File 0002-add-generic-gpu-targets.patch of Package rocblas
From 60c8c0786b61e1ab2040f7b6d7b6c2b4b244c9e1 Mon Sep 17 00:00:00 2001
From: Tom Rix <Tom.Rix@amd.com>
Date: Sun, 8 Mar 2026 01:32:28 +0000
Subject: [PATCH 2/6] add generic gpu targets
To support generic gpu targets ex/ -DGPU_TARGETS=gfx11-generic.
Tensile does not have support for every possible gpu target. Instead
of adding then piecement, provide support for all the generic targets.
In Common.py overload int tuple for SupportedISA, where if the last
value is negative, then this is a generic isa.
Ex
(10,3,-1) -> gfx10-3-generic
(11,0,-1) -> gfx11-generic
In AsmCaps, cut-n-paste generic tables from a close existing table.
ex/ (10,3,0) was used of (10,3,-1). Then fix the values based on
the derrived vs cached warnings during a build.
Add new mapping where appropriate.
Signed-off-by: Tom Rix <Tom.Rix@amd.com>
---
shared/tensile/Tensile/AsmCaps.py | 264 ++++++++++++++++++
shared/tensile/Tensile/Common.py | 57 +++-
.../cmake/TensileSupportedArchitectures.cmake | 9 +-
.../Source/lib/include/Tensile/AMDGPU.hpp | 44 ++-
.../include/Tensile/PlaceholderLibrary.hpp | 18 ++
5 files changed, 375 insertions(+), 17 deletions(-)
diff --git a/shared/tensile/Tensile/AsmCaps.py b/shared/tensile/Tensile/AsmCaps.py
index 48eeec1f9a6c..58776e249b78 100644
--- a/shared/tensile/Tensile/AsmCaps.py
+++ b/shared/tensile/Tensile/AsmCaps.py
@@ -169,6 +169,50 @@ def getCapabilitiesCache(rocmVersion: NamedTuple) -> dict:
'v_mov_b64': False,
'v_pk_fma_f16': True,
'v_pk_fmac_f16': False},
+ (9, 0, -1): {'HasAddLshl': True,
+ 'HasAtomicAdd': False,
+ 'HasDirectToLdsDest': False,
+ 'HasDirectToLdsNoDest': True,
+ 'HasExplicitCO': True,
+ 'HasExplicitNC': False,
+ 'HasGLCModifier': True,
+ 'HasNTModifier': False,
+ 'HasLshlOr': True,
+ 'HasMFMA': False,
+ 'HasMFMA_b8': False,
+ 'HasMFMA_bf16_1k': False,
+ 'HasMFMA_bf16_original': False,
+ 'HasMFMA_constSrc': False,
+ 'HasMFMA_f64': False,
+ 'HasMFMA_f8': False,
+ 'HasMFMA_i8_908': False,
+ 'HasMFMA_i8_940': False,
+ 'HasMFMA_vgpr': False,
+ 'HasMFMA_xf32': False,
+ 'HasSMulHi': True,
+ 'HasWMMA': False,
+ 'KernargPreloading': False,
+ 'MaxLgkmcnt': 15,
+ 'MaxVmcnt': 63,
+ 'SupportedISA': True,
+ 'SupportedSource': True,
+ 'VOP3v_dot4_i32_i8': False,
+ 'v_dot2_f32_f16': False,
+ 'v_dot2c_f32_f16': False,
+ 'v_dot4_i32_i8': False,
+ 'v_dot4c_i32_i8': False,
+ 'v_fma_f16': True,
+ 'v_fma_f32': True,
+ 'v_fma_f64': True,
+ 'v_fma_mix_f32': False,
