@@ -6,21 +6,21 @@
__attribute__((global))
void kernel(int *out) {
int i = 0;
- out[i++] = threadIdx.x; // CHECK: call noundef i32
@llvm.nvvm.read.ptx.sreg.tid.x()
- out[i++] = threadIdx.y; // CHECK: call noundef i32
@llvm.nvvm.read.ptx.sreg.tid.y()
- out[i++] = threadIdx
@@ -6,21 +6,21 @@
__attribute__((global))
void kernel(int *out) {
int i = 0;
- out[i++] = threadIdx.x; // CHECK: call noundef i32
@llvm.nvvm.read.ptx.sreg.tid.x()
- out[i++] = threadIdx.y; // CHECK: call noundef i32
@llvm.nvvm.read.ptx.sreg.tid.y()
- out[i++] = threadIdx
@@ -6,21 +6,21 @@
__attribute__((global))
void kernel(int *out) {
int i = 0;
- out[i++] = threadIdx.x; // CHECK: call noundef i32
@llvm.nvvm.read.ptx.sreg.tid.x()
- out[i++] = threadIdx.y; // CHECK: call noundef i32
@llvm.nvvm.read.ptx.sreg.tid.y()
- out[i++] = threadIdx
@@ -6,21 +6,21 @@
__attribute__((global))
void kernel(int *out) {
int i = 0;
- out[i++] = threadIdx.x; // CHECK: call noundef i32
@llvm.nvvm.read.ptx.sreg.tid.x()
- out[i++] = threadIdx.y; // CHECK: call noundef i32
@llvm.nvvm.read.ptx.sreg.tid.y()
- out[i++] = threadIdx
@@ -6,21 +6,21 @@
__attribute__((global))
void kernel(int *out) {
int i = 0;
- out[i++] = threadIdx.x; // CHECK: call noundef i32
@llvm.nvvm.read.ptx.sreg.tid.x()
- out[i++] = threadIdx.y; // CHECK: call noundef i32
@llvm.nvvm.read.ptx.sreg.tid.y()
- out[i++] = threadIdx
@@ -139,24 +138,23 @@ define ptx_device i32 @test_ctaid_w() {
define ptx_device i32 @test_nctaid_y() {
; CHECK: mov.u32 %r{{[0-9]+}}, %nctaid.y;
-; RANGE: call i32 @llvm.nvvm.read.ptx.sreg.nctaid.y(), !range
![[GRID_SIZE_YZ:[0-9]+]]
+; RANGE: call range(i32 1, 65536) i32 @llv
@@ -139,24 +138,23 @@ define ptx_device i32 @test_ctaid_w() {
define ptx_device i32 @test_nctaid_y() {
; CHECK: mov.u32 %r{{[0-9]+}}, %nctaid.y;
-; RANGE: call i32 @llvm.nvvm.read.ptx.sreg.nctaid.y(), !range
![[GRID_SIZE_YZ:[0-9]+]]
+; RANGE: call range(i32 1, 65536) i32 @llv
@@ -139,24 +138,23 @@ define ptx_device i32 @test_ctaid_w() {
define ptx_device i32 @test_nctaid_y() {
; CHECK: mov.u32 %r{{[0-9]+}}, %nctaid.y;
-; RANGE: call i32 @llvm.nvvm.read.ptx.sreg.nctaid.y(), !range
![[GRID_SIZE_YZ:[0-9]+]]
+; RANGE: call range(i32 1, 65536) i32 @llv
https://github.com/AlexMaclean updated
https://github.com/llvm/llvm-project/pull/94422
>From 708374e03f1bf70006f2472f19edad1bd621e2d6 Mon Sep 17 00:00:00 2001
From: Alex MacLean
Date: Mon, 3 Jun 2024 16:46:36 +
Subject: [PATCH 1/4] [NVPTX] Revamp NVVMIntrRange pass
---
clang/test/CodeGenC
@@ -139,24 +138,23 @@ define ptx_device i32 @test_ctaid_w() {
define ptx_device i32 @test_nctaid_y() {
; CHECK: mov.u32 %r{{[0-9]+}}, %nctaid.y;
-; RANGE: call i32 @llvm.nvvm.read.ptx.sreg.nctaid.y(), !range
![[GRID_SIZE_YZ:[0-9]+]]
+; RANGE: call range(i32 1, 65536) i32 @llv
@@ -1,15 +1,15 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck
-allow-deprecated-dag-overlap %s
; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 | FileCheck
-allow-deprecated-dag-overlap %s
; RUN: opt < %s -S -mtriple=nvptx-nvidia-cuda -passes=nvvm-intr-range \
-; RUN: |
https://github.com/Artem-B edited
https://github.com/llvm/llvm-project/pull/94422
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/Artem-B approved this pull request.
