diff --git a/clang/test/Driver/clang-linker-wrapper.cpp b/clang/test/Driver/clang-linker-wrapper.cpp
index f2acf035db317..a667fc9492dc5 100644
--- a/clang/test/Driver/clang-linker-wrapper.cpp
+++ b/clang/test/Driver/clang-linker-wrapper.cpp
@@ -121,7 +121,7 @@
 // CHK-CMDS-AOT-NV-NEXT: sycl-post-link{{.*}} SYCL_POST_LINK_OPTIONS -o [[SYCLPOSTLINKOUT:.*]].table [[SECONDLLVMLINKOUT]].bc
 // CHK-CMDS-AOT-NV-NEXT: clang{{.*}} -o [[CLANGOUT:.*]] -dumpdir a.out.nvptx64.sm_50.img. --target=nvptx64-nvidia-cuda -march={{.*}}
 // CHK-CMDS-AOT-NV-NEXT: ptxas{{.*}} --output-file [[PTXASOUT:.*]] [[CLANGOUT]]
-// CHK-CMDS-AOT-NV-NEXT: fatbinary{{.*}} --create [[FATBINOUT:.*]] --image=profile={{.*}},file=[[CLANGOUT]] --image=profile={{.*}},file=[[PTXASOUT]]
+// CHK-CMDS-AOT-NV-NEXT: fatbinary{{.*}} --create [[FATBINOUT:.*]] --image3=kind=ptx,sm={{(compute_)?50|pute_50}},file=[[CLANGOUT]] --image3=kind=elf,sm=50,file=[[PTXASOUT]]
 // CHK-CMDS-AOT-NV-NEXT: offload-wrapper: output: [[WRAPPEROUT:.*]].bc, input: [[FATBINOUT]]
 // CHK-CMDS-AOT-NV-NEXT: clang{{.*}} -c -o [[LLCOUT:.*]] [[WRAPPEROUT]]
 // CHK-CMDS-AOT-NV-NEXT: "{{.*}}/ld" -- HOST_LINKER_FLAGS -dynamic-linker HOST_DYN_LIB -o a.out [[LLCOUT]] HOST_LIB_PATH HOST_STAT_LIB {{.*}}.o
@@ -166,7 +166,7 @@
 // CHK-CMDS-AOT-NV-EMBED-IR-NEXT: clang{{.*}} -c -o [[LLCOUT1:.*]] [[WRAPPEROUT1]]
 // CHK-CMDS-AOT-NV-EMBED-IR-NEXT: clang{{.*}} -o [[CLANGOUT:.*]] -dumpdir a.out.nvptx64.sm_50.img. --target=nvptx64-nvidia-cuda -march={{.*}}
 // CHK-CMDS-AOT-NV-EMBED-IR-NEXT: ptxas{{.*}} --output-file [[PTXASOUT:.*]] [[CLANGOUT]]
-// CHK-CMDS-AOT-NV-EMBED-IR-NEXT: fatbinary{{.*}} --create [[FATBINOUT:.*]] --image=profile={{.*}},file=[[CLANGOUT]] --image=profile={{.*}},file=[[PTXASOUT]]
+// CHK-CMDS-AOT-NV-EMBED-IR-NEXT: fatbinary{{.*}} --create [[FATBINOUT:.*]] --image3=kind=ptx,sm={{(compute_)?50|pute_50}},file=[[CLANGOUT]] --image3=kind=elf,sm=50,file=[[PTXASOUT]]
 // CHK-CMDS-AOT-NV-EMBED-IR-NEXT: offload-wrapper: output: [[WRAPPEROUT:.*]].bc, input: [[FATBINOUT]]
 // CHK-CMDS-AOT-NV-EMBED-IR-NEXT: clang{{.*}} -c -o [[LLCOUT2:.*]] [[WRAPPEROUT]]
 // CHK-CMDS-AOT-NV-EMBED-IR-NEXT: "{{.*}}/ld" -- HOST_LINKER_FLAGS -dynamic-linker HOST_DYN_LIB -o a.out [[LLCOUT1]] [[LLCOUT2]] HOST_LIB_PATH HOST_STAT_LIB {{.*}}.o
diff --git a/clang/test/Driver/linker-wrapper.c b/clang/test/Driver/linker-wrapper.c
index 07daac39cc7e9..a27391dbff56c 100644
--- a/clang/test/Driver/linker-wrapper.c
+++ b/clang/test/Driver/linker-wrapper.c
@@ -106,7 +106,7 @@ __attribute__((visibility("protected"), used)) int x;
 