+ 'v_fmac_f16': False,
+ 'v_fmac_f32': False,
+ 'v_mac_f16': True,
+ 'v_mac_f32': True,
+ 'v_mad_mix_f32': False,
+ 'v_mov_b64': False,
+ 'v_pk_fma_f16': True,
+ 'v_pk_fmac_f16': False},
(9, 0, 6): {'HasAddLshl': True,
'HasAtomicAdd': False,
'HasDirectToLdsDest': False,
@@ -345,6 +389,50 @@ def getCapabilitiesCache(rocmVersion: NamedTuple) -> dict:
'v_mov_b64': True,
'v_pk_fma_f16': True,
'v_pk_fmac_f16': False},
+ (9, 4, -1): {'HasAddLshl': True,
+ 'HasAtomicAdd': True,
+ 'HasDirectToLdsDest': False,
+ 'HasDirectToLdsNoDest': True,
+ 'HasExplicitCO': True,
+ 'HasExplicitNC': False,
+ 'HasGLCModifier': False,
+ 'HasNTModifier': True,
+ 'HasLshlOr': True,
+ 'HasMFMA': True,
+ 'HasMFMA_b8': False,
+ 'HasMFMA_bf16_1k': True,
+ 'HasMFMA_bf16_original': False,
+ 'HasMFMA_constSrc': True,
+ 'HasMFMA_f64': True,
+ 'HasMFMA_f8': False,
+ 'HasMFMA_i8_908': False,
+ 'HasMFMA_i8_940': True,
+ 'HasMFMA_vgpr': True,
+ 'HasMFMA_xf32': False,
+ 'HasSMulHi': True,
+ 'HasWMMA': False,
+ 'KernargPreloading': True,
+ 'MaxLgkmcnt': 15,
+ 'MaxVmcnt': 63,
+ 'SupportedISA': True,
+ 'SupportedSource': True,
+ 'VOP3v_dot4_i32_i8': True,
+ 'v_dot2_f32_f16': True,
+ 'v_dot2c_f32_f16': True,
+ 'v_dot4_i32_i8': False,
+ 'v_dot4c_i32_i8': True,
+ 'v_fma_f16': True,
+ 'v_fma_f32': True,
+ 'v_fma_f64': True,
+ 'v_fma_mix_f32': True,
+ 'v_fmac_f16': False,
+ 'v_fmac_f32': True,
+ 'v_mac_f16': True,
+ 'v_mac_f32': False,
+ 'v_mad_mix_f32': False,
+ 'v_mov_b64': True,
+ 'v_pk_fma_f16': True,
+ 'v_pk_fmac_f16': False},
(9, 5, 0): {'HasAddLshl': True,
'HasAtomicAdd': True,
'HasDirectToLdsDest': False,
@@ -433,6 +521,50 @@ def getCapabilitiesCache(rocmVersion: NamedTuple) -> dict:
'v_mov_b64': False,
'v_pk_fma_f16': True,
'v_pk_fmac_f16': False},
+ (10, 1, -1): {'HasAddLshl': True,
+ 'HasAtomicAdd': False,
+ 'HasDirectToLdsDest': False,
+ 'HasDirectToLdsNoDest': True,
+ 'HasExplicitCO': True,
+ 'HasExplicitNC': True,
+ 'HasGLCModifier': True,
+ 'HasNTModifier': False,
+ 'HasLshlOr': True,
+ 'HasMFMA': False,
+ 'HasMFMA_b8': False,
+ 'HasMFMA_bf16_1k': False,
+ 'HasMFMA_bf16_original': False,
+ 'HasMFMA_constSrc': False,
+ 'HasMFMA_f64': False,
+ 'HasMFMA_f8': False,
+ 'HasMFMA_i8_908': False,
+ 'HasMFMA_i8_940': False,
+ 'HasMFMA_vgpr': False,
+ 'HasMFMA_xf32': False,
+ 'HasSMulHi': True,
+ 'HasWMMA': False,
+ 'KernargPreloading': False,
+ 'MaxLgkmcnt': 15,
+ 'MaxVmcnt': 63,
+ 'SupportedISA': True,
+ 'SupportedSource': True,
