diff mbox series

amdgcn: Add gfx1036 target

Message ID 20240325112735.2F0863858410@sourceware.org
State New
Headers show
Series amdgcn: Add gfx1036 target | expand

Commit Message

Richard Biener March 25, 2024, 11:27 a.m. UTC 
Add support for the gfx1036 RDNA2 APU integrated graphics devices.  The ROCm
documentation warns that these may not be supported, but it seems to work
at least partially.

x86 host bootstrap/regtest running, target-libgomp testing for the
offload produces results comparable to those of gfx1030.  The nice
thing is that gfx1036 is inside every Zen4 desktop CPU (Ryzen 7xxx)
and testing on that doesn't interfere with a separate GPU used for
your desktop (where I experienced crashes when using the GPU for both
offload and graphics).

I'll note that while gfx1030 works with llvm14 gfx1036 needs llvm15
as minimum version for the assembler.

OK for trunk?

I'll follow up with the libgomp testing test summary for archival
purposes.  I still see linker errors for testcases using -g
(the ld: ^[[0;31merror: ^[[0mincompatible mach: 
/tmp/ccr0oDpD.mkoffload.dbg.o^M kind)

Thanks,
Richard.

gcc/ChangeLog:

	* config.gcc (amdgcn): Add gfx1036 entries.
	* config/gcn/gcn-hsa.h (NO_XNACK): Likewise.
	(gcn_local_sym_hash): Likewise.
	* config/gcn/gcn-opts.h (enum processor_type): Likewise.
	(TARGET_GFX1036): New macro.
	* config/gcn/gcn.cc (gcn_option_override): Handle gfx1036.
	(gcn_omp_device_kind_arch_isa): Likewise.
	(output_file_start): Likewise.
	* config/gcn/gcn.h (TARGET_CPU_CPP_BUILTINS): Add __gfx1036__.
	(TARGET_CPU_CPP_BUILTINS): Rename __gfx1030 to __gfx1030__.
	* config/gcn/gcn.opt: Add gfx1036.
	* config/gcn/mkoffload.cc (EF_AMDGPU_MACH_AMDGCN_GFX1036): New.
	(main): Handle gfx1036.
	* config/gcn/t-omp-device: Add gfx1036 isa.
	* doc/install.texi (amdgcn): Add gfx1036.
	* doc/invoke.texi (-march): Likewise.

libgomp/ChangeLog:

	* plugin/plugin-gcn.c (EF_AMDGPU_MACH): GFX1036.
	(gcn_gfx1103_s): New.
	(isa_hsa_name): Handle gfx1036.
	(isa_code): Likewise.
	(max_isa_vgprs): Likewise.
---
 gcc/config.gcc              |  4 ++--
 gcc/config/gcn/gcn-hsa.h    |  6 +++---
 gcc/config/gcn/gcn-opts.h   |  2 ++
 gcc/config/gcn/gcn.cc       | 10 ++++++++++
 gcc/config/gcn/gcn.h        |  4 +++-
 gcc/config/gcn/gcn.opt      |  3 +++
 gcc/config/gcn/mkoffload.cc |  5 +++++
 gcc/config/gcn/t-omp-device |  2 +-
 gcc/doc/install.texi        |  3 ++-
 gcc/doc/invoke.texi         |  3 +++
 libgomp/plugin/plugin-gcn.c |  8 ++++++++
 11 files changed, 42 insertions(+), 8 deletions(-)
diff mbox series

