On 12/12/2018 11:53, Andrew Stubbs wrote:
Since the previous v2 posting, the sqrt_insn additional option mechanism has been reworked. Otherwise the patch has only been rebased.
This updated patch includes the missing internals documentation. OK? Andrew
Port testsuite to GCN This collection of miscellaneous patches configures the testsuite to run on AMD GCN in a standalone (i.e. not offloading) configuration. It assumes you have your Dejagnu set up to run binaries via the gcn-run tool. 2018-12-17 Andrew Stubbs <a...@codesourcery.com> Kwok Cheung Yeung <k...@codesourcery.com> Julian Brown <jul...@codesourcery.com> Tom de Vries <t...@codesourcery.com> gcc/doc/ * sourcebuild.texi: Document dg-add-options sqrt_insn. gcc/testsuite/ * gcc.dg/20020312-2.c: Add amdgcn support. * gcc.dg/Wno-frame-address.c: Disable on amdgcn. * gcc.dg/builtin-apply2.c: Likewise. * gcc.dg/torture/stackalign/builtin-apply-2.c: Likewise. * gcc.dg/gimplefe-28.c: Add dg-add-options for sqrt_insn. * gcc.dg/intermod-1.c: Add -mlocal-symbol-id on amdgcn. * gcc.dg/memcmp-1.c: Increase timeout factor. * gcc.dg/pr59605-2.c: Addd -DMAX_COPY=1025 on amdgcn. * gcc.dg/sibcall-10.c: xfail on amdgcn. * gcc.dg/sibcall-9.c: Likewise. * gcc.dg/tree-ssa/gen-vect-11c.c: Likewise. * gcc.dg/tree-ssa/pr84512.c: Likewise. * gcc.dg/tree-ssa/loop-1.c: Adjust expectations for amdgcn. * gfortran.dg/bind_c_array_params_2.f90: Likewise. * lib/target-supports.exp (check_effective_target_trampolines): Configure amdgcn. (check_profiling_available): Likewise. (check_effective_target_global_constructor): Likewise. (check_effective_target_return_address): Likewise. (check_effective_target_fopenacc): Likewise. (check_effective_target_fopenmp): Likewise. (check_effective_target_vect_int): Likewise. (check_effective_target_vect_intfloat_cvt): Likewise. (check_effective_target_vect_uintfloat_cvt): Likewise. (check_effective_target_vect_floatint_cvt): Likewise. (check_effective_target_vect_floatuint_cvt): Likewise. (check_effective_target_vect_simd_clones): Likewise. (check_effective_target_vect_shift): Likewise. (check_effective_target_whole_vector_shift): Likewise. (check_effective_target_vect_bswap): Likewise. (check_effective_target_vect_shift_char): Likewise. (check_effective_target_vect_long): Likewise. (check_effective_target_vect_float): Likewise. (check_effective_target_vect_double): Likewise. (check_effective_target_vect_perm): Likewise. (check_effective_target_vect_perm_byte): Likewise. (check_effective_target_vect_perm_short): Likewise. (check_effective_target_vect_widen_mult_qi_to_hi): Likewise. (check_effective_target_vect_widen_mult_hi_to_si): Likewise. (check_effective_target_vect_widen_mult_qi_to_hi_pattern): Likewise. (check_effective_target_vect_widen_mult_hi_to_si_pattern): Likewise. (check_effective_target_vect_natural_alignment): Likewise. (check_effective_target_vect_fully_masked): Likewise. (check_effective_target_vect_element_align): Likewise. (check_effective_target_vect_masked_store): Likewise. (check_effective_target_vect_scatter_store): Likewise. (check_effective_target_vect_condition): Likewise. (check_effective_target_vect_cond_mixed): Likewise. (check_effective_target_vect_char_mult): Likewise. (check_effective_target_vect_short_mult): Likewise. (check_effective_target_vect_int_mult): Likewise. (check_effective_target_sqrt_insn): Likewise. (check_effective_target_vect_call_sqrtf): Likewise. (check_effective_target_vect_call_btrunc): Likewise. (check_effective_target_vect_call_btruncf): Likewise. (check_effective_target_vect_call_ceil): Likewise. (check_effective_target_vect_call_floorf): Likewise. (check_effective_target_lto): Likewise. (check_vect_support_and_set_flags): Likewise. (check_effective_target_vect_stridedN): Enable