+ 'VOP3v_dot4_i32_i8': False,
+ 'v_dot2_f32_f16': False,
+ 'v_dot2c_f32_f16': False,
+ 'v_dot4_i32_i8': False,
+ 'v_dot4c_i32_i8': False,
+ 'v_fma_f16': True,
+ 'v_fma_f32': True,
+ 'v_fma_f64': True,
+ 'v_fma_mix_f32': True,
+ 'v_fmac_f16': False,
+ 'v_fmac_f32': True,
+ 'v_mac_f16': False,
+ 'v_mac_f32': True,
+ 'v_mad_mix_f32': False,
+ 'v_mov_b64': False,
+ 'v_pk_fma_f16': True,
+ 'v_pk_fmac_f16': False},
(10, 1, 1): {'HasAddLshl': True,
'HasAtomicAdd': False,
'HasDirectToLdsDest': False,
@@ -565,6 +697,50 @@ def getCapabilitiesCache(rocmVersion: NamedTuple) -> dict:
'v_mov_b64': False,
'v_pk_fma_f16': True,
'v_pk_fmac_f16': False},
+ (10, 3, -1): {'HasAddLshl': True,
+ 'HasAtomicAdd': False,
+ 'HasDirectToLdsDest': False,
+ 'HasDirectToLdsNoDest': True,
+ 'HasExplicitCO': True,
+ 'HasExplicitNC': True,
+ 'HasGLCModifier': True,
+ 'HasNTModifier': False,
+ 'HasLshlOr': True,
+ 'HasMFMA': False,
+ 'HasMFMA_b8': False,
+ 'HasMFMA_bf16_1k': False,
+ 'HasMFMA_bf16_original': False,
+ 'HasMFMA_constSrc': False,
+ 'HasMFMA_f64': False,
+ 'HasMFMA_f8': False,
+ 'HasMFMA_i8_908': False,
+ 'HasMFMA_i8_940': False,
+ 'HasMFMA_vgpr': False,
+ 'HasMFMA_xf32': False,
+ 'HasSMulHi': True,
+ 'HasWMMA': False,
+ 'KernargPreloading': False,
+ 'MaxLgkmcnt': 15,
+ 'MaxVmcnt': 63,
+ 'SupportedISA': True,
+ 'SupportedSource': True,
+ 'VOP3v_dot4_i32_i8': True,
+ 'v_dot2_f32_f16': True,
+ 'v_dot2c_f32_f16': True,
+ 'v_dot4_i32_i8': False,
+ 'v_dot4c_i32_i8': True,
+ 'v_fma_f16': True,
+ 'v_fma_f32': True,
+ 'v_fma_f64': True,
+ 'v_fma_mix_f32': True,
+ 'v_fmac_f16': False,
+ 'v_fmac_f32': True,
+ 'v_mac_f16': False,
+ 'v_mac_f32': False,
+ 'v_mad_mix_f32': False,
+ 'v_mov_b64': False,
+ 'v_pk_fma_f16': True,
+ 'v_pk_fmac_f16': False},
(10, 3, 1): {'HasAddLshl': True,
'HasAtomicAdd': False,
'HasDirectToLdsDest': False,
@@ -873,6 +1049,50 @@ def getCapabilitiesCache(rocmVersion: NamedTuple) -> dict:
'v_mov_b64': False,
'v_pk_fma_f16': True,
'v_pk_fmac_f16': False},
+ (11, 0, -1): {'HasAddLshl': True,
+ 'HasAtomicAdd': True,
+ 'HasDirectToLdsDest': False,
+ 'HasDirectToLdsNoDest': False,
+ 'HasExplicitCO': True,
+ 'HasExplicitNC': True,
+ 'HasGLCModifier': True,
+ 'HasNTModifier': False,
+ 'HasLshlOr': True,
+ 'HasMFMA': False,
+ 'HasMFMA_b8': False,
+ 'HasMFMA_bf16_1k': False,
+ 'HasMFMA_bf16_original': False,
+ 'HasMFMA_constSrc': False,
+ 'HasMFMA_f64': False,
+ 'HasMFMA_f8': False,
+ 'HasMFMA_i8_908': False,
+ 'HasMFMA_i8_940': False,