Patch

diff --git a/gcc/config.gcc b/gcc/config.gcc
index 87a5c92b6e3..17873ac2103 100644
--- a/gcc/config.gcc
+++ b/gcc/config.gcc
@@ -4560,7 +4560,7 @@  case "${target}" in
 		for which in arch tune; do
 			eval "val=\$with_$which"
 			case ${val} in
-			"" | fiji | gfx900 | gfx906 | gfx908 | gfx90a | gfx1030 | gfx1100 | gfx1103)
+			"" | fiji | gfx900 | gfx906 | gfx908 | gfx90a | gfx1030 | gfx1036 | gfx1100 | gfx1103)
 				# OK
 				;;
 			*)
@@ -4576,7 +4576,7 @@  case "${target}" in
 			TM_MULTILIB_CONFIG=
 			;;
 		xdefault | xyes)
-			TM_MULTILIB_CONFIG=`echo "gfx900,gfx906,gfx908,gfx90a,gfx1030,gfx1100,gfx1103" | sed "s/${with_arch},\?//;s/,$//"`
+			TM_MULTILIB_CONFIG=`echo "gfx900,gfx906,gfx908,gfx90a,gfx1030,gfx1036,gfx1100,gfx1103" | sed "s/${with_arch},\?//;s/,$//"`
 			;;
 		*)
 			TM_MULTILIB_CONFIG="${with_multilib_list}"
diff --git a/gcc/config/gcn/gcn-hsa.h b/gcc/config/gcn/gcn-hsa.h
index ac32b8a328f..7d6e3141cea 100644
--- a/gcc/config/gcn/gcn-hsa.h
+++ b/gcc/config/gcn/gcn-hsa.h
@@ -90,7 +90,7 @@  extern unsigned int gcn_local_sym_hash (const char *name);
    the ELF flags (e_flags) of that generated file must be identical to those
    generated by the compiler.  */
 
-#define NO_XNACK "march=fiji:;march=gfx1030:;march=gfx1100:;march=gfx1103:;" \
+#define NO_XNACK "march=fiji:;march=gfx1030:;march=gfx1036:;march=gfx1100:;march=gfx1103:;" \
     /* These match the defaults set in gcn.cc.  */ \
     "!mxnack*|mxnack=default:%{march=gfx900|march=gfx906|march=gfx908:-mattr=-xnack};"
 #define NO_SRAM_ECC "!march=*:;march=fiji:;march=gfx900:;march=gfx906:;"
@@ -106,8 +106,8 @@  extern unsigned int gcn_local_sym_hash (const char *name);
 		  "%{" ABI_VERSION_SPEC "} " \
 		  "%{" NO_XNACK XNACKOPT "} " \
 		  "%{" NO_SRAM_ECC SRAMOPT "} " \
-		  "%{march=gfx1030|march=gfx1100|march=gfx1103:-mattr=+wavefrontsize64} " \
-		  "%{march=gfx1030|march=gfx1100|march=gfx1103:-mattr=+cumode} " \
+		  "%{march=gfx1030|march=gfx1036|march=gfx1100|march=gfx1103:-mattr=+wavefrontsize64} " \
+		  "%{march=gfx1030|march=gfx1036|march=gfx1100|march=gfx1103:-mattr=+cumode} " \
 		  "-filetype=obj"
 #define LINK_SPEC "--pie --export-dynamic"
 #define LIB_SPEC  "-lc"
diff --git a/gcc/config/gcn/gcn-opts.h b/gcc/config/gcn/gcn-opts.h
index 285746f7f4d..49099bad7e7 100644
--- a/gcc/config/gcn/gcn-opts.h
+++ b/gcc/config/gcn/gcn-opts.h
@@ -26,6 +26,7 @@  enum processor_type
   PROCESSOR_GFX908,
   PROCESSOR_GFX90a,
   PROCESSOR_GFX1030,
+  PROCESSOR_GFX1036,
   PROCESSOR_GFX1100,
   PROCESSOR_GFX1103
 };
@@ -36,6 +37,7 @@  enum processor_type
 #define TARGET_GFX908 (gcn_arch == PROCESSOR_GFX908)
 #define TARGET_GFX90a (gcn_arch == PROCESSOR_GFX90a)
 #define TARGET_GFX1030 (gcn_arch == PROCESSOR_GFX1030)
+#define TARGET_GFX1036 (gcn_arch == PROCESSOR_GFX1036)
 #define TARGET_GFX1100 (gcn_arch == PROCESSOR_GFX1100)
 #define TARGET_GFX1103 (gcn_arch == PROCESSOR_GFX1103)
 