when fully masked is available. (add_options_for_sqrt_insn): New procedure. diff --git a/gcc/doc/sourcebuild.texi b/gcc/doc/sourcebuild.texi index 94c8002..170ee5d 100644 --- a/gcc/doc/sourcebuild.texi +++ b/gcc/doc/sourcebuild.texi @@ -2518,6 +2518,10 @@ Add the flags needed to define macro STACK_SIZE and set it to the stack size limit associated with the @ref{stack_size_et,,@code{stack_size} effective target}. +@item sqrt_insn +Add the target-specific flags needed to enable hardware square root +instructions, if any. + @item tls Add the target-specific flags needed to use thread-local storage. @end table diff --git a/gcc/testsuite/gcc.dg/20020312-2.c b/gcc/testsuite/gcc.dg/20020312-2.c index e72a5b2..c584d35 100644 --- a/gcc/testsuite/gcc.dg/20020312-2.c +++ b/gcc/testsuite/gcc.dg/20020312-2.c @@ -119,6 +119,8 @@ extern void abort (void); # endif #elif defined (__or1k__) /* No pic register. */ +#elif defined (__AMDGCN__) +/* No pic register. */ #else # error "Modify the test for your target." #endif diff --git a/gcc/testsuite/gcc.dg/Wno-frame-address.c b/gcc/testsuite/gcc.dg/Wno-frame-address.c index 11ae0cd..51f20b4 100644 --- a/gcc/testsuite/gcc.dg/Wno-frame-address.c +++ b/gcc/testsuite/gcc.dg/Wno-frame-address.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-skip-if "Cannot access arbitrary stack frames" { arm*-*-* avr-*-* hppa*-*-* ia64-*-* visium-*-* csky-*-* msp430-*-* } } */ +/* { dg-skip-if "Cannot access arbitrary stack frames" { arm*-*-* amdgpu-*-* avr-*-* hppa*-*-* ia64-*-* visium-*-* csky-*-* msp430-*-* } } */ /* { dg-options "-Werror" } */ /* { dg-additional-options "-mbackchain" { target { s390*-*-* } } } */ diff --git a/gcc/testsuite/gcc.dg/builtin-apply2.c b/gcc/testsuite/gcc.dg/builtin-apply2.c index b39f7a0..3eadc77 100644 --- a/gcc/testsuite/gcc.dg/builtin-apply2.c +++ b/gcc/testsuite/gcc.dg/builtin-apply2.c @@ -1,6 +1,6 @@ /* { dg-do run } */ /* { dg-require-effective-target untyped_assembly } */ -/* { dg-skip-if "Variadic funcs have all args on stack. Normal funcs have args in registers." { "avr-*-* nds32*-*-*" } } */ +/* { dg-skip-if "Variadic funcs have all args on stack. Normal funcs have args in registers." { "avr-*-* nds32*-*-* amdgcn-*-*" } } */ /* { dg-skip-if "Variadic funcs use different argument passing from normal funcs." { "riscv*-*-* or1k*-*-* msp430-*-*" } } */ /* { dg-skip-if "Variadic funcs use Base AAPCS. Normal funcs use VFP variant." { arm*-*-* && arm_hf_eabi } } */ diff --git a/gcc/testsuite/gcc.dg/gimplefe-28.c b/gcc/testsuite/gcc.dg/gimplefe-28.c index 467172d..d2f6b4c 100644 --- a/gcc/testsuite/gcc.dg/gimplefe-28.c +++ b/gcc/testsuite/gcc.dg/gimplefe-28.c @@ -1,5 +1,6 @@ /* { dg-do compile { target sqrt_insn } } */ /* { dg-options "-fgimple -O2" } */ +/* { dg-add-options sqrt_insn } */ double __GIMPLE f1 (double x) diff --git a/gcc/testsuite/gcc.dg/intermod-1.c b/gcc/testsuite/gcc.dg/intermod-1.c index 9f8d19d..44a8ce0 100644 --- a/gcc/testsuite/gcc.dg/intermod-1.c +++ b/gcc/testsuite/gcc.dg/intermod-1.c @@ -1,4 +1,5 @@ /* { dg-do compile } */ +/* { dg-additional-options "-mlocal-symbol-id=" { target amdgcn-*-* } } */ /* { dg-final { scan-assembler-not {foo[1-9]\.