+ 'HasMFMA_vgpr': False,
+ 'HasMFMA_xf32': False,
+ 'HasSMulHi': True,
+ 'HasWMMA': True,
+ 'KernargPreloading': False,
+ 'MaxLgkmcnt': 15,
+ 'MaxVmcnt': 63,
+ 'SupportedISA': True,
+ 'SupportedSource': True,
+ 'VOP3v_dot4_i32_i8': True,
+ 'v_dot2_f32_f16': True,
+ 'v_dot2c_f32_f16': True,
+ 'v_dot4_i32_i8': False,
+ 'v_dot4c_i32_i8': False,
+ 'v_fma_f16': True,
+ 'v_fma_f32': True,
+ 'v_fma_f64': True,
+ 'v_fma_mix_f32': True,
+ 'v_fmac_f16': False,
+ 'v_fmac_f32': True,
+ 'v_mac_f16': False,
+ 'v_mac_f32': False,
+ 'v_mad_mix_f32': False,
+ 'v_mov_b64': False,
+ 'v_pk_fma_f16': True,
+ 'v_pk_fmac_f16': False},
(11, 0, 1): {'HasAddLshl': True,
'HasAtomicAdd': True,
'HasDirectToLdsDest': False,
@@ -1225,6 +1445,50 @@ def getCapabilitiesCache(rocmVersion: NamedTuple) -> dict:
'v_mov_b64': False,
'v_pk_fma_f16': True,
'v_pk_fmac_f16': False},
+ (12, 0, -1): {'HasAddLshl': True,
+ 'HasAtomicAdd': False,
+ 'HasDirectToLdsDest': False,
+ 'HasDirectToLdsNoDest': False,
+ 'HasExplicitCO': True,
+ 'HasExplicitNC': True,
+ 'HasGLCModifier': False,
+ 'HasNTModifier': False,
+ 'HasLshlOr': True,
+ 'HasMFMA': False,
+ 'HasMFMA_b8': False,
+ 'HasMFMA_bf16_1k': False,
+ 'HasMFMA_bf16_original': False,
+ 'HasMFMA_constSrc': False,
+ 'HasMFMA_f64': False,
+ 'HasMFMA_f8': False,
+ 'HasMFMA_i8_908': False,
+ 'HasMFMA_i8_940': False,
+ 'HasMFMA_vgpr': False,
+ 'HasMFMA_xf32': False,
+ 'HasSMulHi': True,
+ 'HasWMMA': False,
+ 'KernargPreloading': False,
+ 'MaxLgkmcnt': 15,
+ 'MaxVmcnt': 63,
+ 'SupportedISA': True,
+ 'SupportedSource': True,
+ 'VOP3v_dot4_i32_i8': True,
+ 'v_dot2_f32_f16': True,
+ 'v_dot2c_f32_f16': False,
+ 'v_dot4_i32_i8': False,
+ 'v_dot4c_i32_i8': False,
+ 'v_fma_f16': True,
+ 'v_fma_f32': True,
+ 'v_fma_f64': True,
+ 'v_fma_mix_f32': True,
+ 'v_fmac_f16': False,
+ 'v_fmac_f32': True,
+ 'v_mac_f16': False,
+ 'v_mac_f32': False,
+ 'v_mad_mix_f32': False,
+ 'v_mov_b64': False,
+ 'v_pk_fma_f16': True,
+ 'v_pk_fmac_f16': False},
(12, 0, 1): {'HasAddLshl': True,
'HasAtomicAdd': False,
'HasDirectToLdsDest': False,
diff --git a/shared/tensile/Tensile/Common.py b/shared/tensile/Tensile/Common.py
index b97fa061327b..9a2c399fad1b 100644
--- a/shared/tensile/Tensile/Common.py
+++ b/shared/tensile/Tensile/Common.py
@@ -246,12 +246,12 @@ globalParameters["NumMergedFiles"] = 1 # The number of files that ker
globalParameters["MaxFileName"] = 64 # If a file name would be longer than this, shorten it with a hash.
