> @alexfh I'm working on that. I'm asking suggestion on solving it in a better 
> way, but at least we can disable the test for Darwin (maybe just for stage1 
> if possible) since it's expected due to the ABI change.

Disabled these tests for Darwin. I'll reland the patch in one day if no 
objections.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-29 Thread Phoebe Wang via Phabricator via cfe-commits 
pengfei updated this revision to Diff 441222.
pengfei added a comment.

Disable `extendhfsf2/truncsfhf2` tests on Darwin to avoid the fail.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

Files:
  clang/docs/LanguageExtensions.rst
  clang/docs/ReleaseNotes.rst
  clang/lib/Basic/Targets/X86.cpp
  clang/test/CodeGen/X86/Float16-arithmetic.c
  clang/test/CodeGen/X86/Float16-complex.c
  clang/test/CodeGen/X86/avx512fp16-complex.c
  clang/test/Sema/Float16.c
  clang/test/Sema/conversion-target-dep.c
  clang/test/SemaCXX/Float16.cpp
  compiler-rt/test/builtins/CMakeLists.txt
  compiler-rt/test/builtins/Unit/extendhfsf2_test.c
  compiler-rt/test/builtins/Unit/truncdfhf2_test.c
  compiler-rt/test/builtins/Unit/truncsfhf2_test.c

Index: compiler-rt/test/builtins/Unit/truncsfhf2_test.c
===
--- compiler-rt/test/builtins/Unit/truncsfhf2_test.c
+++ compiler-rt/test/builtins/Unit/truncsfhf2_test.c
@@ -1,4 +1,7 @@
 // RUN: %clang_builtins %s %librt -o %t && %run %t
+// FIXME: Darwin used a different ABI for FP16 type. Disable the test to avoid
+// it fails on stage1 build.
+// UNSUPPORTED: darwin
 // REQUIRES: librt_has_truncsfhf2
 
 #include 
Index: compiler-rt/test/builtins/Unit/truncdfhf2_test.c
===
--- compiler-rt/test/builtins/Unit/truncdfhf2_test.c
+++ compiler-rt/test/builtins/Unit/truncdfhf2_test.c
@@ -1,4 +1,7 @@
 // RUN: %clang_builtins %s %librt -o %t && %run %t
+// FIXME: Darwin used a different ABI for FP16 type. Disable the test to avoid
+// it fails on stage1 build.
+// UNSUPPORTED: darwin
 // REQUIRES: librt_has_truncdfhf2
 
 #include 
Index: compiler-rt/test/builtins/Unit/extendhfsf2_test.c
===
--- compiler-rt/test/builtins/Unit/extendhfsf2_test.c
+++ compiler-rt/test/builtins/Unit/extendhfsf2_test.c
@@ -1,4 +1,7 @@
 // RUN: %clang_builtins %s %librt -o %t && %run %t
+// FIXME: Darwin used a different ABI for FP16 type. Disable the test to avoid
+// it fails on stage1 build.
+// UNSUPPORTED: darwin
 // REQUIRES: librt_has_extendhfsf2
 
 #include 
Index: compiler-rt/test/builtins/CMakeLists.txt
===
--- compiler-rt/test/builtins/CMakeLists.txt
+++ compiler-rt/test/builtins/CMakeLists.txt
@@ -44,7 +44,7 @@
 string(REPLACE ";" " " BUILTINS_TEST_TARGET_CFLAGS "${BUILTINS_TEST_TARGET_CFLAGS}")
   endif()
 
-  if (${arch} MATCHES "arm|aarch64|arm64" AND COMPILER_RT_HAS_FLOAT16)
+  if (${arch} MATCHES "arm|aarch64|arm64|i?86|x86_64|AMD64" 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()
Index: clang/test/SemaCXX/Float16.cpp
===
--- clang/test/SemaCXX/Float16.cpp
+++ clang/test/SemaCXX/Float16.cpp
@@ -1,4 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/Sema/conversion-target-dep.c
===
--- clang/test/Sema/conversion-target-dep.c
+++ clang/test/Sema/conversion-target-dep.c
@@ -6,7 +6,7 @@
 
 long double ld;
 double d;
-_Float16 f16; // x86-error {{_Float16 is not supported on this target}}
+_Float16 f16;
 
 int main(void) {
   ld = d; // x86-warning {{implicit conversion increases floating-point precision: 'double' to 'long double'}}
Index: clang/test/Sema/Float16.c
===
--- clang/test/Sema/Float16.c
+++ clang/test/Sema/Float16.c
@@ -1,5 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc -target-feature +avx512fp16 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index:

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-29 Thread Phoebe Wang via Phabricator via cfe-commits 
pengfei added a comment.