diff --git a/gcc/config/gcn/gcn.cc b/gcc/config/gcn/gcn.cc
index efb73af50c4..700e554855e 100644
--- a/gcc/config/gcn/gcn.cc
+++ b/gcc/config/gcn/gcn.cc
@@ -139,6 +139,7 @@  gcn_option_override (void)
       : gcn_arch == PROCESSOR_GFX908 ? ISA_CDNA1
       : gcn_arch == PROCESSOR_GFX90a ? ISA_CDNA2
       : gcn_arch == PROCESSOR_GFX1030 ? ISA_RDNA2
+      : gcn_arch == PROCESSOR_GFX1036 ? ISA_RDNA2
       : gcn_arch == PROCESSOR_GFX1100 ? ISA_RDNA3
       : gcn_arch == PROCESSOR_GFX1103 ? ISA_RDNA3
       : ISA_UNKNOWN);
@@ -165,6 +166,7 @@  gcn_option_override (void)
   /* gfx803 "Fiji", gfx1030 and gfx1100 do not support XNACK.  */
   if (gcn_arch == PROCESSOR_FIJI
       || gcn_arch == PROCESSOR_GFX1030
+      || gcn_arch == PROCESSOR_GFX1036
       || gcn_arch == PROCESSOR_GFX1100
       || gcn_arch == PROCESSOR_GFX1103)
     {
@@ -172,6 +174,7 @@  gcn_option_override (void)
 	error ("%<-mxnack=on%> is incompatible with %<-march=%s%>",
 	       (gcn_arch == PROCESSOR_FIJI ? "fiji"
 		: gcn_arch == PROCESSOR_GFX1030 ? "gfx1030"
+		: gcn_arch == PROCESSOR_GFX1036 ? "gfx1036"
 		: gcn_arch == PROCESSOR_GFX1100 ? "gfx1100"
 		: gcn_arch == PROCESSOR_GFX1103 ? "gfx1103"
 		: NULL));
@@ -3049,6 +3052,8 @@  gcn_omp_device_kind_arch_isa (enum omp_device_kind_arch_isa trait,
 	return gcn_arch == PROCESSOR_GFX90a;
       if (strcmp (name, "gfx1030") == 0)
 	return gcn_arch == PROCESSOR_GFX1030;
+      if (strcmp (name, "gfx1036") == 0)
+	return gcn_arch == PROCESSOR_GFX1036;
       if (strcmp (name, "gfx1100") == 0)
 	return gcn_arch == PROCESSOR_GFX1100;
       if (strcmp (name, "gfx1103") == 0)
@@ -6584,6 +6589,11 @@  output_file_start (void)
       xnack = "";
       sram_ecc = "";
       break;
+    case PROCESSOR_GFX1036:
+      cpu = "gfx1036";
+      xnack = "";
+      sram_ecc = "";
+      break;
     case PROCESSOR_GFX1100:
       cpu = "gfx1100";
       xnack = "";
diff --git a/gcc/config/gcn/gcn.h b/gcc/config/gcn/gcn.h
index b003db6cd26..4148ceaf582 100644
--- a/gcc/config/gcn/gcn.h
+++ b/gcc/config/gcn/gcn.h
@@ -48,7 +48,9 @@ 
       else if (TARGET_GFX90a)                                                  \
 	builtin_define ("__gfx90a__");                                         \
       else if (TARGET_GFX1030)                                                 \
-	builtin_define ("__gfx1030");                                          \
+	builtin_define ("__gfx1030__");                                        \
+      else if (TARGET_GFX1036)                                                 \
+	builtin_define ("__gfx1036__");                                        \
       else if (TARGET_GFX1100)                                                 \
 	builtin_define ("__gfx1100__");                                        \
       else if (TARGET_GFX1103)                                                 \
diff --git a/gcc/config/gcn/gcn.opt b/gcc/config/gcn/gcn.opt
index e06a2849d90..1067b45f294 100644
--- a/gcc/config/gcn/gcn.opt
+++ b/gcc/config/gcn/gcn.opt
@@ -43,6 +43,9 @@  Enum(gpu_type) String(gfx90a) Value(PROCESSOR_GFX90a)
 EnumValue
 Enum(gpu_type) String(gfx1030) Value(PROCESSOR_GFX1030)
 