globalParameters["SupportedISA"] = [(8,0,3),
- (9,0,0), (9,0,6), (9,0,8), (9,0,10),
- (9,4,2), (9,5,0),
- (10,1,0), (10,1,1), (10,1,2), (10,3,0), (10,3,1), (10,3,2), (10,3,3), (10,3,4), (10,3,5), (10,3,6),
- (11,0,0), (11,0,1), (11,0,2), (11,0,3),
+ (9,0,0), (9,0,6), (9,0,8), (9,0,10), (9,0,-1),
+ (9,4,2), (9,4,-1), (9,5,0),
+ (10,1,0), (10,1,1), (10,1,2), (10,1,-1), (10,3,0), (10,3,1), (10,3,2), (10,3,3), (10,3,4), (10,3,5), (10,3,6), (10,3,-1),
+ (11,0,0), (11,0,1), (11,0,2), (11,0,3), (11,0,-1),
(11,5,0), (11,5,1), (11,5,2), (11,5,3),
- (12,0,0), (12,0,1)] # assembly kernels writer supports these architectures
+ (12,0,0), (12,0,1), (12,0,-1)] # assembly kernels writer supports these architectures
globalParameters["KeepBuildTmp"] = True # Do not remove build artifacts during the build process or build_tmp after build completes
globalParameters["GenerateManifestAndExit"] = False # Output manifest file with list of expected library objects and exit
@@ -320,15 +320,15 @@ architectureMap = {
'gfx803':'r9nano', 'gfx900':'vega10', 'gfx900:xnack-':'vega10',
'gfx906':'vega20', 'gfx906:xnack+':'vega20', 'gfx906:xnack-':'vega20',
'gfx908':'arcturus','gfx908:xnack+':'arcturus', 'gfx908:xnack-':'arcturus',
- 'gfx90a':'aldebaran', 'gfx90a:xnack+':'aldebaran', 'gfx90a:xnack-':'aldebaran',
- 'gfx942':'aquavanjaram942', 'gfx942:xnack+':'aquavanjaram942', 'gfx942:xnack-':'aquavanjaram942',
+ 'gfx90a':'aldebaran', 'gfx90a:xnack+':'aldebaran', 'gfx90a:xnack-':'aldebaran', 'gfx9-generic':'gfx9-generic',
+ 'gfx942':'aquavanjaram942', 'gfx942:xnack+':'aquavanjaram942', 'gfx942:xnack-':'aquavanjaram942', 'gfx9-4-generic':'gfx9-4-generic',
'gfx950':'gfx950', 'gfx950:xnack+':'gfx950', 'gfx950:xnack-':'gfx950',
- 'gfx1010':'navi10', 'gfx1011':'navi12', 'gfx1012':'navi14',
- 'gfx1030':'navi21', 'gfx1031':'navi22', 'gfx1032':'navi23', 'gfx1033':'van gogh', 'gfx1034':'navi24', 'gfx1035':'rembrandt', 'gfx1036':'raphael',
- 'gfx1100':'navi31', 'gfx1101':'navi32', 'gfx1102':'navi33', 'gfx1103':'gfx1103',
+ 'gfx1010':'navi10', 'gfx1011':'navi12', 'gfx1012':'navi14', 'gfx10-1-generic':'gfx10-1-generic',
+ 'gfx1030':'navi21', 'gfx1031':'navi22', 'gfx1032':'navi23', 'gfx1033':'van gogh', 'gfx1034':'navi24', 'gfx1035':'rembrandt', 'gfx1036':'raphael', 'gfx10-3-generic':'gfx10-3-generic',
+ 'gfx1100':'navi31', 'gfx1101':'navi32', 'gfx1102':'navi33', 'gfx1103':'gfx1103', 'gfx11-generic':'gfx11-generic',
'gfx1150':'strixpoint', 'gfx1151':'strixhalo', 'gfx1152':'gfx1152', 'gfx1153':'gfx1153',
'gfx1200':'gfx1200',
- 'gfx1201':'gfx1201'
+ 'gfx1201':'gfx1201', 'gfx12-generic':'gfx12-generic',
}
def getArchitectureName(gfxName: str) -> Optional[str]:
@@ -2201,6 +2201,21 @@ def tryAssembler(isaVersion, asmString, debug=False, *options):
def gfxArch(name: str) -> Optional[IsaVersion]:
import re
+
+ # Handle special case for generic architectures like 'gfx10-3-generic'
+ generic_match = re.search(r'gfx([0-9]+)-([0-9]+)-generic', name)
+ if generic_match:
+ major = int(generic_match.group(1))
+ minor = int(generic_match.group(2))
+ return (major, minor, -1) # step=-1 to indicate generic
+
+ # Handle special case for generic architectures like 'gfx11-generic'
+ generic_match = re.search(r'gfx([0-9]+)-generic', name)
+ if generic_match:
+ major = int(generic_match.group(1))
+ return (major, 0, -1) # step=-1 to indicate generic, minor=0
+
+ # Handle regular architectures like 'gfx900', 'gfx803' etc.