In D128571#3619265 , @alexfh wrote:

> @pengfei could you fix the Darwin tests as well? And a general comment 
> regarding the ongoing `_Float16` effort: I think that this change should have 
> been a part of https://reviews.llvm.org/D107082 to make it possible to build 
> a consistently working toolchain. Thus, if this commit can't be landed in a 
> reasonable time, I'd suggest reverting https://reviews.llvm.org/D107082.

@alexfh I'm working on that. I'm asking suggestion on solving it in a better 
way, but at least we can disable the test for Darwin (maybe just for stage1 if 
possible) since it's expected due to the ABI change.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-29 Thread Phoebe Wang via Phabricator via cfe-commits 
pengfei added a comment.

Thanks @benlangmuir for the revert. The problem seems Darwin supports the 
`_Float16` type already but with a different ABI. I have no idea how to solve 
the problem ATM. Post a question on discourse: 
https://discourse.llvm.org/t/compiler-rt-tests-fail-on-darwin-stage1-build-after-the-abi-change-of-half-type-on-x86/63508


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-29 Thread Alexander Kornienko via Phabricator via cfe-commits 
alexfh added a comment.

@pengfei could you fix the Darwin tests as well? And a general comment 
regarding the ongoing `_Float16` effort: I think that this change should have 
been a part of https://reviews.llvm.org/D107082 to make it possible to build a 
consistently working toolchain. Thus, if this commit can't be landed in a 
reasonable time, I'd suggest reverting https://reviews.llvm.org/D107082.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-28 Thread Ben Langmuir via Phabricator via cfe-commits 
benlangmuir added a comment.

Reverted in eab2a06f0fde 
 due to 
the Darwin test failures.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-28 Thread Ben Langmuir via Phabricator via cfe-commits 
benlangmuir added a comment.

This broke some compiler-rt tests on Darwin:
https://green.lab.llvm.org/green/job/clang-stage1-RA/29920/

  Test Result (3 failures / +3)
  Builtins-x86_64-darwin.Builtins-x86_64-darwin.extendhfsf2_test.c
  Builtins-x86_64-darwin.Builtins-x86_64-darwin.truncdfhf2_test.c
  Builtins-x86_64-darwin.Builtins-x86_64-darwin.truncsfhf2_test.c


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-28 Thread Phoebe Wang via Phabricator via cfe-commits 
pengfei added a subscriber: vitalybuka.
pengfei added a comment.

Thanks @vitalybuka ! I believe the fail was caused by missing 
`COMPILER_RT_HAS_FLOAT16` in these tests. Relanded.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-28 Thread Phoebe Wang via Phabricator via cfe-commits 
This revision was automatically updated to reflect the committed changes.
Closed by commit rG527ef8ca981e: Reland [X86] Support `_Float16` on SSE2 
and up (authored by pengfei).
Herald added subscribers: Sanitizers, Enna1, mgorny.
Herald added a project: Sanitizers.

Changed prior to commit:
  https://reviews.llvm.org/D128571?vs=440199=440490#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

Files:
  clang/docs/LanguageExtensions.rst
  clang/docs/ReleaseNotes.rst
  clang/lib/Basic/Targets/X86.cpp
  clang/test/CodeGen/X86/Float16-arithmetic.c
  clang/test/CodeGen/X86/Float16-complex.c
  clang/test/CodeGen/X86/avx512fp16-complex.c
  clang/test/Sema/Float16.c
  clang/test/Sema/conversion-target-dep.c
  clang/test/SemaCXX/Float16.cpp
  compiler-rt/test/builtins/CMakeLists.txt

Index: compiler-rt/test/builtins/CMakeLists.txt
===
--- compiler-rt/test/builtins/CMakeLists.txt
+++ compiler-rt/test/builtins/CMakeLists.txt
@@ -44,7 +44,7 @@
 string(REPLACE ";" " " BUILTINS_TEST_TARGET_CFLAGS "${BUILTINS_TEST_TARGET_CFLAGS}")
   endif()
 
