[llvm] [NVPTX][NFC] Update test to use bfloat type (PR #101493)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Aug 1 07:52:02 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-nvptx
Author: Hugh Delaney (hdelan)
<details>
<summary>Changes</summary>
Intrinsics are defined with a bfloat type, not i16 and i32 storage types. As such declarations are no longer needed once the correct types are used.
---
Full diff: https://github.com/llvm/llvm-project/pull/101493.diff
2 Files Affected:
- (modified) llvm/test/CodeGen/NVPTX/math-intrins-sm80-ptx70-autoupgrade.ll (+48-92)
- (modified) llvm/test/CodeGen/NVPTX/math-intrins-sm86-ptx72-autoupgrade.ll (+24-58)
``````````diff
diff --git a/llvm/test/CodeGen/NVPTX/math-intrins-sm80-ptx70-autoupgrade.ll b/llvm/test/CodeGen/NVPTX/math-intrins-sm80-ptx70-autoupgrade.ll
index 34b9c08509326..783fd22b892a9 100644
--- a/llvm/test/CodeGen/NVPTX/math-intrins-sm80-ptx70-autoupgrade.ll
+++ b/llvm/test/CodeGen/NVPTX/math-intrins-sm80-ptx70-autoupgrade.ll
@@ -1,80 +1,36 @@
; RUN: llc < %s -march=nvptx64 -mcpu=sm_80 -mattr=+ptx70 | FileCheck %s
; RUN: %if ptxas-11.0 %{ llc < %s -march=nvptx64 -mcpu=sm_80 -mattr=+ptx70 | %ptxas-verify -arch=sm_80 %}
-declare i16 @llvm.nvvm.abs.bf16(i16)
-declare i32 @llvm.nvvm.abs.bf16x2(i32)
-declare i16 @llvm.nvvm.neg.bf16(i16)
-declare i32 @llvm.nvvm.neg.bf16x2(i32)
-
-declare float @llvm.nvvm.fmin.nan.f(float, float)
-declare float @llvm.nvvm.fmin.ftz.nan.f(float, float)
-declare half @llvm.nvvm.fmin.f16(half, half)
-declare half @llvm.nvvm.fmin.ftz.f16(half, half)
-declare half @llvm.nvvm.fmin.nan.f16(half, half)
-declare half @llvm.nvvm.fmin.ftz.nan.f16(half, half)
-declare <2 x half> @llvm.nvvm.fmin.f16x2(<2 x half>, <2 x half>)
-declare <2 x half> @llvm.nvvm.fmin.ftz.f16x2(<2 x half>, <2 x half>)
-declare <2 x half> @llvm.nvvm.fmin.nan.f16x2(<2 x half>, <2 x half>)
-declare <2 x half> @llvm.nvvm.fmin.ftz.nan.f16x2(<2 x half>, <2 x half>)
-declare i16 @llvm.nvvm.fmin.bf16(i16, i16)
-declare i16 @llvm.nvvm.fmin.nan.bf16(i16, i16)
-declare i32 @llvm.nvvm.fmin.bf16x2(i32, i32)
-declare i32 @llvm.nvvm.fmin.nan.bf16x2(i32, i32)
-
-declare float @llvm.nvvm.fmax.nan.f(float, float)
-declare float @llvm.nvvm.fmax.ftz.nan.f(float, float)
-declare half @llvm.nvvm.fmax.f16(half, half)
-declare half @llvm.nvvm.fmax.ftz.f16(half, half)
-declare half @llvm.nvvm.fmax.nan.f16(half, half)
-declare half @llvm.nvvm.fmax.ftz.nan.f16(half, half)
-declare <2 x half> @llvm.nvvm.fmax.f16x2(<2 x half>, <2 x half>)
-declare <2 x half> @llvm.nvvm.fmax.ftz.f16x2(<2 x half>, <2 x half>)
-declare <2 x half> @llvm.nvvm.fmax.nan.f16x2(<2 x half>, <2 x half>)