match = re.search(r'gfx([0-9a-fA-F]{3,})', name)
if not match: return None
@@ -2219,11 +2234,23 @@ def gfxArch(name: str) -> Optional[IsaVersion]:
return rv
def gfxName(arch):
- # convert last digit to hex because reasons
- name = str(arch[0]) + str(arch[1]) + ('%x' % arch[2])
+ # If arch[2] is negative, this is a generic target
+ if arch[2] < 0:
+ if arch[0] == 9:
+ if arch[1] == 4:
+ name = str(arch[0]) + '-' + str(arch[1]) + '-generic'
+ else:
+ name = str(arch[0]) + '-generic'
+ elif arch[0] == 10:
+ name = str(arch[0]) + '-' + str(arch[1]) + '-generic'
+ else:
+ name = str(arch[0]) + '-generic'
+ else:
+ # The normal case
+ # convert last digit to hex because reasons
+ name = str(arch[0]) + str(arch[1]) + ('%x' % arch[2])
return 'gfx' + ''.join(map(str,name))
-
def detectIsaWindows(output):
i = 0
for line in output:
@@ -2475,7 +2502,7 @@ def assignGlobalParameters( config, capabilitiesCache: Optional[dict] = None ):
if os.name == "nt":
globalParameters["CurrentISA"] = (9,0,6)
printWarning("Failed to detect ISA so forcing (gfx906) on windows")
- isasWithDisabledHWMonitor = ((9,4,2), (9,5,0), (11,0,0), (11,0,1), (11,0,2), (11,0,3), (11,5,0), (11,5,1), (11,5,2), (11,5,3), (12,0,0), (12,0,1))
+ isasWithDisabledHWMonitor = ((9,0,-1), (9,4,2), (9,4,-1), (9,5,0), (10,1,-1), (10,3,-1), (11,0,0), (11,0,1), (11,0,2), (11,0,3), (11,5,0), (11,5,1), (11,5,2), (11,5,3), (11,0,-1), (12,0,0), (12,0,1), (12,0,-1))
if globalParameters["CurrentISA"] in isasWithDisabledHWMonitor:
isaString = ', '.join(map(gfxName, isasWithDisabledHWMonitor))
printWarning(f"HardwareMonitor currently disabled for {isaString}")
diff --git a/shared/tensile/Tensile/Source/cmake/TensileSupportedArchitectures.cmake b/shared/tensile/Tensile/Source/cmake/TensileSupportedArchitectures.cmake
index a1fb7166cf63..5f3e2d54a003 100644
--- a/shared/tensile/Tensile/Source/cmake/TensileSupportedArchitectures.cmake
+++ b/shared/tensile/Tensile/Source/cmake/TensileSupportedArchitectures.cmake
@@ -35,11 +35,14 @@ if(NOT BUILD_ADDRESS_SANITIZER)
"gfx906"
"gfx908"
"gfx90a"
+ "gfx9-generic"
"gfx942"
+ "gfx9-4-generic"
"gfx950"
"gfx1010"
"gfx1011"
"gfx1012"
+ "gfx10-1-generic"
"gfx1030"
"gfx1031"
"gfx1032"
@@ -47,6 +50,7 @@ if(NOT BUILD_ADDRESS_SANITIZER)
"gfx1034"
"gfx1035"
"gfx1036"
+ "gfx10-3-generic"
"gfx1100"
"gfx1101"
"gfx1102"
@@ -55,8 +59,11 @@ if(NOT BUILD_ADDRESS_SANITIZER)
"gfx1151"
"gfx1152"
"gfx1153"
+ "gfx11-generic"
"gfx1200"
- "gfx1201")
+ "gfx1201"
+ "gfx12-generic"
+ )
set(SUPPORTED_ARCHITECTURES ${BASE_ARCHITECTURES})
list(APPEND SUPPORTED_ARCHITECTURES
diff --git a/shared/tensile/Tensile/Source/lib/include/Tensile/AMDGPU.hpp b/shared/tensile/Tensile/Source/lib/include/Tensile/AMDGPU.hpp
index 1d22bfe712da..be9d5a78c077 100644
--- a/shared/tensile/Tensile/Source/lib/include/Tensile/AMDGPU.hpp
+++ b/shared/tensile/Tensile/Source/lib/include/Tensile/AMDGPU.hpp
@@ -81,7 +81,13 @@ namespace Tensile