-  if (${arch} MATCHES "arm|aarch64|arm64" AND COMPILER_RT_HAS_FLOAT16)
+  if (${arch} MATCHES "arm|aarch64|arm64|i?86|x86_64|AMD64" 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()
Index: clang/test/SemaCXX/Float16.cpp
===
--- clang/test/SemaCXX/Float16.cpp
+++ clang/test/SemaCXX/Float16.cpp
@@ -1,4 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/Sema/conversion-target-dep.c
===
--- clang/test/Sema/conversion-target-dep.c
+++ clang/test/Sema/conversion-target-dep.c
@@ -6,7 +6,7 @@
 
 long double ld;
 double d;
-_Float16 f16; // x86-error {{_Float16 is not supported on this target}}
+_Float16 f16;
 
 int main(void) {
   ld = d; // x86-warning {{implicit conversion increases floating-point precision: 'double' to 'long double'}}
Index: clang/test/Sema/Float16.c
===
--- clang/test/Sema/Float16.c
+++ clang/test/Sema/Float16.c
@@ -1,5 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc -target-feature +avx512fp16 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/CodeGen/X86/Float16-complex.c
===
--- clang/test/CodeGen/X86/Float16-complex.c
+++ clang/test/CodeGen/X86/Float16-complex.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -target-feature +avx512fp16 -o - | FileCheck %s --check-prefix=X86
+// RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -o - | FileCheck %s --check-prefix=X86
 
 _Float16 _Complex add_half_rr(_Float16 a, _Float16 b) {
   // X86-LABEL: @add_half_rr(
Index: clang/test/CodeGen/X86/Float16-arithmetic.c
===
--- /dev/null
+++ clang/test/CodeGen/X86/Float16-arithmetic.c
@@ -0,0 +1,29 @@
+// RUN: %clang_cc1 -triple  x86_64-unknown-unknown \
+// RUN: -emit-llvm -o - %s  | FileCheck %s --check-prefixes=CHECK
+
+// CHECK-NOT: fpext
+// CHECK-NOT: fptrunc
+
+_Float16 add1(_Float16 a, _Float16 b) {
+  return a + b;
+}
+
+_Float16 add2(_Float16 a, _Float16 b, _Float16 c) {
+  return a + b + c;
+}
+
+_Float16 div(_Float16 a, _Float16 b) {
+  return a / b;
+}
+
+_Float16 mul(_Float16 a, _Float16 b) {
+  return a * b;
+}
+
+_Float16 add_and_mul1(_Float16 a, _Float16 b, _Float16 c, _Float16 d) {
+  return a * b + c * d;
+}
+
+_Float16 add_and_mul2(_Float16 a, _Float16 b, _Float16 c, _Float16 d) {
+  return (a - 6 * b) + c;
+}
Index:

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-27 Thread Phoebe Wang via Phabricator via cfe-commits 
This revision was automatically updated to reflect the committed changes.
Closed by commit rGf5d781d6273c: [X86] Support `_Float16` on SSE2 and up 
(authored by pengfei).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

Files:
  clang/docs/LanguageExtensions.rst
  clang/docs/ReleaseNotes.rst
  clang/lib/Basic/Targets/X86.cpp
  clang/test/CodeGen/X86/Float16-arithmetic.c
  clang/test/CodeGen/X86/Float16-complex.c
  clang/test/CodeGen/X86/avx512fp16-complex.c
  clang/test/Sema/Float16.c
  clang/test/Sema/conversion-target-dep.c
  clang/test/SemaCXX/Float16.cpp

Index: clang/test/SemaCXX/Float16.cpp
===
--- clang/test/SemaCXX/Float16.cpp
+++ clang/test/SemaCXX/Float16.cpp
@@ -1,4 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/Sema/conversion-target-dep.c
===
--- clang/test/Sema/conversion-target-dep.c
+++ clang/test/Sema/conversion-target-dep.c
@@ -6,7 +6,7 @@
 
 long double ld;
 double d;
-_Float16 f16; // x86-error {{_Float16 is not supported on this target}}
+_Float16 f16;
 
 int main(void) {
   ld = d; // x86-warning {{implicit conversion increases floating-point precision: 'double' to 'long double'}}
Index: clang/test/Sema/Float16.c
===
--- clang/test/Sema/Float16.c
+++ clang/test/Sema/Float16.c
@@ -1,5 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc -target-feature +avx512fp16 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/CodeGen/X86/Float16-complex.c
===
--- clang/test/CodeGen/X86/Float16-complex.c
+++ clang/test/CodeGen/X86/Float16-complex.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -target-feature +avx512fp16 -o - | FileCheck %s --check-prefix=X86
+// RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -o - | FileCheck %s --check-prefix=X86
 
 _Float16 _Complex add_half_rr(_Float16 a, _Float16 b) {
   // X86-LABEL: @add_half_rr(
Index: clang/test/CodeGen/X86/Float16-arithmetic.c
===
--- /dev/null
+++ clang/test/CodeGen/X86/Float16-arithmetic.c
@@ -0,0 +1,29 @@
+// RUN: %clang_cc1 -triple  x86_64-unknown-unknown \
+// RUN: -emit-llvm -o - %s  | FileCheck %s --check-prefixes=CHECK
+
+// CHECK-NOT: fpext
+// CHECK-NOT: fptrunc
+
+_Float16 add1(_Float16 a, _Float16 b) {
+  return a + b;
+}
+
+_Float16 add2(_Float16 a, _Float16 b, _Float16 c) {
+  return a + b + c;
+}
+
+_Float16 div(_Float16 a, _Float16 b) {
+  return a / b;
+}
+
+_Float16 mul(_Float16 a, _Float16 b) {
+  return a * b;
+}
+
+_Float16 add_and_mul1(_Float16 a, _Float16 b, _Float16 c, _Float16 d) {
+  return a * b + c * d;
+}
+
+_Float16 add_and_mul2(_Float16 a, _Float16 b, _Float16 c, _Float16 d) {
+  return (a - 6 * b) + c;
+}
Index: clang/lib/Basic/Targets/X86.cpp
===
--- clang/lib/Basic/Targets/X86.cpp
+++ clang/lib/Basic/Targets/X86.cpp
@@ -239,7 +239,6 @@
   HasAVX512ER = true;
 } else if (Feature == "+avx512fp16") {
   HasAVX512FP16 = true;
-  HasFloat16 = true;
 } else if (Feature == "+avx512pf") {
   HasAVX512PF = true;
 } else if (Feature == "+avx512dq") {
@@ -355,6 +354,9 @@
.Default(NoSSE);
 SSELevel = std::max(SSELevel, Level);
 
+// Turn on _float16 for x86 (feature sse2)
+HasFloat16 = SSELevel >= SSE2;
+
 MMX3DNowEnum ThreeDNowLevel = llvm::StringSwitch(Feature)
   .Case("+3dnowa", AMD3DNowAthlon)
   .Case("+3dnow", AMD3DNow)
Index: clang/docs/ReleaseNotes.rst

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-27 Thread Zahira Ammarguellat via Phabricator via cfe-commits 
zahiraam accepted this revision.
zahiraam added a comment.

LGTM.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-27 Thread John McCall via Phabricator via cfe-commits 
rjmccall accepted this revision.
rjmccall added a comment.

Thank you, LGTM.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-25 Thread Phoebe Wang via Phabricator via cfe-commits 
pengfei updated this revision to Diff 440016.
pengfei marked 3 inline comments as done.
pengfei added a comment.

Address review comments. Thanks @rjmccall !


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

Files:
  clang/docs/LanguageExtensions.rst
  clang/docs/ReleaseNotes.rst
  clang/lib/Basic/Targets/X86.cpp
  clang/test/CodeGen/X86/Float16-arithmetic.c
  clang/test/CodeGen/X86/Float16-complex.c
  clang/test/CodeGen/X86/avx512fp16-complex.c
  clang/test/Sema/Float16.c
  clang/test/Sema/conversion-target-dep.c
  clang/test/SemaCXX/Float16.cpp

Index: clang/test/SemaCXX/Float16.cpp
===
--- clang/test/SemaCXX/Float16.cpp
+++ clang/test/SemaCXX/Float16.cpp
@@ -1,4 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/Sema/conversion-target-dep.c
===
--- clang/test/Sema/conversion-target-dep.c
+++ clang/test/Sema/conversion-target-dep.c
@@ -6,7 +6,7 @@
 
 long double ld;
 double d;
-_Float16 f16; // x86-error {{_Float16 is not supported on this target}}
+_Float16 f16;
 
 int main(void) {
   ld = d; // x86-warning {{implicit conversion increases floating-point precision: 'double' to 'long double'}}
Index: clang/test/Sema/Float16.c
===
--- clang/test/Sema/Float16.c
+++ clang/test/Sema/Float16.c
@@ -1,5 +1,6 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc -target-feature +avx512fp16 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple i686-linux-pc -target-feature +sse2 %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
 // RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
Index: clang/test/CodeGen/X86/Float16-complex.c
===
--- clang/test/CodeGen/X86/Float16-complex.c
+++ clang/test/CodeGen/X86/Float16-complex.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -target-feature +avx512fp16 -o - | FileCheck %s --check-prefix=X86
+// RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -o - | FileCheck %s --check-prefix=X86
 
 _Float16 _Complex add_half_rr(_Float16 a, _Float16 b) {
   // X86-LABEL: @add_half_rr(
Index: clang/test/CodeGen/X86/Float16-arithmetic.c
===
--- /dev/null
+++ clang/test/CodeGen/X86/Float16-arithmetic.c
@@ -0,0 +1,29 @@
+// RUN: %clang_cc1 -triple  x86_64-unknown-unknown \
+// RUN: -emit-llvm -o - %s  | FileCheck %s --check-prefixes=CHECK
+
+// CHECK-NOT: fpext
+// CHECK-NOT: fptrunc
+
+_Float16 add1(_Float16 a, _Float16 b) {
+  return a + b;
+}
+
+_Float16 add2(_Float16 a, _Float16 b, _Float16 c) {
+  return a + b + c;
+}
+
+_Float16 div(_Float16 a, _Float16 b) {
+  return a / b;
+}
+
+_Float16 mul(_Float16 a, _Float16 b) {
+  return a * b;
+}
+
+_Float16 add_and_mul1(_Float16 a, _Float16 b, _Float16 c, _Float16 d) {
+  return a * b + c * d;
+}
+
+_Float16 add_and_mul2(_Float16 a, _Float16 b, _Float16 c, _Float16 d) {
+  return (a - 6 * b) + c;
+}
Index: clang/lib/Basic/Targets/X86.cpp
===
--- clang/lib/Basic/Targets/X86.cpp
+++ clang/lib/Basic/Targets/X86.cpp
@@ -239,7 +239,6 @@
   HasAVX512ER = true;
 } else if (Feature == "+avx512fp16") {
   HasAVX512FP16 = true;
-  HasFloat16 = true;
 } else if (Feature == "+avx512pf") {
   HasAVX512PF = true;
 } else if (Feature == "+avx512dq") {
@@ -355,6 +354,9 @@
.Default(NoSSE);
 SSELevel = std::max(SSELevel, Level);
 
+// Turn on _float16 for x86 (feature sse2)
+HasFloat16 = SSELevel >= SSE2;
+
 MMX3DNowEnum ThreeDNowLevel = llvm::StringSwitch(Feature)
   .Case("+3dnowa", AMD3DNowAthlon)
   .Case("+3dnow", AMD3DNow)
Index: clang/docs/ReleaseNotes.rst

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-25 Thread John McCall via Phabricator via cfe-commits 
rjmccall added inline comments.



Comment at: clang/docs/LanguageExtensions.rst:746
 * SPIR
-* X86 (Only available under feature AVX512-FP16)
+* X86 (Enabled with feature SSE2 and up)
 

Could you take the wording I suggested from the other patch?  You'll need to 
drop the part about avoiding intermediate truncations, but it's important to 
still document the practical/performance difference when AVX512-FP16 is not 
available, even if the observable behavior is the same.



Comment at: clang/docs/ReleaseNotes.rst:517
 
+- Support for ``_Float16`` type has been added.
+





Comment at: clang/test/SemaCXX/Float16.cpp:4
+// RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s
 

This test (and Float16.c) should continue to have positive and negative 
examples even if generic x86_64 is no longer negative.  Generic i386 should 
still be negative, for example.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-25 Thread Benjamin Kramer via Phabricator via cfe-commits 
bkramer accepted this revision.
bkramer added a comment.
This revision is now accepted and ready to land.

Thanks


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128571/new/

https://reviews.llvm.org/D128571

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128571: [X86] Support `_Float16` on SSE2 and up

2022-06-24 Thread Phoebe Wang via Phabricator via cfe-commits 
pengfei created this revision.
pengfei added reviewers: zahiraam, rjmccall, bkramer, alexfh.
Herald added a subscriber: jsji.
Herald added a project: All.
pengfei requested review of this revision.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

This is split from D113107  to address #56204 
and 
https://discourse.llvm.org/t/how-to-build-compiler-rt-for-new-x86-half-float-abi/63366


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D128571

Files:
  clang/docs/LanguageExtensions.rst
  clang/docs/ReleaseNotes.rst
  clang/lib/Basic/Targets/X86.cpp
  clang/test/CodeGen/X86/Float16-arithmetic.c
  clang/test/CodeGen/X86/Float16-complex.c
  clang/test/CodeGen/X86/avx512fp16-complex.c
  clang/test/Sema/Float16.c
  clang/test/Sema/conversion-target-dep.c
  clang/test/SemaCXX/Float16.cpp

Index: clang/test/SemaCXX/Float16.cpp
===
--- clang/test/SemaCXX/Float16.cpp
+++ clang/test/SemaCXX/Float16.cpp
@@ -1,18 +1,10 @@
 // RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
-// RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
-// RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
-// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s
 
-#ifdef HAVE
 // expected-no-diagnostics
-#endif // HAVE
 
-#ifndef HAVE
-// expected-error@+2{{_Float16 is not supported on this target}}
-#endif // !HAVE
 _Float16 f;
 
-#ifndef HAVE
-// expected-error@+2{{invalid suffix 'F16' on floating constant}}
-#endif // !HAVE
 const auto g = 1.1F16;
Index: clang/test/Sema/conversion-target-dep.c
===
--- clang/test/Sema/conversion-target-dep.c
+++ clang/test/Sema/conversion-target-dep.c
@@ -6,7 +6,7 @@
 
 long double ld;
 double d;
-_Float16 f16; // x86-error {{_Float16 is not supported on this target}}
+_Float16 f16;
 
 int main(void) {
   ld = d; // x86-warning {{implicit conversion increases floating-point precision: 'double' to 'long double'}}
Index: clang/test/Sema/Float16.c
===
--- clang/test/Sema/Float16.c
+++ clang/test/Sema/Float16.c
@@ -1,18 +1,13 @@
 // RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc %s
-// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc -target-feature +avx512fp16 %s -DHAVE
-// RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s -DHAVE
-// RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s -DHAVE
-// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s -DHAVE
+// RUN: %clang_cc1 -fsyntax-only -verify -triple x86_64-linux-pc -target-feature +avx512fp16 %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple spir-unknown-unknown %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple armv7a-linux-gnu %s
+// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64-linux-gnu %s
 
-#ifndef HAVE
-// expected-error@+2{{_Float16 is not supported on this target}}
-#endif // HAVE
 _Float16 f;
 
-#ifdef HAVE
 _Complex _Float16 a;
 void builtin_complex(void) {
   _Float16 a = 0;
   (void)__builtin_complex(a, a); // expected-error {{'_Complex _Float16' is invalid}}
 }
-#endif
Index: clang/test/CodeGen/X86/Float16-complex.c
===
--- clang/test/CodeGen/X86/Float16-complex.c
+++ clang/test/CodeGen/X86/Float16-complex.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -target-feature +avx512fp16 -o - | FileCheck %s --check-prefix=X86
+// RUN: %clang_cc1 %s -O0 -emit-llvm -triple x86_64-unknown-unknown -o - | FileCheck %s --check-prefix=X86
 
 _Float16 _Complex add_half_rr(_Float16 a, _Float16 b) {
   // X86-LABEL: @add_half_rr(
Index: clang/test/CodeGen/X86/Float16-arithmetic.c
===
--- /dev/null
+++ clang/test/CodeGen/X86/Float16-arithmetic.c
@@ -0,0 +1,29 @@
+// RUN: %clang_cc1 -triple  x86_64-unknown-unknown \
+// RUN: -emit-llvm -o - %s  | FileCheck %s --check-prefixes=CHECK
+
+// CHECK-NOT: fpext
+// CHECK-NOT: fptrunc
+
+_Float16 add1(_Float16 a, _Float16 b) {
+  return a + b;
+}
+
+_Float16 add2(_Float16 a, _Float16 b, _Float16 c) {
+  return a + b + c;
+}
+
+_Float16 div(_Float16 a, _Float16 b) {
+  return a / b;
+}
+
+_Float16 mul(_Float16 a, _Float16 b) {
+  return a * b;
+}
+
+_Float16 add_and_mul1(_Float16 a, _Float16 b, _Float16 c, _Float16 d) {
+  return a * b + c * d;
+}
+
+_Float16 add_and_mul2(_Float16 a, _Float16 b, _Float16 c, _Float16 d) {
+  return (a - 6 * b) + c;
+}
Index: clang/lib/Basic/Targets/X86.cpp