[0-9]} } } */ /* Check that we don't get .0 suffixes on static variables when not using diff --git a/gcc/testsuite/gcc.dg/memcmp-1.c b/gcc/testsuite/gcc.dg/memcmp-1.c index 619cf9b..ea837ca 100644 --- a/gcc/testsuite/gcc.dg/memcmp-1.c +++ b/gcc/testsuite/gcc.dg/memcmp-1.c @@ -2,6 +2,7 @@ /* { dg-do run } */ /* { dg-options "-O2" } */ /* { dg-require-effective-target ptr32plus } */ +/* { dg-timeout-factor 2 } */ #include <stdio.h> #include <stdlib.h> diff --git a/gcc/testsuite/gcc.dg/pr59605-2.c b/gcc/testsuite/gcc.dg/pr59605-2.c index 6d6ff23..9575481 100644 --- a/gcc/testsuite/gcc.dg/pr59605-2.c +++ b/gcc/testsuite/gcc.dg/pr59605-2.c @@ -1,6 +1,6 @@ /* { dg-do run } */ /* { dg-options "-O2" } */ -/* { dg-additional-options "-DMAX_COPY=1025" { target { { simulator } || { nvptx-*-* } } } } */ +/* { dg-additional-options "-DMAX_COPY=1025" { target { { simulator } || { nvptx-*-* amdgcn*-*-* } } } } */ /* { dg-additional-options "-minline-stringops-dynamically" { target { i?86-*-* x86_64-*-* } } } */ #include "pr59605.c" diff --git a/gcc/testsuite/gcc.dg/sibcall-10.c b/gcc/testsuite/gcc.dg/sibcall-10.c index 4acca50..3d58036 100644 --- a/gcc/testsuite/gcc.dg/sibcall-10.c +++ b/gcc/testsuite/gcc.dg/sibcall-10.c @@ -5,7 +5,7 @@ Copyright (C) 2002 Free Software Foundation Inc. Contributed by Hans-Peter Nilsson <h...@bitrange.com> */ -/* { dg-do run { xfail { { cris-*-* crisv32-*-* csky-*-* h8300-*-* hppa*64*-*-* m32r-*-* mcore-*-* mn10300-*-* msp430*-*-* nds32*-*-* xstormy16-*-* v850*-*-* vax-*-* xtensa*-*-* } || { arm*-*-* && { ! arm32 } } } } } */ +/* { dg-do run { xfail { { amdgcn*-*-* cris-*-* crisv32-*-* csky-*-* h8300-*-* hppa*64*-*-* m32r-*-* mcore-*-* mn10300-*-* msp430*-*-* nds32*-*-* xstormy16-*-* v850*-*-* vax-*-* xtensa*-*-* } || { arm*-*-* && { ! arm32 } } } } } */ /* -mlongcall disables sibcall patterns. */ /* { dg-skip-if "" { powerpc*-*-* } { "-mlongcall" } { "" } } */ /* -msave-restore disables sibcall patterns. */ diff --git a/gcc/testsuite/gcc.dg/sibcall-9.c b/gcc/testsuite/gcc.dg/sibcall-9.c index 32b2e1d..6df671d 100644 --- a/gcc/testsuite/gcc.dg/sibcall-9.c +++ b/gcc/testsuite/gcc.dg/sibcall-9.c @@ -5,7 +5,7 @@ Copyright (C) 2002 Free Software Foundation Inc. Contributed by Hans-Peter Nilsson <h...@bitrange.com> */ -/* { dg-do run { xfail { { cris-*-* crisv32-*-* csky-*-* h8300-*-* hppa*64*-*-* m32r-*-* mcore-*-* mn10300-*-* msp430*-*-* nds32*-*-* nvptx-*-* xstormy16-*-* v850*-*-* vax-*-* xtensa*-*-* } || { arm*-*-* && { ! arm32 } } } } } */ +/* { dg-do run { xfail { { amdgcn*-*-* cris-*-* crisv32-*-* csky-*-* h8300-*-* hppa*64*-*-* m32r-*-* mcore-*-* mn10300-*-* msp430*-*-* nds32*-*-* nvptx-*-* xstormy16-*-* v850*-*-* vax-*-* xtensa*-*-* } || { arm*-*-* && { ! arm32 } } } } } */ /* -mlongcall disables sibcall patterns. */ /* { dg-skip-if "" { powerpc*-*-* } { "-mlongcall" } { "" } } */ /* -msave-restore disables sibcall patterns. */ diff --git a/gcc/testsuite/gcc.dg/torture/stackalign/builtin-apply-2.c b/gcc/testsuite/gcc.dg/torture/stackalign/builtin-apply-2.c index ecb779a..1c6fe4f 100644 --- a/gcc/testsuite/gcc.dg/torture/stackalign/builtin-apply-2.c +++ b/gcc/testsuite/gcc.dg/torture/stackalign/builtin-apply-2.c @@ -9,7 +9,7 @@ /* arm_hf_eabi: Variadic funcs use Base AAPCS. Normal funcs use VFP variant. avr: Variadic funcs don't pass arguments in registers, while normal funcs do. */ -/* { dg-skip-if "Variadic funcs use different argument passing from normal funcs" { arm_hf_eabi || { avr-*-* riscv*-*-* or1k*-*-* msp430-*-* } } } */ +/* { dg-skip-if "Variadic funcs use different argument passing from normal funcs" { arm_hf_eabi || { avr-*-* riscv*-*-* or1k*-*-* msp430-*-* amdgcn-*-* } } } */ /* { dg-skip-if "Variadic funcs have all args on stack. Normal funcs have args in registers." { nds32*-*-* } { v850*-*-* } } */ /* { dg-require-effective-target untyped_assembly } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-11c.c b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-11c.c index 236d3a5..22ff44c 100644 --- a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-11c.c +++ b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-11c.c @@ -39,4 +39,4 @@ int main () } -/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 1 "vect" } } */ +/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 1 "vect" { xfail amdgcn*-*-* } } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/loop-1.c b/gcc/testsuite/gcc.dg/tree-ssa/loop-1.c index 274f594..4b5a434 100644 --- a/gcc/testsuite/gcc.dg/tree-ssa/loop-1.c +++ b/gcc/testsuite/gcc.dg/tree-ssa/loop-1.c @@ -45,8 +45,10 @@ int xxx(void) relaxation. */ /* CRIS and MSP430 keep the address in a register. */ /* m68k sometimes puts the address in a register, depending on CPU and PIC. */ +/* AMD GCN loads symbol addresses as hi/lo pairs, and then reuses that for + each jump. */ -/* { dg-final { scan-assembler-times "foo" 5 { xfail hppa*-*-* ia64*-*-* sh*-*-* cris-*-* crisv32-*-* fido-*-* m68k-*-* i?86-*-mingw* i?86-*-cygwin* x86_64-*-mingw* visium-*-* nvptx*-*-* pdp11*-*-* msp430-*-* } } } */ +/* { dg-final { scan-assembler-times "foo" 5 { xfail hppa*-*-* ia64*-*-* sh*-*-* cris-*-* crisv32-*-* fido-*-* m68k-*-* i?86-*-mingw* i?86-*-cygwin* x86_64-*-mingw* visium-*-* nvptx*-*-* pdp11*-*-* msp430-*-* amdgcn*-*-* } } } */ /* { dg-final { scan-assembler-times "foo,%r" 5 { target hppa*-*-* } } } */ /* { dg-final { scan-assembler-times "= foo" 5 { target ia64*-*-* } } } */ /* { dg-final { scan-assembler-times "call\[ \t\]*_foo" 5 { target i?86-*-mingw* i?86-*-cygwin* } } } */ @@ -56,3 +58,5 @@ int xxx(void) /* { dg-final { scan-assembler-times "\[jb\]sr" 5 { target fido-*-* m68k-*-* pdp11-*-* } } } */ /* { dg-final { scan-assembler-times "bra *tr,r\[1-9\]*,r21" 5 { target visium-*-* } } } */ /* { dg-final { scan-assembler-times "(?n)\[ \t\]call\[ \t\].*\[ \t\]foo," 5 { target nvptx*-*-* } } } */ +/* { dg-final { scan-assembler-times "add_u32\t\[sv\]\[0-9\]*, \[sv\]\[0-9\]*, foo@rel32@lo" 1 { target { amdgcn*-*-* } } } } */ +/* { dg-final { scan-assembler-times "s_swappc_b64" 5 { target { amdgcn*-*-* } } } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr84512.c b/gcc/testsuite/gcc.dg/tree-ssa/pr84512.c index 056d1c4..3975757 100644 --- a/gcc/testsuite/gcc.dg/tree-ssa/pr84512.c +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr84512.c @@ -13,4 +13,4 @@ int foo() } /* Listed targets xfailed due to PR84958. */ -/* { dg-final { scan-tree-dump "return 285;" "optimized" { xfail { { alpha*-*-* nvptx*-*-* } || { sparc*-*-* && lp64 } } } } } */ +/* { dg-final { scan-tree-dump "return 285;" "optimized" { xfail { { alpha*-*-* amdgcn*-*-* nvptx*-*-* } || { sparc*-*-* && lp64 } } } } } */ diff --git a/gcc/testsuite/gfortran.dg/bind_c_array_params_2.f90 b/gcc/testsuite/gfortran.dg/bind_c_array_params_2.f90 index 25f5dda..34ed055 100644 --- a/gcc/testsuite/gfortran.dg/bind_c_array_params_2.f90 +++ b/gcc/testsuite/gfortran.dg/bind_c_array_params_2.f90 @@ -16,8 +16,9 @@ integer :: aa(4,4) call test(aa) end -! { dg-final { scan-assembler-times "\[ \t\]\[$,_0-9\]*myBindC" 1 { target { ! { hppa*-*-* s390*-*-* *-*-cygwin* } } } } } +! { dg-final { scan-assembler-times "\[ \t\]\[$,_0-9\]*myBindC" 1 { target { ! { hppa*-*-* s390*-*-* *-*-cygwin* amdgcn*-*-* } } } } } ! { dg-final { scan-assembler-times "myBindC,%r2" 1 { target { hppa*-*-* } } } } ! { dg-final { scan-assembler-times "call\tmyBindC" 1 { target { *-*-cygwin* } } } } ! { dg-final { scan-assembler-times "brasl\t%r\[0-9\]*,myBindC" 1 { target { s390*-*-* } } } } +! { dg-final { scan-assembler-times "add_u32\t\[sv\]\[0-9\]*, \[sv\]\[0-9\]*, myBindC@rel32@lo" 1 { target { amdgcn*-*-* } } } } ! { dg-final { scan-tree-dump-times "test \\\(&parm\\." 