aboutsummaryrefslogtreecommitdiff
path: root/llvm/docs/AMDGPUUsage.rst
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/docs/AMDGPUUsage.rst')
-rw-r--r--llvm/docs/AMDGPUUsage.rst61
1 files changed, 3 insertions, 58 deletions
diff --git a/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst
index f971bc0..7780c0a 100644
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -13239,9 +13239,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
store atomic release - workgroup - global 1. s_waitcnt lgkmcnt(0) &
- generic vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit vmcnt(0) and
- vscnt(0).
- If OpenCL, omit
lgkmcnt(0).
- Could be split into
@@ -13287,8 +13284,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
2. buffer/global/flat_store
store atomic release - workgroup - local 1. s_waitcnt vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit.
- If OpenCL, omit.
- Could be split into
separate s_waitcnt
@@ -13376,9 +13371,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
atomicrmw release - workgroup - global 1. s_waitcnt lgkmcnt(0) &
- generic vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit vmcnt(0) and
- vscnt(0).
- If OpenCL, omit lgkmcnt(0).
- Could be split into
separate s_waitcnt
@@ -13423,8 +13415,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
2. buffer/global/flat_atomic
atomicrmw release - workgroup - local 1. s_waitcnt vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit.
- If OpenCL, omit.
- Could be split into
separate s_waitcnt
@@ -13508,9 +13498,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
fence release - workgroup *none* 1. s_waitcnt lgkmcnt(0) &
vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit vmcnt(0) and
- vscnt(0).
- If OpenCL and
address space is
not generic, omit
@@ -13637,9 +13624,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
atomicrmw acq_rel - workgroup - global 1. s_waitcnt lgkmcnt(0) &
vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit vmcnt(0) and
- vscnt(0).
- If OpenCL, omit
lgkmcnt(0).
- Must happen after
@@ -13691,8 +13675,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
2. buffer/global_atomic
3. s_waitcnt vm/vscnt(0)
- - If CU wavefront execution
- mode, omit.
- Use vmcnt(0) if atomic with
return and vscnt(0) if
atomic with no-return.
@@ -13717,8 +13699,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
atomicrmw acq_rel - workgroup - local 1. s_waitcnt vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit.
- If OpenCL, omit.
- Could be split into
separate s_waitcnt
@@ -13778,9 +13758,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
atomicrmw acq_rel - workgroup - generic 1. s_waitcnt lgkmcnt(0) &
vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit vmcnt(0) and
- vscnt(0).
- If OpenCL, omit lgkmcnt(0).
- Could be split into
separate s_waitcnt
@@ -13826,9 +13803,9 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
3. s_waitcnt lgkmcnt(0) &
vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit vmcnt(0) and
- vscnt(0).
+ - If atomic with return, omit
+ vscnt(0), if atomic with
+ no-return, omit vmcnt(0).
- If OpenCL, omit lgkmcnt(0).
- Must happen before
the following
@@ -14001,9 +13978,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
fence acq_rel - workgroup *none* 1. s_waitcnt lgkmcnt(0) &
vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit vmcnt(0) and
- vscnt(0).
- If OpenCL and
address space is
not generic, omit
@@ -14233,9 +14207,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
load atomic seq_cst - workgroup - global 1. s_waitcnt lgkmcnt(0) &
- generic vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit vmcnt(0) and
- vscnt(0).
- Could be split into
separate s_waitcnt
vmcnt(0), s_waitcnt
@@ -14344,8 +14315,6 @@ table :ref:`amdgpu-amdhsa-memory-model-code-sequences-gfx10-gfx11-table`.
1. s_waitcnt vmcnt(0) & vscnt(0)
- - If CU wavefront execution
- mode, omit.
- Could be split into
separate s_waitcnt
vmcnt(0) and s_waitcnt
@@ -15347,8 +15316,6 @@ the instruction in the code sequence that references the table.
| ``s_wait_storecnt 0x0``
| ``s_wait_loadcnt 0x0``
| ``s_wait_dscnt 0x0``
- | **CU wavefront execution mode:**
- | ``s_wait_dscnt 0x0``
- If OpenCL, omit ``s_wait_dscnt 0x0``.