gfx1152 = 1152,
gfx1153 = 1153,
gfx1200 = 1200,
- gfx1201 = 1201
+ gfx1201 = 1201,
+ gfx9_generic = -900,
+ gfx9_4_generic = -940,
+ gfx10_1_generic = -1010,
+ gfx10_3_generic = -1030,
+ gfx11_generic = -1100,
+ gfx12_generic = -1200,
};
static std::string toString(Processor p)
@@ -142,6 +148,18 @@ namespace Tensile
return "gfx1200";
case AMDGPU::Processor::gfx1201:
return "gfx1201";
+ case AMDGPU::Processor::gfx9_generic:
+ return "gfx9-generic";
+ case AMDGPU::Processor::gfx9_4_generic:
+ return "gfx9-4-generic";
+ case AMDGPU::Processor::gfx10_1_generic:
+ return "gfx10-1-generic";
+ case AMDGPU::Processor::gfx10_3_generic:
+ return "gfx10-3-generic";
+ case AMDGPU::Processor::gfx11_generic:
+ return "gfx11-generic";
+ case AMDGPU::Processor::gfx12_generic:
+ return "gfx12-generic";
}
return "";
}
@@ -256,6 +274,30 @@ namespace Tensile
{
return AMDGPU::Processor::gfx1201;
}
+ else if(deviceString.find("gfx9-generic") != std::string::npos)
+ {
+ return AMDGPU::Processor::gfx9_generic;
+ }
+ else if(deviceString.find("gfx9-4-generic") != std::string::npos)
+ {
+ return AMDGPU::Processor::gfx9_4_generic;
+ }
+ else if(deviceString.find("gfx10-1-generic") != std::string::npos)
+ {
+ return AMDGPU::Processor::gfx10_1_generic;
+ }
+ else if(deviceString.find("gfx10-3-generic") != std::string::npos)
+ {
+ return AMDGPU::Processor::gfx10_3_generic;
+ }
+ else if(deviceString.find("gfx11-generic") != std::string::npos)
+ {
+ return AMDGPU::Processor::gfx11_generic;
+ }
+ else if(deviceString.find("gfx12-generic") != std::string::npos)
+ {
+ return AMDGPU::Processor::gfx12_generic;
+ }
else
{
return static_cast<AMDGPU::Processor>(0);
diff --git a/shared/tensile/Tensile/Source/lib/include/Tensile/PlaceholderLibrary.hpp b/shared/tensile/Tensile/Source/lib/include/Tensile/PlaceholderLibrary.hpp
index a9da044e8f39..2f8b18779936 100644
--- a/shared/tensile/Tensile/Source/lib/include/Tensile/PlaceholderLibrary.hpp
+++ b/shared/tensile/Tensile/Source/lib/include/Tensile/PlaceholderLibrary.hpp
@@ -66,6 +66,12 @@ namespace Tensile
gfx1153,
gfx1200,
gfx1201,
+ gfx9_generic,
+ gfx9_4_generic,
+ gfx10_1_generic,
+ gfx10_3_generic,
+ gfx11_generic,
+ gfx12_generic,
All
};
@@ -130,6 +136,18 @@ namespace Tensile
return "TensileLibrary_*_gfx1200";
case LazyLoadingInit::gfx1201:
return "TensileLibrary_*_gfx1201";
+ case LazyLoadingInit::gfx9_generic:
+ return "TensileLibrary_*_gfx9-generic";
+ case LazyLoadingInit::gfx9_4_generic:
+ return "TensileLibrary_*_gfx9-4-generic";
+ case LazyLoadingInit::gfx10_1_generic:
+ return "TensileLibrary_*_gfx10-1-generic";
+ case LazyLoadingInit::gfx10_3_generic:
+ return "TensileLibrary_*_gfx10-3-generic";
+ case LazyLoadingInit::gfx11_generic:
+ return "TensileLibrary_*_gfx11-generic";
+ case LazyLoadingInit::gfx12_generic:
+ return "TensileLibrary_*_gfx12-generic";
case LazyLoadingInit::None:
return "";
}
--
2.53.0