1 "original" } } diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp index 98ff90e..e46343a 100644 --- a/gcc/testsuite/lib/target-supports.exp +++ b/gcc/testsuite/lib/target-supports.exp @@ -659,6 +659,7 @@ proc check_profiling_available { test_what } { # missing other needed machinery. if {[istarget aarch64*-*-elf] || [istarget am3*-*-linux*] + || [istarget amdgcn-*-*] || [istarget arm*-*-eabi*] || [istarget arm*-*-elf] || [istarget arm*-*-symbianelf*] @@ -784,6 +785,9 @@ proc check_effective_target_global_constructor {} { if { [istarget nvptx-*-*] } { return 0 } + if { [istarget amdgcn-*-*] } { + return 0 + } return 1 } @@ -804,6 +808,10 @@ proc check_effective_target_return_address {} { if { [istarget nvptx-*-*] } { return 0 } + # It could be supported on amdgcn, but isn't yet. + if { [istarget amdgcn*-*-*] } { + return 0 + } return 1 } @@ -945,9 +953,10 @@ proc check_effective_target_fgraphite {} { # code, 0 otherwise. proc check_effective_target_fopenacc {} { - # nvptx can be built with the device-side bits of openacc, but it + # nvptx/amdgcn can be built with the device-side bits of openacc, but it # does not make sense to test it as an openacc host. if [istarget nvptx-*-*] { return 0 } + if [istarget amdgcn-*-*] { return 0 } return [check_no_compiler_messages fopenacc object { void foo (void) { } @@ -958,9 +967,10 @@ proc check_effective_target_fopenacc {} { # code, 0 otherwise. proc check_effective_target_fopenmp {} { - # nvptx can be built with the device-side bits of libgomp, but it + # nvptx/amdgcn can be built with the device-side bits of libgomp, but it # does not make sense to test it as an openmp host. if [istarget nvptx-*-*] { return 0 } + if [istarget amdgcn-*-*] { return 0 } return [check_no_compiler_messages fopenmp object { void foo (void) { } @@ -3122,6 +3132,7 @@ proc check_effective_target_vect_int { } { [istarget i?86-*-*] || [istarget x86_64-*-*] || ([istarget powerpc*-*-*] && ![istarget powerpc-*-linux*paired*]) + || [istarget amdgcn-*-*] || [istarget spu-*-*] || [istarget sparc*-*-*] || [istarget alpha*-*-*] @@ -3146,7 +3157,8 @@ proc check_effective_target_vect_intfloat_cvt { } { && ![istarget powerpc-*-linux*paired*]) || [is-effective-target arm_neon] || ([istarget mips*-*-*] - && [et-is-effective-target mips_msa]) }}] + && [et-is-effective-target mips_msa]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports signed double->int conversion @@ -3210,7 +3222,8 @@ proc check_effective_target_vect_uintfloat_cvt { } { || [istarget aarch64*-*-*] || [is-effective-target arm_neon] || ([istarget mips*-*-*] - && [et-is-effective-target mips_msa]) }}] + && [et-is-effective-target mips_msa]) + || [istarget amdgcn-*-*] }}] } @@ -3224,7 +3237,8 @@ proc check_effective_target_vect_floatint_cvt { } { && ![istarget powerpc-*-linux*paired*]) || [is-effective-target arm_neon] || ([istarget mips*-*-*] - && [et-is-effective-target mips_msa]) }}] + && [et-is-effective-target mips_msa]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports unsigned float->int conversion @@ -3236,7 +3250,8 @@ proc check_effective_target_vect_floatuint_cvt { } { && ![istarget powerpc-*-linux*paired*]) || [is-effective-target arm_neon] || ([istarget mips*-*-*] - && [et-is-effective-target mips_msa]) }}] + && [et-is-effective-target mips_msa]) + || [istarget amdgcn-*-*] }}] } # Return 1 if peeling for alignment might be profitable on the target @@ -3260,7 +3275,8 @@ proc check_effective_target_vect_simd_clones { } { # be able to assemble avx512f. return [check_cached_effective_target_indexed vect_simd_clones { expr { (([istarget i?86-*-*] || [istarget x86_64-*-*]) - && [check_effective_target_avx512f]) }}] + && [check_effective_target_avx512f]) + || [istarget amdgcn-*-*] }}] } # Return 1 if this is a AArch64 target supporting big endian @@ -5371,7 +5387,8 @@ proc check_effective_target_vect_shift { } { && ([et-is-effective-target mips_msa] || [et-is-effective-target mips_loongson_mmi])) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports hardware vector shift by register operation. @@ -5393,7 +5410,8 @@ proc check_effective_target_whole_vector_shift { } { || ([istarget mips*-*-*] && [et-is-effective-target mips_loongson_mmi]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) } { + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] } { set answer 1 } else { set answer 0 @@ -5407,7 +5425,9 @@ proc check_effective_target_whole_vector_shift { } { proc check_effective_target_vect_bswap { } { return [check_cached_effective_target_indexed vect_bswap { - expr { [istarget aarch64*-*-*] || [is-effective-target arm_neon] }}] + expr { [istarget aarch64*-*-*] + || [is-effective-target arm_neon] + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports hardware vector shift operation for char. @@ -5420,7 +5440,8 @@ proc check_effective_target_vect_shift_char { } { || ([istarget mips*-*-*] && [et-is-effective-target mips_msa]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports hardware vectors of long, 0 otherwise. @@ -5438,7 +5459,8 @@ proc check_effective_target_vect_long { } { || ([istarget mips*-*-*] && [et-is-effective-target mips_msa]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) } { + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] } { set answer 1 } else { set answer 0 @@ -5466,7 +5488,8 @@ proc check_effective_target_vect_float { } { && [et-is-effective-target mips_msa]) || [is-effective-target arm_neon] || ([istarget s390*-*-*] - && [check_effective_target_s390_vxe]) }}] + && [check_effective_target_s390_vxe]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports hardware vectors of float without @@ -5495,7 +5518,8 @@ proc check_effective_target_vect_double { } { || ([istarget mips*-*-*] && [et-is-effective-target mips_msa]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx])} }] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*]} }] } # Return 1 if the target supports conditional addition, subtraction, @@ -5570,7 +5594,8 @@ proc check_effective_target_vect_perm { } { && ([et-is-effective-target mpaired_single] || [et-is-effective-target mips_msa])) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if, for some VF: @@ -5663,7 +5688,8 @@ proc check_effective_target_vect_perm_byte { } { || ([istarget mips-*.*] && [et-is-effective-target mips_msa]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports SLP permutation of 3 vectors when each @@ -5692,7 +5718,8 @@ proc check_effective_target_vect_perm_short { } { || ([istarget mips*-*-*] && [et-is-effective-target mips_msa]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports SLP permutation of 3 vectors when each @@ -5783,7 +5810,8 @@ proc check_effective_target_vect_widen_mult_qi_to_hi { } { && ![check_effective_target_aarch64_sve]) || [is-effective-target arm_neon] || ([istarget s390*-*-*] - && [check_effective_target_s390_vx])) }}] + && [check_effective_target_s390_vx])) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target plus current options supports a vector @@ -5807,7 +5835,8 @@ proc check_effective_target_vect_widen_mult_hi_to_si { } { || [istarget i?86-*-*] || [istarget x86_64-*-*] || [is-effective-target arm_neon] || ([istarget s390*-*-*] - && [check_effective_target_s390_vx])) }}] + && [check_effective_target_s390_vx])) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target plus current options supports a vector @@ -5821,7 +5850,8 @@ proc check_effective_target_vect_widen_mult_qi_to_hi_pattern { } { || ([is-effective-target arm_neon] && [check_effective_target_arm_little_endian]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target plus current options supports a vector @@ -5838,7 +5868,8 @@ proc check_effective_target_vect_widen_mult_hi_to_si_pattern { } { || ([is-effective-target arm_neon] && [check_effective_target_arm_little_endian]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target plus current options supports a vector @@ -6079,7 +6110,8 @@ proc check_effective_target_vect_natural_alignment { } { set et_vect_natural_alignment 1 if { [check_effective_target_arm_eabi] || [istarget nvptx-*-*] - || [istarget s390*-*-*] } { + || [istarget s390*-*-*] + || [istarget amdgcn-*-*] } { set et_vect_natural_alignment 0 } verbose "check_effective_target_vect_natural_alignment:\ @@ -6090,7 +6122,8 @@ proc check_effective_target_vect_natural_alignment { } { # Return true if fully-masked loops are supported. proc check_effective_target_vect_fully_masked { } { - return [check_effective_target_aarch64_sve] + return [expr { [check_effective_target_aarch64_sve] + || [istarget amdgcn*-*-*] }] } # Return 1 if the target doesn't prefer any alignment beyond element @@ -6142,7 +6175,8 @@ proc check_effective_target_vect_element_align { } { return [check_cached_effective_target_indexed vect_element_align { expr { ([istarget arm*-*-*] && ![check_effective_target_arm_vect_no_misalign]) - || [check_effective_target_vect_hw_misalign] }}] + || [check_effective_target_vect_hw_misalign] + || [istarget amdgcn-*-*] }}] } # Return 1 if we expect to see unaligned accesses in at least some @@ -6167,13 +6201,15 @@ proc check_effective_target_vect_load_lanes { } { # Return 1 if the target supports vector masked stores. proc check_effective_target_vect_masked_store { } { - return [check_effective_target_aarch64_sve] + return [expr { [check_effective_target_aarch64_sve] + || [istarget amdgcn*-*-*] }] } # Return 1 if the target supports vector scatter stores. proc check_effective_target_vect_scatter_store { } { - return [check_effective_target_aarch64_sve] + return [expr { [check_effective_target_aarch64_sve] + || [istarget amdgcn*-*-*] }] } # Return 1 if the target supports vector conditional operations, 0 otherwise. @@ -6190,7 +6226,8 @@ proc check_effective_target_vect_condition { } { || ([istarget arm*-*-*] && [check_effective_target_arm_neon_ok]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports vector conditional operations where @@ -6204,7 +6241,8 @@ proc check_effective_target_vect_cond_mixed { } { || ([istarget mips*-*-*] && [et-is-effective-target mips_msa]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports vector char multiplication, 0 otherwise. @@ -6219,7 +6257,8 @@ proc check_effective_target_vect_char_mult { } { || ([istarget mips*-*-*] && [et-is-effective-target mips_msa]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports vector short multiplication, 0 otherwise. @@ -6236,7 +6275,8 @@ proc check_effective_target_vect_short_mult { } { && ([et-is-effective-target mips_msa] || [et-is-effective-target mips_loongson_mmi])) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports vector int multiplication, 0 otherwise. @@ -6252,7 +6292,8 @@ proc check_effective_target_vect_int_mult { } { && [et-is-effective-target mips_msa]) || [check_effective_target_arm32] || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports 64 bit hardware vector @@ -6327,6 +6368,9 @@ foreach N {2 3 4 8} { || [istarget aarch64*-*-*]) && N >= 2 && N <= 4 } { return 1 } + if [check_effective_target_vect_fully_masked] { + return 1 + } return 0 }] } @@ -6394,7 +6438,17 @@ proc check_effective_target_sqrt_insn { } { || [istarget aarch64*-*-*] || ([istarget arm*-*-*] && [check_effective_target_arm_vfp_ok]) || ([istarget s390*-*-*] - && [check_effective_target_s390_vx]) }}] + && [check_effective_target_s390_vx]) + || [istarget amdgcn-*-*] }}] +} + +# Return any additional options to enable square root intructions. + +proc add_options_for_sqrt_insn { flags } { + if { [istarget amdgcn*-*-*] } { + return "$flags -ffast-math" + } + return $flags } # Return 1 if the target supports vector sqrtf calls. @@ -6413,7 +6467,8 @@ proc check_effective_target_vect_call_sqrtf { } { proc check_effective_target_vect_call_lrint { } { set et_vect_call_lrint 0 if { (([istarget i?86-*-*] || [istarget x86_64-*-*]) - && [check_effective_target_ilp32]) } { + && [check_effective_target_ilp32]) + || [istarget amdgcn-*-*] } { set et_vect_call_lrint 1 } @@ -6425,21 +6480,24 @@ proc check_effective_target_vect_call_lrint { } { proc check_effective_target_vect_call_btrunc { } { return [check_cached_effective_target_indexed vect_call_btrunc { - expr { [istarget aarch64*-*-*] }}] + expr { [istarget aarch64*-*-*] + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports vector btruncf calls. proc check_effective_target_vect_call_btruncf { } { return [check_cached_effective_target_indexed vect_call_btruncf { - expr { [istarget aarch64*-*-*] }}] + expr { [istarget aarch64*-*-*] + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports vector ceil calls. proc check_effective_target_vect_call_ceil { } { return [check_cached_effective_target_indexed vect_call_ceil { - expr { [istarget aarch64*-*-*] }}] + expr { [istarget aarch64*-*-*] + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports vector ceilf calls. @@ -6460,7 +6518,8 @@ proc check_effective_target_vect_call_floor { } { proc check_effective_target_vect_call_floorf { } { return [check_cached_effective_target_indexed vect_call_floorf { - expr { [istarget aarch64*-*-*] }}] + expr { [istarget aarch64*-*-*] + || [istarget amdgcn-*-*] }}] } # Return 1 if the target supports vector lceil calls. @@ -8007,7 +8066,8 @@ proc check_effective_target_gld { } { # (LTO) support. proc check_effective_target_lto { } { - if { [istarget nvptx-*-*] } { + if { [istarget nvptx-*-*] + || [istarget amdgcn-*-*] } { return 0; } return [check_no_compiler_messages lto object { @@ -8325,6 +8385,8 @@ proc check_vect_support_and_set_flags { } { lappend DEFAULT_VECTCFLAGS "-march=z14" "-mzarch" set dg-do-what-default compile } + } elseif [istarget amdgcn-*-*] { + set dg-do-what-default run } else { return 0 }