LGTM.
https://github.com/llvm/llvm-project/pull/94422
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -0,0 +1,60 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
UTC_ARGS: --check-attributes --version 5
+; RUN: opt < %s -S -mtriple=nvptx-nvidia-cuda -mcpu=sm_20
-passes=nvvm-intr-range | FileCheck %s
+
+define i32 @test_maxntid() {
+; CHECK-LABEL:
@@ -128,6 +128,15 @@ bool findOneNVVMAnnotation(const GlobalValue *gv, const
std::string &prop,
return true;
}
+static std::optional
+findOneNVVMAnnotation(const GlobalValue &GV, const std::string &PropName) {
+ unsigned RetVal;
+ bool Found = findOneNVVMAnnotation(&GV, P
https://github.com/AlexMaclean updated
https://github.com/llvm/llvm-project/pull/94422
>From 708374e03f1bf70006f2472f19edad1bd621e2d6 Mon Sep 17 00:00:00 2001
From: Alex MacLean
Date: Mon, 3 Jun 2024 16:46:36 +
Subject: [PATCH 1/3] [NVPTX] Revamp NVVMIntrRange pass
---
clang/test/CodeGenC
@@ -1,50 +1,51 @@
-//===- NVVMIntrRange.cpp - Set !range metadata for NVVM intrinsics
===//
+//===- NVVMIntrRange.cpp - Set range attributes for NVVM intrinsics
---===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM
Exceptions.
// See ht
https://github.com/AlexMaclean updated
https://github.com/llvm/llvm-project/pull/94422
>From 708374e03f1bf70006f2472f19edad1bd621e2d6 Mon Sep 17 00:00:00 2001
From: Alex MacLean
Date: Mon, 3 Jun 2024 16:46:36 +
Subject: [PATCH 1/2] [NVPTX] Revamp NVVMIntrRange pass
---
clang/test/CodeGenC
@@ -0,0 +1,60 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
UTC_ARGS: --check-attributes --version 5
+; RUN: opt < %s -S -mtriple=nvptx-nvidia-cuda -mcpu=sm_20
-passes=nvvm-intr-range | FileCheck %s
+
+define i32 @test_maxntid() {
+; CHECK-LABEL:
@@ -1,50 +1,51 @@
-//===- NVVMIntrRange.cpp - Set !range metadata for NVVM intrinsics
===//
+//===- NVVMIntrRange.cpp - Set range attributes for NVVM intrinsics
---===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM
Exceptions.
// See ht
https://github.com/Artem-B commented:
Nice.
https://github.com/llvm/llvm-project/pull/94422
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/Artem-B edited
https://github.com/llvm/llvm-project/pull/94422
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -128,6 +128,15 @@ bool findOneNVVMAnnotation(const GlobalValue *gv, const
std::string &prop,
return true;
}
+static std::optional
+findOneNVVMAnnotation(const GlobalValue &GV, const std::string &PropName) {
+ unsigned RetVal;
+ bool Found = findOneNVVMAnnotation(&GV, P
Artem-B wrote:
> I've also re-enabled this pass in the TM, it was disabled years ago due to
> "numerical discrepancies" https://reviews.llvm.org/D96166. In our testing we
> haven't seen any issues with adding ranges to intrinsics, and I cannot find
> any further info about what issues were enc
https://github.com/AlexMaclean updated
https://github.com/llvm/llvm-project/pull/94422
>From 708374e03f1bf70006f2472f19edad1bd621e2d6 Mon Sep 17 00:00:00 2001
From: Alex MacLean
Date: Mon, 3 Jun 2024 16:46:36 +
Subject: [PATCH] [NVPTX] Revamp NVVMIntrRange pass
---
clang/test/CodeGenCUDA/
25 matches
Mail list logo