+EnumValue
+Enum(gpu_type) String(gfx1036) Value(PROCESSOR_GFX1036)
+
 EnumValue
 Enum(gpu_type) String(gfx1100) Value(PROCESSOR_GFX1100)
 
diff --git a/gcc/config/gcn/mkoffload.cc b/gcc/config/gcn/mkoffload.cc
index 58eeada8295..04356b86195 100644
--- a/gcc/config/gcn/mkoffload.cc
+++ b/gcc/config/gcn/mkoffload.cc
@@ -59,6 +59,8 @@ 
 #define EF_AMDGPU_MACH_AMDGCN_GFX90a 0x3f
 #undef  EF_AMDGPU_MACH_AMDGCN_GFX1030
 #define EF_AMDGPU_MACH_AMDGCN_GFX1030 0x36
+#undef  EF_AMDGPU_MACH_AMDGCN_GFX1036
+#define EF_AMDGPU_MACH_AMDGCN_GFX1036 0x45
 #undef  EF_AMDGPU_MACH_AMDGCN_GFX1100
 #define EF_AMDGPU_MACH_AMDGCN_GFX1100 0x41
 #undef  EF_AMDGPU_MACH_AMDGCN_GFX1103
@@ -971,6 +973,8 @@  main (int argc, char **argv)
 	elf_arch = EF_AMDGPU_MACH_AMDGCN_GFX90a;
       else if (strcmp (argv[i], "-march=gfx1030") == 0)
 	elf_arch = EF_AMDGPU_MACH_AMDGCN_GFX1030;
+      else if (strcmp (argv[i], "-march=gfx1036") == 0)
+	elf_arch = EF_AMDGPU_MACH_AMDGCN_GFX1036;
       else if (strcmp (argv[i], "-march=gfx1100") == 0)
 	elf_arch = EF_AMDGPU_MACH_AMDGCN_GFX1100;
       else if (strcmp (argv[i], "-march=gfx1103") == 0)
@@ -1016,6 +1020,7 @@  main (int argc, char **argv)
     {
     case EF_AMDGPU_MACH_AMDGCN_GFX803:
     case EF_AMDGPU_MACH_AMDGCN_GFX1030:
+    case EF_AMDGPU_MACH_AMDGCN_GFX1036:
     case EF_AMDGPU_MACH_AMDGCN_GFX1100:
     case EF_AMDGPU_MACH_AMDGCN_GFX1103:
       SET_XNACK_UNSET (elf_flags);
diff --git a/gcc/config/gcn/t-omp-device b/gcc/config/gcn/t-omp-device
index 037df2657cc..7bcf910cbd0 100644
--- a/gcc/config/gcn/t-omp-device
+++ b/gcc/config/gcn/t-omp-device
@@ -1,4 +1,4 @@ 
 omp-device-properties-gcn: $(srcdir)/config/gcn/gcn.cc
 	echo kind: gpu > $@
 	echo arch: amdgcn gcn >> $@
-	echo isa: fiji gfx803 gfx900 gfx906 gfx908 gfx90a gfx1030 gfx1100 gfx1103 >> $@
+	echo isa: fiji gfx803 gfx900 gfx906 gfx908 gfx90a gfx1030 gfx1036 gfx1100 gfx1103 >> $@
diff --git a/gcc/doc/install.texi b/gcc/doc/install.texi
index a9872e86bee..269fe7ec870 100644
--- a/gcc/doc/install.texi
+++ b/gcc/doc/install.texi
@@ -1266,7 +1266,8 @@  default set of libraries is selected based on the value of
 @item amdgcn*-*-*
 @var{list} is a comma separated list of ISA names (allowed values: @code{fiji},
 @code{gfx900}, @code{gfx906}, @code{gfx908}, @code{gfx90a}, @code{gfx1030},
-@code{gfx1100}, @code{gfx1103}).  It ought not include the name of the default
+@code{gfx1036}, @code{gfx1100}, @code{gfx1103}).
+It ought not include the name of the default
 ISA, specified via @option{--with-arch}.  If @var{list} is empty, then there
 will be no multilibs and only the default run-time library will be built.  If
 @var{list} is @code{default} or @option{--with-multilib-list=} is not
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index e7b96212354..d09074e13de 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -21792,6 +21792,9 @@  Compile for CDNA2 Instinct MI200 series devices (gfx90a).
 @item gfx1030
 Compile for RDNA2 gfx1030 devices (GFX10 series).
 
