https://gcc.gnu.org/g:5deeae29dab2af64e3342daf7a30000e424c64ea
commit r15-9190-g5deeae29dab2af64e3342daf7a30000e424c64ea
Author: Thomas Schwinge <tschwi...@baylibre.com>
Date: Wed Apr 2 10:25:17 2025 +0200
nvptx: Don't use PTX '.const', constant state space [PR119573]
This avoids cases where a "File uses too much global constant data" (final
executable, or single object file), and avoids cases of wrong code
generation:
"error : State space incorrect for instruction 'st'" ('st.const'), or
another
case where an "illegal instruction was encountered", or a lot of cases where
for two compilation units (such as a library linked with user code) we ran
into
"error : Memory space doesn't match" due to differences in '.const' usage
between definition and use of a variable.
We progress:
ptxas error : File uses too much global constant data (0x1f01a bytes,
0x10000 max)
nvptx-run: cuLinkAddData failed: a PTX JIT compilation failed
(CUDA_ERROR_INVALID_PTX, 218)
... into:
PASS: 20_util/to_chars/103955.cc -std=gnu++17 (test for excess errors)
[-FAIL:-]{+PASS:+} 20_util/to_chars/103955.cc -std=gnu++17 execution
test
We progress:
ptxas error : File uses too much global constant data (0x36c65 bytes,
0x10000 max)
nvptx-as: ptxas returned 255 exit status
... into:
[-UNSUPPORTED:-]{+PASS:+} gcc.c-torture/compile/pr46534.c -O0
{+(test for excess errors)+}
[-UNSUPPORTED:-]{+PASS:+} gcc.c-torture/compile/pr46534.c -O1
{+(test for excess errors)+}
[-UNSUPPORTED:-]{+PASS:+} gcc.c-torture/compile/pr46534.c -O2
{+(test for excess errors)+}
[-UNSUPPORTED:-]{+PASS:+} gcc.c-torture/compile/pr46534.c -O3 -g
{+(test for excess errors)+}
[-UNSUPPORTED:-]{+PASS:+} gcc.c-torture/compile/pr46534.c -Os
{+(test for excess errors)+}
[-FAIL:-]{+PASS:+} g++.dg/torture/pr31863.C -O0 (test for excess
errors)
[-FAIL:-]{+PASS:+} g++.dg/torture/pr31863.C -O1 (test for excess
errors)
[-FAIL:-]{+PASS:+} g++.dg/torture/pr31863.C -O2 (test for excess
errors)
[-FAIL:-]{+PASS:+} g++.dg/torture/pr31863.C -O3 -g (test for excess
errors)
[-FAIL:-]{+PASS:+} g++.dg/torture/pr31863.C -Os (test for excess
errors)
[-FAIL:-]{+PASS:+} gfortran.dg/bind-c-contiguous-1.f90 -O0 (test for
excess errors)
[-UNRESOLVED:-]{+PASS:+} gfortran.dg/bind-c-contiguous-1.f90 -O0
[-compilation failed to produce executable-]{+execution test+}
[-FAIL:-]{+PASS:+} gfortran.dg/bind-c-contiguous-4.f90 -O0 (test for
excess errors)
[-UNRESOLVED:-]{+PASS:+} gfortran.dg/bind-c-contiguous-4.f90 -O0
[-compilation failed to produce executable-]{+execution test+}
[-FAIL:-]{+PASS:+} gfortran.dg/bind-c-contiguous-5.f90 -O0 (test for
excess errors)
[-UNRESOLVED:-]{+PASS:+} gfortran.dg/bind-c-contiguous-5.f90 -O0
[-compilation failed to produce executable-]{+execution test+}
[-FAIL:-]{+PASS:+} 20_util/to_chars/double.cc -std=gnu++17 (test for
excess errors)
[-UNRESOLVED:-]{+PASS:+} 20_util/to_chars/double.cc -std=gnu++17
[-compilation failed to produce executable-]{+execution test+}
[-FAIL:-]{+PASS:+} 20_util/to_chars/float.cc -std=gnu++17 (test for
excess errors)
[-UNRESOLVED:-]{+PASS:+} 20_util/to_chars/float.cc -std=gnu++17
[-compilation failed to produce executable-]{+execution test+}
[-FAIL:-]{+PASS:+} special_functions/13_ellint_3/check_value.cc
-std=gnu++17 (test for excess errors)
[-UNRESOLVED:-]{+PASS:+} special_functions/13_ellint_3/check_value.cc
-std=gnu++17 [-compilation failed to produce executable-]{+execution test+}
[-FAIL:-]{+PASS:+}
tr1/5_numerical_facilities/special_functions/14_ellint_3/check_value.cc
-std=gnu++17 (test for excess errors)
[-UNRESOLVED:-]{+PASS:+}
tr1/5_numerical_facilities/special_functions/14_ellint_3/check_value.cc
-std=gnu++17 [-compilation failed to produce executable-]{+execution test+}
..., and progress likewise, but fail later with an unrelated error:
[-FAIL:-]{+PASS:+} ext/special_functions/hyperg/check_value.cc
-std=gnu++17 (test for excess errors)
[-UNRESOLVED:-]{+FAIL:+} ext/special_functions/hyperg/check_value.cc
-std=gnu++17 [-compilation failed to produce executable-]{+execution test+}
[...]/libstdc++-v3/testsuite/ext/special_functions/hyperg/check_value.cc:12317:
void test(const testcase_hyperg<Ret> (&)[Num], Ret) [with Ret = double;
unsigned int Num = 19]: Assertion 'max_abs_frac < toler' failed.
..., and:
[-FAIL:-]{+PASS:+}
tr1/5_numerical_facilities/special_functions/17_hyperg/check_value.cc
-std=gnu++17 (test for excess errors)
[-UNRESOLVED:-]{+FAIL:+}
tr1/5_numerical_facilities/special_functions/17_hyperg/check_value.cc
-std=gnu++17 [-compilation failed to produce executable-]{+execution test+}
[...]/libstdc++-v3/testsuite/tr1/5_numerical_facilities/special_functions/17_hyperg/check_value.cc:12316:
void test(const testcase_hyperg<Ret> (&)[Num], Ret) [with Ret = double;
unsigned int Num = 19]: Assertion 'max_abs_frac < toler' failed.
We progress:
nvptx-run: error getting kernel result: an illegal instruction was
encountered (CUDA_ERROR_ILLEGAL_INSTRUCTION, 715)
... into:
PASS: g++.dg/cpp1z/inline-var1.C -std=gnu++17 (test for excess errors)
[-FAIL:-]{+PASS:+} g++.dg/cpp1z/inline-var1.C -std=gnu++17 execution
test
PASS: g++.dg/cpp1z/inline-var1.C -std=gnu++20 (test for excess errors)
[-FAIL:-]{+PASS:+} g++.dg/cpp1z/inline-var1.C -std=gnu++20 execution
test
PASS: g++.dg/cpp1z/inline-var1.C -std=gnu++26 (test for excess errors)
[-FAIL:-]{+PASS:+} g++.dg/cpp1z/inline-var1.C -std=gnu++26 execution
test
(A lot of '.const' -> '.global' etc. Haven't researched what the actual
problem was.)
We progress:
ptxas /tmp/cc5TSZZp.o, line 142; error : State space incorrect for
instruction 'st'
ptxas /tmp/cc5TSZZp.o, line 174; error : State space incorrect for
instruction 'st'
ptxas fatal : Ptx assembly aborted due to errors
nvptx-as: ptxas returned 255 exit status
... into:
[-FAIL:-]{+PASS:+} g++.dg/torture/builtin-clear-padding-1.C -O0
(test for excess errors)
[-UNRESOLVED:-]{+PASS:+} g++.dg/torture/builtin-clear-padding-1.C -O0
[-compilation failed to produce executable-]{+execution test+}
PASS: g++.dg/torture/builtin-clear-padding-1.C -O1 (test for excess
errors)
PASS: g++.dg/torture/builtin-clear-padding-1.C -O1 execution test
[-FAIL:-]{+PASS:+} g++.dg/torture/builtin-clear-padding-1.C -O2
(test for excess errors)
[-UNRESOLVED:-]{+PASS:+} g++.dg/torture/builtin-clear-padding-1.C -O2
[-compilation failed to produce executable-]{+execution test+}
[-FAIL:-]{+PASS:+} g++.dg/torture/builtin-clear-padding-1.C -O3 -g
(test for excess errors)
[-UNRESOLVED:-]{+PASS:+} g++.dg/torture/builtin-clear-padding-1.C -O3
-g [-compilation failed to produce executable-]{+execution test+}
[-FAIL:-]{+PASS:+} g++.dg/torture/builtin-clear-padding-1.C -Os
(test for excess errors)
[-UNRESOLVED:-]{+PASS:+} g++.dg/torture/builtin-clear-padding-1.C -Os
[-compilation failed to produce executable-]{+execution test+}
This indeed tried to write ('st.const') into 's2', which was '.const'
(also: 's1' was '.const') -- even though, no explicit 'const' in
'g++.dg/torture/builtin-clear-padding-1.C'; "interesting".
We progress:
error : Memory space doesn't match for
'_ZNSt3tr18__detail12__prime_listE' in 'input file 3 at offset 53085', first
specified in 'input file 1 at offset 1924'
nvptx-run: cuLinkAddData failed: device kernel image is invalid
(CUDA_ERROR_INVALID_SOURCE, 300)
... into execution test PASS for a few dozens of libstdc++ test cases.
We progress:
error : Memory space doesn't match for
'_ZNSt6locale17_S_twinned_facetsE' in 'input file 11 at offset 479903', first
specified in 'input file 9 at offset 59300'
nvptx-run: cuLinkAddData failed: device kernel image is invalid
(CUDA_ERROR_INVALID_SOURCE, 300)
... into:
PASS: g++.dg/tree-ssa/pr20458.C -std=gnu++17 (test for excess errors)
[-FAIL:-]{+PASS:+} g++.dg/tree-ssa/pr20458.C -std=gnu++17 execution
test
PASS: g++.dg/tree-ssa/pr20458.C -std=gnu++26 (test for excess errors)
[-FAIL:-]{+PASS:+} g++.dg/tree-ssa/pr20458.C -std=gnu++26 execution
test
..., and likewise for a few hundreds of libstdc++ test cases.
We progress:
error : Memory space doesn't match for
'_ZNSt6locale5_Impl19_S_facet_categoriesE' in 'input file 11 at offset 821962',
first specified in 'input file 10 at offset 676317'
nvptx-run: cuLinkAddData failed: device kernel image is invalid
(CUDA_ERROR_INVALID_SOURCE, 300)
... into execution test PASS for a hundred of libstdc++ test cases.
We progress:
error : Memory space doesn't match for '_ctype_' in 'input file 22 at
offset 1698331', first specified in 'input file 9 at offset 57095'
nvptx-run: cuLinkAddData failed: device kernel image is invalid
(CUDA_ERROR_INVALID_SOURCE, 300)
... into execution test PASS for another few libstdc++ test cases.
PR target/119573
gcc/
* config/nvptx/nvptx.cc (nvptx_encode_section_info): Don't set
'DATA_AREA_CONST' for 'TREE_CONSTANT', or 'TREE_READONLY'.
(nvptx_asm_declare_constant_name): Use '.global' instead of
'.const'.
gcc/testsuite/
* gcc.c-torture/compile/pr46534.c: Don't 'dg-skip-if' nvptx.
* gcc.target/nvptx/decl.c: Adjust.
libstdc++-v3/
* config/cpu/nvptx/t-nvptx (AM_MAKEFLAGS): Don't amend.
Diff:
---
gcc/config/nvptx/nvptx.cc | 8 +++-----
gcc/testsuite/gcc.c-torture/compile/pr46534.c | 1 -
gcc/testsuite/gcc.target/nvptx/decl.c | 6 +++---
libstdc++-v3/config/cpu/nvptx/t-nvptx | 6 ------
4 files changed, 6 insertions(+), 15 deletions(-)
diff --git a/gcc/config/nvptx/nvptx.cc b/gcc/config/nvptx/nvptx.cc
index 022037f13627..de0ce5d91645 100644
--- a/gcc/config/nvptx/nvptx.cc
+++ b/gcc/config/nvptx/nvptx.cc
@@ -470,9 +470,7 @@ nvptx_encode_section_info (tree decl, rtx rtl, int first)
{
nvptx_data_area area = DATA_AREA_GENERIC;
- if (TREE_CONSTANT (decl))
- area = DATA_AREA_CONST;
- else if (VAR_P (decl))
+ if (VAR_P (decl))
{
if (lookup_attribute ("shared", DECL_ATTRIBUTES (decl)))
{
@@ -482,7 +480,7 @@ nvptx_encode_section_info (tree decl, rtx rtl, int first)
" memory is not supported", decl);
}
else
- area = TREE_READONLY (decl) ? DATA_AREA_CONST : DATA_AREA_GLOBAL;
+ area = DATA_AREA_GLOBAL;
}
SET_SYMBOL_DATA_AREA (XEXP (rtl, 0), area);
@@ -2597,7 +2595,7 @@ nvptx_asm_declare_constant_name (FILE *file, const char
*name,
fprintf (file, "\t");
tree type = TREE_TYPE (exp);
- nvptx_assemble_decl_begin (file, name, ".const", type, obj_size,
+ nvptx_assemble_decl_begin (file, name, ".global", type, obj_size,
TYPE_ALIGN (type));
}
diff --git a/gcc/testsuite/gcc.c-torture/compile/pr46534.c
b/gcc/testsuite/gcc.c-torture/compile/pr46534.c
index 1894636f0ead..7f10bc097eba 100644
--- a/gcc/testsuite/gcc.c-torture/compile/pr46534.c
+++ b/gcc/testsuite/gcc.c-torture/compile/pr46534.c
@@ -1,4 +1,3 @@
-/* { dg-skip-if "too big" { nvptx-*-* } } */
/* PR middle-end/46534 */
extern int printf (const char *, ...);
diff --git a/gcc/testsuite/gcc.target/nvptx/decl.c
b/gcc/testsuite/gcc.target/nvptx/decl.c
index 190a64d5679a..45dd699f420f 100644
--- a/gcc/testsuite/gcc.target/nvptx/decl.c
+++ b/gcc/testsuite/gcc.target/nvptx/decl.c
@@ -13,8 +13,8 @@ int Foo ()
}
/* { dg-final { scan-assembler "\[\r\n\]\[\t \]*.visible .global
\[^,\r\n\]*glob_export" } } */
-/* { dg-final { scan-assembler "\[\r\n\]\[\t \]*.visible .const
\[^,\r\n\]*cst_export" } } */
+/* { dg-final { scan-assembler "\[\r\n\]\[\t \]*.visible .global
\[^,\r\n\]*cst_export" } } */
/* { dg-final { scan-assembler "\[\r\n\]\[\t \]*.global \[^,\r\n\]*glob_local"
} } */
-/* { dg-final { scan-assembler "\[\r\n\]\[\t \]*.const \[^,\r\n\]*cst_local" }
} */
+/* { dg-final { scan-assembler "\[\r\n\]\[\t \]*.global \[^,\r\n\]*cst_local"
} } */
/* { dg-final { scan-assembler "\[\r\n\]\[\t \]*.extern .global
\[^,\r\n\]*glob_import" } } */
-/* { dg-final { scan-assembler "\[\r\n\]\[\t \]*.extern .const
\[^,\r\n\]*cst_import" } } */
+/* { dg-final { scan-assembler "\[\r\n\]\[\t \]*.extern .global
\[^,\r\n\]*cst_import" } } */
diff --git a/libstdc++-v3/config/cpu/nvptx/t-nvptx
b/libstdc++-v3/config/cpu/nvptx/t-nvptx
index a2f0f2dcb609..eacc5468d627 100644
--- a/libstdc++-v3/config/cpu/nvptx/t-nvptx
+++ b/libstdc++-v3/config/cpu/nvptx/t-nvptx
@@ -1,7 +1 @@
# Per-file flags, see '../../../configure.host', "inject per-file flags".
-
-# 'ptxas'/CUDA Driver rejects objects with a lot of global constant data:
-# ptxas error : File uses too much global constant data ([...])
-# Cut short the assembly-time check; defer to actual use of the object file.
-AM_MAKEFLAGS += CXXFLAGS-src/c++17/floating_to_chars.lo=-Wa,--no-verify
-AM_MAKEFLAGS += CXXFLAGS-src/c++20/tzdb.lo=-Wa,--no-verify