 // CUDA: clang{{.*}} -o [[IMG_SM70:.+]] -dumpdir a.out.nvptx64.sm_70.img. --target=nvptx64-nvidia-cuda -march=sm_70
 // CUDA: clang{{.*}} -o [[IMG_SM52:.+]] -dumpdir a.out.nvptx64.sm_52.img. --target=nvptx64-nvidia-cuda -march=sm_52
-// CUDA: fatbinary{{.*}}-64 --create {{.*}}.fatbin --image=profile=sm_70,file=[[IMG_SM70]] --image=profile=sm_52,file=[[IMG_SM52]]
+// CUDA: fatbinary{{.*}}-64 --create {{.*}}.fatbin --image3=kind=elf,sm=70,file=[[IMG_SM70]] --image3=kind=elf,sm=52,file=[[IMG_SM52]]
 // CUDA: usr/bin/ld{{.*}} {{.*}}.openmp.image.{{.*}}.o {{.*}}.cuda.image.{{.*}}.o
 
 // RUN: llvm-offload-binary -o %t.out \
@@ -240,7 +240,7 @@ __attribute__((visibility("protected"), used)) int x;
 // RUN:   %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=RELOCATABLE-LINK-CUDA
 
 // RELOCATABLE-LINK-CUDA: clang{{.*}} -o {{.*}}.img -dumpdir a.out.nvptx64.sm_89.img. --target=nvptx64-nvidia-cuda
-// RELOCATABLE-LINK-CUDA: fatbinary{{.*}} -64 --create {{.*}}.fatbin --image=profile=sm_89,file={{.*}}.img
+// RELOCATABLE-LINK-CUDA: fatbinary{{.*}} -64 --create {{.*}}.fatbin --image3=kind=elf,sm=89,file={{.*}}.img
 // RELOCATABLE-LINK-CUDA: /usr/bin/ld.lld{{.*}}-r
 // RELOCATABLE-LINK-CUDA: llvm-objcopy{{.*}}a.out --remove-section .llvm.offloading
 
diff --git a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
index 2a16c6ae4f40a..603539c8baa41 100644
--- a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
+++ b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
@@ -481,9 +481,22 @@ fatbinary(ArrayRef<std::pair<StringRef, StringRef>> InputFiles,
   CmdArgs.push_back(Triple.isArch64Bit() ? "-64" : "-32");
   CmdArgs.push_back("--create");
   CmdArgs.push_back(*TempFileOrErr);
-  for (const auto &[File, Arch] : InputFiles)
-    CmdArgs.push_back(
-        Args.MakeArgString("--image=profile=" + Arch + ",file=" + File));
+
+  for (const auto &[File, Arch] : InputFiles) {
+    // When bundling SYCL NVPTX, we may get both a cubin (sm_*) and a PTX
+    // assembly image (compute_*). `fatbinary` needs the right kind for each.
+    StringRef Kind = "elf";
+    StringRef ArchId = Arch;
+    if (Arch.starts_with("sm_")) {
+      ArchId = Arch.drop_front(3);
+    } else if (Arch.starts_with("compute_")) {
+      Kind = "ptx";
+      ArchId = Arch.drop_front(8);
+    }
+
+    CmdArgs.push_back(Args.MakeArgString("--image3=kind=" + Kind +
+                                         ",sm=" + ArchId + ",file=" + File));
+  }
 
   if (Error Err = executeCommands(*FatBinaryPath, CmdArgs))
     return std::move(Err);
diff --git a/sycl/test-e2e/AtomicRef/atomic_memory_order_acq_rel.cpp b/sycl/test-e2e/AtomicRef/atomic_memory_order_acq_rel.cpp
index bac155b16b3c4..9245e57abde85 100644
--- a/sycl/test-e2e/AtomicRef/atomic_memory_order_acq_rel.cpp
+++ b/sycl/test-e2e/AtomicRef/atomic_memory_order_acq_rel.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -O3 -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_70 %}
+// RUN: %{build} -O3 -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 // NOTE: Tests fetch_add for acquire and release memory ordering.
diff --git a/sycl/test-e2e/AtomicRef/atomic_memory_order_seq_cst.cpp b/sycl/test-e2e/AtomicRef/atomic_memory_order_seq_cst.cpp
index 462834453129e..900f840ee6acc 100644
--- a/sycl/test-e2e/AtomicRef/atomic_memory_order_seq_cst.cpp
+++ b/sycl/test-e2e/AtomicRef/atomic_memory_order_seq_cst.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -O3 -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_70 %}
+// RUN: %{build} -O3 -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 #include "atomic_memory_order.h"
diff --git a/sycl/test-e2e/GroupAlgorithm/root_group.cpp b/sycl/test-e2e/GroupAlgorithm/root_group.cpp
index 5afc29fb0b61d..4ee5c96d6dd01 100644
--- a/sycl/test-e2e/GroupAlgorithm/root_group.cpp
+++ b/sycl/test-e2e/GroupAlgorithm/root_group.cpp
@@ -2,7 +2,7 @@
 // XFAIL: (opencl && !cpu)
 // XFAIL-TRACKER: https://github.com/intel/llvm/issues/14641
 
-// RUN: %{build} -I . -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_70 %}
+// RUN: %{build} -I . -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 // Disabled temporarily while investigation into the failure is ongoing.
diff --git a/sycl/test-e2e/Matrix/joint_matrix_tensorcores_sm70.cpp b/sycl/test-e2e/Matrix/joint_matrix_tensorcores_sm70.cpp
index bfa1156bc0e6b..71125772f6f91 100644
--- a/sycl/test-e2e/Matrix/joint_matrix_tensorcores_sm70.cpp
+++ b/sycl/test-e2e/Matrix/joint_matrix_tensorcores_sm70.cpp
@@ -7,7 +7,7 @@
 //===----------------------------------------------------------------------===//
 
 // REQUIRES: target-nvidia
-// RUN: %{build} -Xsycl-target-backend --cuda-gpu-arch=sm_70 -o %t.out
+// RUN: %{build} -Xsycl-target-backend --cuda-gpu-arch=sm_75 -o %t.out
 // RUN: %{run} %t.out
 //
 // This tests the unified matrix extension interfaces for the cuda backend.
diff --git a/sycl/test-e2e/Matrix/joint_matrix_tensorcores_sm72.cpp b/sycl/test-e2e/Matrix/joint_matrix_tensorcores_sm72.cpp
index a8dbb59b46e0e..7e8d8fcb9f918 100644
--- a/sycl/test-e2e/Matrix/joint_matrix_tensorcores_sm72.cpp
+++ b/sycl/test-e2e/Matrix/joint_matrix_tensorcores_sm72.cpp
@@ -7,7 +7,7 @@
 //===----------------------------------------------------------------------===//
 
 // REQUIRES: target-nvidia
-// RUN: %{build} -Xsycl-target-backend --cuda-gpu-arch=sm_72 -o %t.out
+// RUN: %{build} -Xsycl-target-backend --cuda-gpu-arch=sm_75 -o %t.out
 // RUN: %{run} %t.out
 //
 // This tests the unified matrix extension interfaces for the cuda backend.
diff --git a/sycl/test-e2e/Reduction/reduction_range_1d_dw.cpp b/sycl/test-e2e/Reduction/reduction_range_1d_dw.cpp
index 58121639594a9..779b315ac6d43 100644
--- a/sycl/test-e2e/Reduction/reduction_range_1d_dw.cpp
+++ b/sycl/test-e2e/Reduction/reduction_range_1d_dw.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -DENABLE_64_BIT=false -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_60 %}
+// RUN: %{build} -DENABLE_64_BIT=false -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 #include "reduction_utils.hpp"
diff --git a/sycl/test-e2e/Reduction/reduction_range_1d_dw_64bit.cpp b/sycl/test-e2e/Reduction/reduction_range_1d_dw_64bit.cpp
index 23c83be59b56c..f7756eaedceda 100644
--- a/sycl/test-e2e/Reduction/reduction_range_1d_dw_64bit.cpp
+++ b/sycl/test-e2e/Reduction/reduction_range_1d_dw_64bit.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -DENABLE_64_BIT=true -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_60 %}
+// RUN: %{build} -DENABLE_64_BIT=true -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 #include "reduction_range_1d_dw.cpp"
diff --git a/sycl/test-e2e/Reduction/reduction_range_1d_reducer_skip.cpp b/sycl/test-e2e/Reduction/reduction_range_1d_reducer_skip.cpp
index 83e13dc07102d..2f5077c41f03f 100644
--- a/sycl/test-e2e/Reduction/reduction_range_1d_reducer_skip.cpp
+++ b/sycl/test-e2e/Reduction/reduction_range_1d_reducer_skip.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_60 %}
+// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 // This test performs basic checks of parallel_for(range<1>, reduction, func)
diff --git a/sycl/test-e2e/Reduction/reduction_range_1d_rw.cpp b/sycl/test-e2e/Reduction/reduction_range_1d_rw.cpp
index ee72e6e516814..9df0bb8faa974 100644
--- a/sycl/test-e2e/Reduction/reduction_range_1d_rw.cpp
+++ b/sycl/test-e2e/Reduction/reduction_range_1d_rw.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_60 %}
+// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 // This test performs basic checks of parallel_for(range<1>, reduction, func)
diff --git a/sycl/test-e2e/Reduction/reduction_range_2d_dw.cpp b/sycl/test-e2e/Reduction/reduction_range_2d_dw.cpp
index 604861ece2123..d8c7ee5fe037b 100644
--- a/sycl/test-e2e/Reduction/reduction_range_2d_dw.cpp
+++ b/sycl/test-e2e/Reduction/reduction_range_2d_dw.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_60 %}
+// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 // This test performs basic checks of parallel_for(range<2>, reduction, func)
diff --git a/sycl/test-e2e/Reduction/reduction_range_2d_dw_reducer_skip.cpp b/sycl/test-e2e/Reduction/reduction_range_2d_dw_reducer_skip.cpp
index b15ed6e6e3b6a..5d9b382dd1546 100644
--- a/sycl/test-e2e/Reduction/reduction_range_2d_dw_reducer_skip.cpp
+++ b/sycl/test-e2e/Reduction/reduction_range_2d_dw_reducer_skip.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_60 %}
+// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 // This test performs basic checks of parallel_for(range<2>, reduction, func)
diff --git a/sycl/test-e2e/Reduction/reduction_range_2d_rw.cpp b/sycl/test-e2e/Reduction/reduction_range_2d_rw.cpp
index bb19278df3281..a264e8a10a007 100644
--- a/sycl/test-e2e/Reduction/reduction_range_2d_rw.cpp
+++ b/sycl/test-e2e/Reduction/reduction_range_2d_rw.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_60 %}
+// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 // This test performs basic checks of parallel_for(range<2>, reduction, func)
diff --git a/sycl/test-e2e/Reduction/reduction_range_3d_dw.cpp b/sycl/test-e2e/Reduction/reduction_range_3d_dw.cpp
index 0a0a2f187f870..63462f8e34d2c 100644
--- a/sycl/test-e2e/Reduction/reduction_range_3d_dw.cpp
+++ b/sycl/test-e2e/Reduction/reduction_range_3d_dw.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_60 %}
+// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 // This test performs basic checks of parallel_for(range<3>, reduction, func)
diff --git a/sycl/test-e2e/Reduction/reduction_range_3d_rw.cpp b/sycl/test-e2e/Reduction/reduction_range_3d_rw.cpp
index e49b55156485a..8141b22138b07 100644
--- a/sycl/test-e2e/Reduction/reduction_range_3d_rw.cpp
+++ b/sycl/test-e2e/Reduction/reduction_range_3d_rw.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_60 %}
+// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 // This test performs basic checks of parallel_for(range<3>, reduction, func)
diff --git a/sycl/test-e2e/Reduction/reduction_range_3d_rw_reducer_skip.cpp b/sycl/test-e2e/Reduction/reduction_range_3d_rw_reducer_skip.cpp
index 017d6a9427dca..0488a93cfc822 100644
--- a/sycl/test-e2e/Reduction/reduction_range_3d_rw_reducer_skip.cpp
+++ b/sycl/test-e2e/Reduction/reduction_range_3d_rw_reducer_skip.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_60 %}
+// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 // This test performs basic checks of parallel_for(range<3>, reduction, func)
diff --git a/sycl/test-e2e/Reduction/reduction_range_usm_dw.cpp b/sycl/test-e2e/Reduction/reduction_range_usm_dw.cpp
index b99f3bdc276f7..b1e290a9348c6 100644
--- a/sycl/test-e2e/Reduction/reduction_range_usm_dw.cpp
+++ b/sycl/test-e2e/Reduction/reduction_range_usm_dw.cpp
@@ -1,4 +1,4 @@
-// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_60 %}
+// RUN: %{build} -o %t.out %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %}
 // RUN: %{run} %t.out
 
 #include "reduction_utils.hpp"
diff --git a/sycl/test-e2e/USM/P2P/p2p_atomics.cpp b/sycl/test-e2e/USM/P2P/p2p_atomics.cpp
index c36b331ca46c4..71bf0ac6b88c8 100644
--- a/sycl/test-e2e/USM/P2P/p2p_atomics.cpp
+++ b/sycl/test-e2e/USM/P2P/p2p_atomics.cpp
@@ -1,5 +1,5 @@
 // REQUIRES: cuda || hip || level_zero
-// RUN:  %{build} %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_61 %} -o %t.out
+// RUN:  %{build} %if target-nvidia %{ -Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_75 %} -o %t.out
 // RUN:  %{run} %t.out
 
 #include <cassert>