-declare <2 x half> @llvm.nvvm.fmax.ftz.nan.f16x2(<2 x half>, <2 x half>)
-declare i16 @llvm.nvvm.fmax.bf16(i16, i16)
-declare i16 @llvm.nvvm.fmax.nan.bf16(i16, i16)
-declare i32 @llvm.nvvm.fmax.bf16x2(i32, i32)
-declare i32 @llvm.nvvm.fmax.nan.bf16x2(i32, i32)
-
-declare half @llvm.nvvm.fma.rn.relu.f16(half, half, half)
-declare half @llvm.nvvm.fma.rn.ftz.relu.f16(half, half, half)
-declare <2 x half> @llvm.nvvm.fma.rn.relu.f16x2(<2 x half>, <2 x half>, <2 x half>)
-declare <2 x half> @llvm.nvvm.fma.rn.ftz.relu.f16x2(<2 x half>, <2 x half>, <2 x half>)
-declare i16 @llvm.nvvm.fma.rn.bf16(i16, i16, i16)
-declare i16 @llvm.nvvm.fma.rn.relu.bf16(i16, i16, i16)
-declare i32 @llvm.nvvm.fma.rn.bf16x2(i32, i32, i32)
-declare i32 @llvm.nvvm.fma.rn.relu.bf16x2(i32, i32, i32)
-
; CHECK-LABEL: abs_bf16
-define i16 @abs_bf16(i16 %0) {
+define bfloat @abs_bf16(bfloat %0) {
; CHECK-NOT: call
; CHECK: abs.bf16
- %res = call i16 @llvm.nvvm.abs.bf16(i16 %0);
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.abs.bf16(bfloat %0);
+ ret bfloat %res
}
; CHECK-LABEL: abs_bf16x2
-define i32 @abs_bf16x2(i32 %0) {
+define <2 x bfloat> @abs_bf16x2(<2 x bfloat> %0) {
; CHECK-NOT: call
; CHECK: abs.bf16x2
- %res = call i32 @llvm.nvvm.abs.bf16x2(i32 %0);
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.abs.bf16x2(<2 x bfloat> %0);
+ ret <2 x bfloat> %res
}
; CHECK-LABEL: neg_bf16
-define i16 @neg_bf16(i16 %0) {
+define bfloat @neg_bf16(bfloat %0) {
; CHECK-NOT: call
; CHECK: neg.bf16
- %res = call i16 @llvm.nvvm.neg.bf16(i16 %0);
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.neg.bf16(bfloat %0);
+ ret bfloat %res
}
; CHECK-LABEL: neg_bf16x2
-define i32 @neg_bf16x2(i32 %0) {
+define <2 x bfloat> @neg_bf16x2(<2 x bfloat> %0) {
; CHECK-NOT: call
; CHECK: neg.bf16x2
- %res = call i32 @llvm.nvvm.neg.bf16x2(i32 %0);
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.neg.bf16x2(<2 x bfloat> %0);
+ ret <2 x bfloat> %res
}
; CHECK-LABEL: fmin_nan_f
@@ -158,35 +114,35 @@ define <2 x half> @fmin_ftz_nan_f16x2(<2 x half> %0, <2 x half> %1) {
}
; CHECK-LABEL: fmin_bf16
-define i16 @fmin_bf16(i16 %0, i16 %1) {
+define bfloat @fmin_bf16(bfloat %0, bfloat %1) {
; CHECK-NOT: call
; CHECK: min.bf16
- %res = call i16 @llvm.nvvm.fmin.bf16(i16 %0, i16 %1)
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.fmin.bf16(bfloat %0, bfloat %1)
+ ret bfloat %res
}
; CHECK-LABEL: fmin_nan_bf16
-define i16 @fmin_nan_bf16(i16 %0, i16 %1) {
+define bfloat @fmin_nan_bf16(bfloat %0, bfloat %1) {
; CHECK-NOT: call
; CHECK: min.NaN.bf16
- %res = call i16 @llvm.nvvm.fmin.nan.bf16(i16 %0, i16 %1)
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.fmin.nan.bf16(bfloat %0, bfloat %1)
+ ret bfloat %res
}
; CHECK-LABEL: fmin_bf16x2
-define i32 @fmin_bf16x2(i32 %0, i32 %1) {
+define <2 x bfloat> @fmin_bf16x2(<2 x bfloat> %0, <2 x bfloat> %1) {
; CHECK-NOT: call
; CHECK: min.bf16x2
- %res = call i32 @llvm.nvvm.fmin.bf16x2(i32 %0, i32 %1)
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.fmin.bf16x2(<2 x bfloat> %0, <2 x bfloat> %1)
+ ret <2 x bfloat> %res
}
; CHECK-LABEL: fmin_nan_bf16x2
-define i32 @fmin_nan_bf16x2(i32 %0, i32 %1) {
+define <2 x bfloat> @fmin_nan_bf16x2(<2 x bfloat> %0, <2 x bfloat> %1) {
; CHECK-NOT: call
; CHECK: min.NaN.bf16x2
- %res = call i32 @llvm.nvvm.fmin.nan.bf16x2(i32 %0, i32 %1)
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.fmin.nan.bf16x2(<2 x bfloat> %0, <2 x bfloat> %1)
+ ret <2 x bfloat> %res
}
; CHECK-LABEL: fmax_nan_f
@@ -270,35 +226,35 @@ define <2 x half> @fmax_ftz_nan_f16x2(<2 x half> %0, <2 x half> %1) {
}
; CHECK-LABEL: fmax_bf16
-define i16 @fmax_bf16(i16 %0, i16 %1) {
+define bfloat @fmax_bf16(bfloat %0, bfloat %1) {
; CHECK-NOT: call
; CHECK: max.bf16
- %res = call i16 @llvm.nvvm.fmax.bf16(i16 %0, i16 %1)
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.fmax.bf16(bfloat %0, bfloat %1)
+ ret bfloat %res
}
; CHECK-LABEL: fmax_nan_bf16
-define i16 @fmax_nan_bf16(i16 %0, i16 %1) {
+define bfloat @fmax_nan_bf16(bfloat %0, bfloat %1) {
; CHECK-NOT: call
; CHECK: max.NaN.bf16
- %res = call i16 @llvm.nvvm.fmax.nan.bf16(i16 %0, i16 %1)
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.fmax.nan.bf16(bfloat %0, bfloat %1)
+ ret bfloat %res
}
; CHECK-LABEL: fmax_bf16x2
-define i32 @fmax_bf16x2(i32 %0, i32 %1) {
+define <2 x bfloat> @fmax_bf16x2(<2 x bfloat> %0, <2 x bfloat> %1) {
; CHECK-NOT: call
; CHECK: max.bf16x2
- %res = call i32 @llvm.nvvm.fmax.bf16x2(i32 %0, i32 %1)
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.fmax.bf16x2(<2 x bfloat> %0, <2 x bfloat> %1)
+ ret <2 x bfloat> %res
}
; CHECK-LABEL: fmax_nan_bf16x2
-define i32 @fmax_nan_bf16x2(i32 %0, i32 %1) {
+define <2 x bfloat> @fmax_nan_bf16x2(<2 x bfloat> %0, <2 x bfloat> %1) {
; CHECK-NOT: call
; CHECK: max.NaN.bf16x2
- %res = call i32 @llvm.nvvm.fmax.nan.bf16x2(i32 %0, i32 %1)
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.fmax.nan.bf16x2(<2 x bfloat> %0, <2 x bfloat> %1)
+ ret <2 x bfloat> %res
}
; CHECK-LABEL: fma_rn_relu_f16
@@ -334,33 +290,33 @@ define <2 x half> @fma_rn_ftz_relu_f16x2(<2 x half> %0, <2 x half> %1, <2 x half
}
; CHECK-LABEL: fma_rn_bf16
-define i16 @fma_rn_bf16(i16 %0, i16 %1, i16 %2) {
+define bfloat @fma_rn_bf16(bfloat %0, bfloat %1, bfloat %2) {
; CHECK-NOT: call
; CHECK: fma.rn.bf16
- %res = call i16 @llvm.nvvm.fma.rn.bf16(i16 %0, i16 %1, i16 %2)
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.fma.rn.bf16(bfloat %0, bfloat %1, bfloat %2)
+ ret bfloat %res
}
; CHECK-LABEL: fma_rn_relu_bf16
-define i16 @fma_rn_relu_bf16(i16 %0, i16 %1, i16 %2) {
+define bfloat @fma_rn_relu_bf16(bfloat %0, bfloat %1, bfloat %2) {
; CHECK-NOT: call
; CHECK: fma.rn.relu.bf16
- %res = call i16 @llvm.nvvm.fma.rn.relu.bf16(i16 %0, i16 %1, i16 %2)
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.fma.rn.relu.bf16(bfloat %0, bfloat %1, bfloat %2)
+ ret bfloat %res
}
; CHECK-LABEL: fma_rn_bf16x2
-define i32 @fma_rn_bf16x2(i32 %0, i32 %1, i32 %2) {
+define <2 x bfloat> @fma_rn_bf16x2(<2 x bfloat> %0, <2 x bfloat> %1, <2 x bfloat> %2) {
; CHECK-NOT: call
; CHECK: fma.rn.bf16x2
- %res = call i32 @llvm.nvvm.fma.rn.bf16x2(i32 %0, i32 %1, i32 %2)
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.fma.rn.bf16x2(<2 x bfloat> %0, <2 x bfloat> %1, <2 x bfloat> %2)
+ ret <2 x bfloat> %res
}
; CHECK-LABEL: fma_rn_relu_bf16x2
-define i32 @fma_rn_relu_bf16x2(i32 %0, i32 %1, i32 %2) {
+define <2 x bfloat> @fma_rn_relu_bf16x2(<2 x bfloat> %0, <2 x bfloat> %1, <2 x bfloat> %2) {
; CHECK-NOT: call
; CHECK: fma.rn.relu.bf16x2
- %res = call i32 @llvm.nvvm.fma.rn.relu.bf16x2(i32 %0, i32 %1, i32 %2)
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.fma.rn.relu.bf16x2(<2 x bfloat> %0, <2 x bfloat> %1, <2 x bfloat> %2)
+ ret <2 x bfloat> %res
}
diff --git a/llvm/test/CodeGen/NVPTX/math-intrins-sm86-ptx72-autoupgrade.ll b/llvm/test/CodeGen/NVPTX/math-intrins-sm86-ptx72-autoupgrade.ll
index b745df484bab2..4070fac67ac9b 100644
--- a/llvm/test/CodeGen/NVPTX/math-intrins-sm86-ptx72-autoupgrade.ll
+++ b/llvm/test/CodeGen/NVPTX/math-intrins-sm86-ptx72-autoupgrade.ll
@@ -1,40 +1,6 @@
; RUN: llc < %s -march=nvptx64 -mcpu=sm_86 -mattr=+ptx72 | FileCheck %s
; RUN: %if ptxas-11.2 %{ llc < %s -march=nvptx64 -mcpu=sm_86 -mattr=+ptx72 | %ptxas-verify -arch=sm_86 %}
-declare half @llvm.nvvm.fmin.xorsign.abs.f16(half, half)
-declare half @llvm.nvvm.fmin.ftz.xorsign.abs.f16(half, half)
-declare half @llvm.nvvm.fmin.nan.xorsign.abs.f16(half, half)
-declare half @llvm.nvvm.fmin.ftz.nan.xorsign.abs.f16(half, half)
-declare <2 x half> @llvm.nvvm.fmin.xorsign.abs.f16x2(<2 x half> , <2 x half>)
-declare <2 x half> @llvm.nvvm.fmin.ftz.xorsign.abs.f16x2(<2 x half> , <2 x half>)
-declare <2 x half> @llvm.nvvm.fmin.nan.xorsign.abs.f16x2(<2 x half> , <2 x half>)
-declare <2 x half> @llvm.nvvm.fmin.ftz.nan.xorsign.abs.f16x2(<2 x half> , <2 x half>)
-declare i16 @llvm.nvvm.fmin.xorsign.abs.bf16(i16, i16)
-declare i16 @llvm.nvvm.fmin.nan.xorsign.abs.bf16(i16, i16)
-declare i32 @llvm.nvvm.fmin.xorsign.abs.bf16x2(i32, i32)
-declare i32 @llvm.nvvm.fmin.nan.xorsign.abs.bf16x2(i32, i32)
-declare float @llvm.nvvm.fmin.xorsign.abs.f(float, float)
-declare float @llvm.nvvm.fmin.ftz.xorsign.abs.f(float, float)
-declare float @llvm.nvvm.fmin.nan.xorsign.abs.f(float, float)
-declare float @llvm.nvvm.fmin.ftz.nan.xorsign.abs.f(float, float)
-
-declare half @llvm.nvvm.fmax.xorsign.abs.f16(half, half)
-declare half @llvm.nvvm.fmax.ftz.xorsign.abs.f16(half, half)
-declare half @llvm.nvvm.fmax.nan.xorsign.abs.f16(half, half)
-declare half @llvm.nvvm.fmax.ftz.nan.xorsign.abs.f16(half, half)
-declare <2 x half> @llvm.nvvm.fmax.xorsign.abs.f16x2(<2 x half> , <2 x half>)
-declare <2 x half> @llvm.nvvm.fmax.ftz.xorsign.abs.f16x2(<2 x half> , <2 x half>)
-declare <2 x half> @llvm.nvvm.fmax.nan.xorsign.abs.f16x2(<2 x half> , <2 x half>)
-declare <2 x half> @llvm.nvvm.fmax.ftz.nan.xorsign.abs.f16x2(<2 x half> , <2 x half>)
-declare i16 @llvm.nvvm.fmax.xorsign.abs.bf16(i16, i16)
-declare i16 @llvm.nvvm.fmax.nan.xorsign.abs.bf16(i16, i16)
-declare i32 @llvm.nvvm.fmax.xorsign.abs.bf16x2(i32, i32)
-declare i32 @llvm.nvvm.fmax.nan.xorsign.abs.bf16x2(i32, i32)
-declare float @llvm.nvvm.fmax.xorsign.abs.f(float, float)
-declare float @llvm.nvvm.fmax.ftz.xorsign.abs.f(float, float)
-declare float @llvm.nvvm.fmax.nan.xorsign.abs.f(float, float)
-declare float @llvm.nvvm.fmax.ftz.nan.xorsign.abs.f(float, float)
-
; CHECK-LABEL: fmin_xorsign_abs_f16
define half @fmin_xorsign_abs_f16(half %0, half %1) {
; CHECK-NOT: call
@@ -100,35 +66,35 @@ define <2 x half> @fmin_ftz_nan_xorsign_abs_f16x2(<2 x half> %0, <2 x half> %1)
}
; CHECK-LABEL: fmin_xorsign_abs_bf16
-define i16 @fmin_xorsign_abs_bf16(i16 %0, i16 %1) {
+define bfloat @fmin_xorsign_abs_bf16(bfloat %0, bfloat %1) {
; CHECK-NOT: call
; CHECK: min.xorsign.abs.bf16
- %res = call i16 @llvm.nvvm.fmin.xorsign.abs.bf16(i16 %0, i16 %1)
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.fmin.xorsign.abs.bf16(bfloat %0, bfloat %1)
+ ret bfloat %res
}
; CHECK-LABEL: fmin_nan_xorsign_abs_bf16
-define i16 @fmin_nan_xorsign_abs_bf16(i16 %0, i16 %1) {
+define bfloat @fmin_nan_xorsign_abs_bf16(bfloat %0, bfloat %1) {
; CHECK-NOT: call
; CHECK: min.NaN.xorsign.abs.bf16
- %res = call i16 @llvm.nvvm.fmin.nan.xorsign.abs.bf16(i16 %0, i16 %1)
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.fmin.nan.xorsign.abs.bf16(bfloat %0, bfloat %1)
+ ret bfloat %res
}
; CHECK-LABEL: fmin_xorsign_abs_bf16x2
-define i32 @fmin_xorsign_abs_bf16x2(i32 %0, i32 %1) {
+define <2 x bfloat> @fmin_xorsign_abs_bf16x2(<2 x bfloat> %0, <2 x bfloat> %1) {
; CHECK-NOT: call
; CHECK: min.xorsign.abs.bf16x2
- %res = call i32 @llvm.nvvm.fmin.xorsign.abs.bf16x2(i32 %0, i32 %1)
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.fmin.xorsign.abs.bf16x2(<2 x bfloat> %0, <2 x bfloat> %1)
+ ret <2 x bfloat> %res
}
; CHECK-LABEL: fmin_nan_xorsign_abs_bf16x2
-define i32 @fmin_nan_xorsign_abs_bf16x2(i32 %0, i32 %1) {
+define <2 x bfloat> @fmin_nan_xorsign_abs_bf16x2(<2 x bfloat> %0, <2 x bfloat> %1) {
; CHECK-NOT: call
; CHECK: min.NaN.xorsign.abs.bf16x2
- %res = call i32 @llvm.nvvm.fmin.nan.xorsign.abs.bf16x2(i32 %0, i32 %1)
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.fmin.nan.xorsign.abs.bf16x2(<2 x bfloat> %0, <2 x bfloat> %1)
+ ret <2 x bfloat> %res
}
; CHECK-LABEL: fmin_xorsign_abs_f
@@ -228,35 +194,35 @@ define <2 x half> @fmax_ftz_nan_xorsign_abs_f16x2(<2 x half> %0, <2 x half> %1)
}
; CHECK-LABEL: fmax_xorsign_abs_bf16
-define i16 @fmax_xorsign_abs_bf16(i16 %0, i16 %1) {
+define bfloat @fmax_xorsign_abs_bf16(bfloat %0, bfloat %1) {
; CHECK-NOT: call
; CHECK: max.xorsign.abs.bf16
- %res = call i16 @llvm.nvvm.fmax.xorsign.abs.bf16(i16 %0, i16 %1)
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.fmax.xorsign.abs.bf16(bfloat %0, bfloat %1)
+ ret bfloat %res
}
; CHECK-LABEL: fmax_nan_xorsign_abs_bf16
-define i16 @fmax_nan_xorsign_abs_bf16(i16 %0, i16 %1) {
+define bfloat @fmax_nan_xorsign_abs_bf16(bfloat %0, bfloat %1) {
; CHECK-NOT: call
; CHECK: max.NaN.xorsign.abs.bf16
- %res = call i16 @llvm.nvvm.fmax.nan.xorsign.abs.bf16(i16 %0, i16 %1)
- ret i16 %res
+ %res = call bfloat @llvm.nvvm.fmax.nan.xorsign.abs.bf16(bfloat %0, bfloat %1)
+ ret bfloat %res
}
; CHECK-LABEL: fmax_xorsign_abs_bf16x2
-define i32 @fmax_xorsign_abs_bf16x2(i32 %0, i32 %1) {
+define <2 x bfloat> @fmax_xorsign_abs_bf16x2(<2 x bfloat> %0, <2 x bfloat> %1) {
; CHECK-NOT: call
; CHECK: max.xorsign.abs.bf16x2
- %res = call i32 @llvm.nvvm.fmax.xorsign.abs.bf16x2(i32 %0, i32 %1)
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.fmax.xorsign.abs.bf16x2(<2 x bfloat> %0, <2 x bfloat> %1)
+ ret <2 x bfloat> %res
}
; CHECK-LABEL: fmax_nan_xorsign_abs_bf16x2
-define i32 @fmax_nan_xorsign_abs_bf16x2(i32 %0, i32 %1) {
+define <2 x bfloat> @fmax_nan_xorsign_abs_bf16x2(<2 x bfloat> %0, <2 x bfloat> %1) {
; CHECK-NOT: call
; CHECK: max.NaN.xorsign.abs.bf16x2
- %res = call i32 @llvm.nvvm.fmax.nan.xorsign.abs.bf16x2(i32 %0, i32 %1)
- ret i32 %res
+ %res = call <2 x bfloat> @llvm.nvvm.fmax.nan.xorsign.abs.bf16x2(<2 x bfloat> %0, <2 x bfloat> %1)
+ ret <2 x bfloat> %res
}
; CHECK-LABEL: fmax_xorsign_abs_f
``````````
</details>
https://github.com/llvm/llvm-project/pull/101493
More information about the llvm-commits
mailing list