- The waits can be
@@ -15394,8 +15361,6 @@ the instruction in the code sequence that references the table.
| ``s_wait_storecnt 0x0``
| ``s_wait_loadcnt 0x0``
| ``s_wait_dscnt 0x0``
- | **CU wavefront execution mode:**
- | ``s_wait_dscnt 0x0``
- If OpenCL, omit.
- The waits can be
@@ -15489,8 +15454,6 @@ the instruction in the code sequence that references the table.
| ``s_wait_storecnt 0x0``
| ``s_wait_loadcnt 0x0``
| ``s_wait_dscnt 0x0``
- | **CU wavefront execution mode:**
- | ``s_wait_dscnt 0x0``
- If OpenCL, omit ``s_wait_dscnt 0x0``.
- If OpenCL and CU wavefront
@@ -15540,8 +15503,6 @@ the instruction in the code sequence that references the table.
| ``s_wait_storecnt 0x0``
| ``s_wait_loadcnt 0x0``
| ``s_wait_dscnt 0x0``
- | **CU wavefront execution mode:**
- | ``s_wait_dscnt 0x0``
- If OpenCL, omit all.
- The waits can be
@@ -15633,8 +15594,6 @@ the instruction in the code sequence that references the table.
| ``s_wait_storecnt 0x0``
| ``s_wait_loadcnt 0x0``
| ``s_wait_dscnt 0x0``
- | **CU wavefront execution mode:**
- | ``s_wait_dscnt 0x0``
- If OpenCL, omit ``s_wait_dscnt 0x0``.
- If OpenCL and
@@ -15764,8 +15723,6 @@ the instruction in the code sequence that references the table.
| ``s_wait_storecnt 0x0``
| ``s_wait_loadcnt 0x0``
| ``s_wait_dscnt 0x0``
- | **CU wavefront execution mode:**
- | ``s_wait_dscnt 0x0``
- If OpenCL, omit ``s_wait_dscnt 0x0``.
- Must happen after
@@ -15822,8 +15779,6 @@ the instruction in the code sequence that references the table.
| **Atomic without return:**
| ``s_wait_storecnt 0x0``
- - If CU wavefront execution
- mode, omit.
- Must happen before
the following
``global_inv``.
@@ -15848,8 +15803,6 @@ the instruction in the code sequence that references the table.
| ``s_wait_storecnt 0x0``
| ``s_wait_loadcnt 0x0``
| ``s_wait_dscnt 0x0``
- | **CU wavefront execution mode:**
- | ``s_wait_dscnt 0x0``
- If OpenCL, omit.
- The waits can be
@@ -15911,8 +15864,6 @@ the instruction in the code sequence that references the table.
| ``s_wait_storecnt 0x0``
| ``s_wait_loadcnt 0x0``
| ``s_wait_dscnt 0x0``
- | **CU wavefront execution mode:**
- | ``s_wait_dscnt 0x0``
- If OpenCL, omit ``s_wait_loadcnt 0x0``.
- The waits can be
@@ -16164,8 +16115,6 @@ the instruction in the code sequence that references the table.
| ``s_wait_storecnt 0x0``
| ``s_wait_loadcnt 0x0``
| ``s_wait_dscnt 0x0``
- | **CU wavefront execution mode:**
- | ``s_wait_dscnt 0x0``
- If OpenCL and
address space is
@@ -16394,8 +16343,6 @@ the instruction in the code sequence that references the table.
| ``s_wait_storecnt 0x0``
| ``s_wait_loadcnt 0x0``
| ``s_wait_dscnt 0x0``
- | **CU wavefront execution mode:**
- | ``s_wait_dscnt 0x0``
- If OpenCL, omit
``s_wait_dscnt 0x0``
@@ -16502,8 +16449,6 @@ the instruction in the code sequence that references the table.
| ``s_wait_storecnt 0x0``
| ``s_wait_loadcnt 0x0``
| ``s_wait_dscnt 0x0``
- | **CU wavefront execution mode:**
- | ``s_wait_dscnt 0x0``
- If OpenCL, omit all.
- The waits can be
generated by cgit v1.1 at 2025-10-22 01:09:53 +0000