+@item gfx1036
+Compile for RDNA2 gfx1036 devices (GFX10 series).
+
 @item gfx1100
 Compile for RDNA3 gfx1100 devices (GFX11 series).
 
diff --git a/libgomp/plugin/plugin-gcn.c b/libgomp/plugin/plugin-gcn.c
index 53dc1c7d23a..1d183b61ca4 100644
--- a/libgomp/plugin/plugin-gcn.c
+++ b/libgomp/plugin/plugin-gcn.c
@@ -391,6 +391,7 @@  typedef enum {
   EF_AMDGPU_MACH_AMDGCN_GFX908 = 0x030,
   EF_AMDGPU_MACH_AMDGCN_GFX90a = 0x03f,
   EF_AMDGPU_MACH_AMDGCN_GFX1030 = 0x036,
+  EF_AMDGPU_MACH_AMDGCN_GFX1036 = 0x045,
   EF_AMDGPU_MACH_AMDGCN_GFX1100 = 0x041,
   EF_AMDGPU_MACH_AMDGCN_GFX1103 = 0x044
 } EF_AMDGPU_MACH;
@@ -1677,6 +1678,7 @@  const static char *gcn_gfx906_s = "gfx906";
 const static char *gcn_gfx908_s = "gfx908";
 const static char *gcn_gfx90a_s = "gfx90a";
 const static char *gcn_gfx1030_s = "gfx1030";
+const static char *gcn_gfx1036_s = "gfx1036";
 const static char *gcn_gfx1100_s = "gfx1100";
 const static char *gcn_gfx1103_s = "gfx1103";
 const static int gcn_isa_name_len = 7;
@@ -1700,6 +1702,8 @@  isa_hsa_name (int isa) {
       return gcn_gfx90a_s;
     case EF_AMDGPU_MACH_AMDGCN_GFX1030:
       return gcn_gfx1030_s;
+    case EF_AMDGPU_MACH_AMDGCN_GFX1036:
+      return gcn_gfx1036_s;
     case EF_AMDGPU_MACH_AMDGCN_GFX1100:
       return gcn_gfx1100_s;
     case EF_AMDGPU_MACH_AMDGCN_GFX1103:
@@ -1746,6 +1750,9 @@  isa_code(const char *isa) {
   if (!strncmp (isa, gcn_gfx1030_s, gcn_isa_name_len))
     return EF_AMDGPU_MACH_AMDGCN_GFX1030;
 
+  if (!strncmp (isa, gcn_gfx1036_s, gcn_isa_name_len))
+    return EF_AMDGPU_MACH_AMDGCN_GFX1036;
+
   if (!strncmp (isa, gcn_gfx1100_s, gcn_isa_name_len))
     return EF_AMDGPU_MACH_AMDGCN_GFX1100;
 
@@ -1770,6 +1777,7 @@  max_isa_vgprs (int isa)
     case EF_AMDGPU_MACH_AMDGCN_GFX90a:
       return 512;
     case EF_AMDGPU_MACH_AMDGCN_GFX1030:
+    case EF_AMDGPU_MACH_AMDGCN_GFX1036:
       return 512;  /* 512 SIMD32 = 256 wavefrontsize64.  */
     case EF_AMDGPU_MACH_AMDGCN_GFX1100:
     case EF_AMDGPU_MACH_AMDGCN_GFX1103: