[llvm] [RISCV] Fix vp-intrinsics args in cost model tests. NFC (PR #112463)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Oct 15 19:50:45 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-analysis
Author: Elvis Wang (ElvisWang123)
<details>
<summary>Changes</summary>
This patch contains following changes to fix vp intrinsics tests.
1. v\*float -> v\*f32, v\*double -> v\*f64 and v\*half -> v\*f16
2. llvm.vp.s{u}itofp.v\*\i*.v\*f\* -> llvm.vp.s{u}itofp.v\*f\*.i\*
3. llvm.vp.fptos{u}i.v\*f\*.v\*i\* -> llvm.vp.fptos{u}i.v\*i\*.v\*f\*
---
Patch is 201.38 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/112463.diff
2 Files Affected:
- (modified) llvm/test/Analysis/CostModel/RISCV/cast.ll (+644-644)
- (modified) llvm/test/Analysis/CostModel/RISCV/cmp.ll (+32-32)
``````````diff
diff --git a/llvm/test/Analysis/CostModel/RISCV/cast.ll b/llvm/test/Analysis/CostModel/RISCV/cast.ll
index 853eef6bcb2e87..44367c7031500b 100644
--- a/llvm/test/Analysis/CostModel/RISCV/cast.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/cast.ll
@@ -3071,113 +3071,113 @@ define void @fpext() {
%v2f16_v2f64 = fpext <2 x half> undef to <2 x double>
%v2f32_v2f64 = fpext <2 x float> undef to <2 x double>
- %vp_v2f16_v2f32 = call <2 x float> @llvm.vp.fpext.v2half.v2float(<2 x half> undef, <2 x i1> undef, i32 undef)
- %vp_v2f16_v2f64 = call <2 x double> @llvm.vp.fpext.v2half.v2double(<2 x half> undef, <2 x i1> undef, i32 undef)
- %vp_v2f32_v2f64 = call <2 x double> @llvm.vp.fpext.v2float.v2double(<2 x float> undef, <2 x i1> undef, i32 undef)
+ %vp_v2f16_v2f32 = call <2 x float> @llvm.vp.fpext.v2f16.v2f32(<2 x half> undef, <2 x i1> undef, i32 undef)
+ %vp_v2f16_v2f64 = call <2 x double> @llvm.vp.fpext.v2f16.v2f64(<2 x half> undef, <2 x i1> undef, i32 undef)
+ %vp_v2f32_v2f64 = call <2 x double> @llvm.vp.fpext.v2f32.v2f64(<2 x float> undef, <2 x i1> undef, i32 undef)
%v4f16_v4f32 = fpext <4 x half> undef to <4 x float>
%v4f16_v4f64 = fpext <4 x half> undef to <4 x double>
%v4f32_v4f64 = fpext <4 x float> undef to <4 x double>
- %vp_v4f16_v4f32 = call <4 x float> @llvm.vp.fpext.v4half.v4float(<4 x half> undef, <4 x i1> undef, i32 undef)
- %vp_v4f16_v4f64 = call <4 x double> @llvm.vp.fpext.v4half.v4double(<4 x half> undef, <4 x i1> undef, i32 undef)
- %vp_v4f32_v4f64 = call <4 x double> @llvm.vp.fpext.v4float.v4double(<4 x float> undef, <4 x i1> undef, i32 undef)
+ %vp_v4f16_v4f32 = call <4 x float> @llvm.vp.fpext.v4f16.v4f32(<4 x half> undef, <4 x i1> undef, i32 undef)
+ %vp_v4f16_v4f64 = call <4 x double> @llvm.vp.fpext.v4f16.v4f64(<4 x half> undef, <4 x i1> undef, i32 undef)
+ %vp_v4f32_v4f64 = call <4 x double> @llvm.vp.fpext.v4f32.v4f64(<4 x float> undef, <4 x i1> undef, i32 undef)
%v8f16_v8f32 = fpext <8 x half> undef to <8 x float>
%v8f16_v8f64 = fpext <8 x half> undef to <8 x double>
%v8f32_v8f64 = fpext <8 x float> undef to <8 x double>
- %vp_v8f16_v8f32 = call <8 x float> @llvm.vp.fpext.v8half.v8float(<8 x half> undef, <8 x i1> undef, i32 undef)
- %vp_v8f16_v8f64 = call <8 x double> @llvm.vp.fpext.v8half.v8double(<8 x half> undef, <8 x i1> undef, i32 undef)
- %vp_v8f32_v8f64 = call <8 x double> @llvm.vp.fpext.v8float.v8double(<8 x float> undef, <8 x i1> undef, i32 undef)
+ %vp_v8f16_v8f32 = call <8 x float> @llvm.vp.fpext.v8f16.v8f32(<8 x half> undef, <8 x i1> undef, i32 undef)
+ %vp_v8f16_v8f64 = call <8 x double> @llvm.vp.fpext.v8f16.v8f64(<8 x half> undef, <8 x i1> undef, i32 undef)
+ %vp_v8f32_v8f64 = call <8 x double> @llvm.vp.fpext.v8f32.v8f64(<8 x float> undef, <8 x i1> undef, i32 undef)
%v16f16_v16f32 = fpext <16 x half> undef to <16 x float>
%v16f16_v16f64 = fpext <16 x half> undef to <16 x double>
%v16f32_v16f64 = fpext <16 x float> undef to <16 x double>
- %vp_v16f16_v16f32 = call <16 x float> @llvm.vp.fpext.v16half.v16float(<16 x half> undef, <16 x i1> undef, i32 undef)
- %vp_v16f16_v16f64 = call <16 x double> @llvm.vp.fpext.v16half.v16double(<16 x half> undef, <16 x i1> undef, i32 undef)
- %vp_v16f32_v16f64 = call <16 x double> @llvm.vp.fpext.v16float.v16double(<16 x float> undef, <16 x i1> undef, i32 undef)
+ %vp_v16f16_v16f32 = call <16 x float> @llvm.vp.fpext.v16f16.v16f32(<16 x half> undef, <16 x i1> undef, i32 undef)
+ %vp_v16f16_v16f64 = call <16 x double> @llvm.vp.fpext.v16f16.v16f64(<16 x half> undef, <16 x i1> undef, i32 undef)
+ %vp_v16f32_v16f64 = call <16 x double> @llvm.vp.fpext.v16f32.v16f64(<16 x float> undef, <16 x i1> undef, i32 undef)
%v32f16_v32f32 = fpext <32 x half> undef to <32 x float>
%v32f16_v32f64 = fpext <32 x half> undef to <32 x double>
%v32f32_v32f64 = fpext <32 x float> undef to <32 x double>
- %vp_v32f16_v32f32 = call <32 x float> @llvm.vp.fpext.v32half.v32float(<32 x half> undef, <32 x i1> undef, i32 undef)
- %vp_v32f16_v32f64 = call <32 x double> @llvm.vp.fpext.v32half.v32double(<32 x half> undef, <32 x i1> undef, i32 undef)
- %vp_v32f32_v32f64 = call <32 x double> @llvm.vp.fpext.v32float.v32double(<32 x float> undef, <32 x i1> undef, i32 undef)
+ %vp_v32f16_v32f32 = call <32 x float> @llvm.vp.fpext.v32f16.v32f32(<32 x half> undef, <32 x i1> undef, i32 undef)
+ %vp_v32f16_v32f64 = call <32 x double> @llvm.vp.fpext.v32f16.v32f64(<32 x half> undef, <32 x i1> undef, i32 undef)
+ %vp_v32f32_v32f64 = call <32 x double> @llvm.vp.fpext.v32f32.v32f64(<32 x float> undef, <32 x i1> undef, i32 undef)
%v64f16_v64f32 = fpext <64 x half> undef to <64 x float>
%v64f16_v64f64 = fpext <64 x half> undef to <64 x double>
%v64f32_v64f64 = fpext <64 x float> undef to <64 x double>
- %vp_v64f16_v64f32 = call <64 x float> @llvm.vp.fpext.v64half.v64float(<64 x half> undef, <64 x i1> undef, i32 undef)
- %vp_v64f16_v64f64 = call <64 x double> @llvm.vp.fpext.v64half.v64double(<64 x half> undef, <64 x i1> undef, i32 undef)
- %vp_v64f32_v64f64 = call <64 x double> @llvm.vp.fpext.v64float.v64double(<64 x float> undef, <64 x i1> undef, i32 undef)
+ %vp_v64f16_v64f32 = call <64 x float> @llvm.vp.fpext.v64f16.v64f32(<64 x half> undef, <64 x i1> undef, i32 undef)
+ %vp_v64f16_v64f64 = call <64 x double> @llvm.vp.fpext.v64f16.v64f64(<64 x half> undef, <64 x i1> undef, i32 undef)
+ %vp_v64f32_v64f64 = call <64 x double> @llvm.vp.fpext.v64f32.v64f64(<64 x float> undef, <64 x i1> undef, i32 undef)
%v128f16_v128f32 = fpext <128 x half> undef to <128 x float>
%v128f16_v128f64 = fpext <128 x half> undef to <128 x double>
%v128f32_v128f64 = fpext <128 x float> undef to <128 x double>
- %vp_v128f16_v128f32 = call <128 x float> @llvm.vp.fpext.v128half.v128float(<128 x half> undef, <128 x i1> undef, i32 undef)
- %vp_v128f16_v128f64 = call <128 x double> @llvm.vp.fpext.v128half.v128double(<128 x half> undef, <128 x i1> undef, i32 undef)
- %vp_v128f32_v128f64 = call <128 x double> @llvm.vp.fpext.v128float.v128double(<128 x float> undef, <128 x i1> undef, i32 undef)
+ %vp_v128f16_v128f32 = call <128 x float> @llvm.vp.fpext.v128f16.v128f32(<128 x half> undef, <128 x i1> undef, i32 undef)
+ %vp_v128f16_v128f64 = call <128 x double> @llvm.vp.fpext.v128f16.v128f64(<128 x half> undef, <128 x i1> undef, i32 undef)
+ %vp_v128f32_v128f64 = call <128 x double> @llvm.vp.fpext.v128f32.v128f64(<128 x float> undef, <128 x i1> undef, i32 undef)
%nxv1f16_nxv1f32 = fpext <vscale x 1 x half> undef to <vscale x 1 x float>
%nxv1f16_nxv1f64 = fpext <vscale x 1 x half> undef to <vscale x 1 x double>
%nxv1f32_nxv1f64 = fpext <vscale x 1 x float> undef to <vscale x 1 x double>
- %vp_nxv1f16_nxv1f32 = call <vscale x 1 x float> @llvm.vp.fpext.nxv1half.nxv1float(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
- %vp_nxv1f16_nxv1f64 = call <vscale x 1 x double> @llvm.vp.fpext.nxv1half.nxv1double(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
- %vp_nxv1f32_nxv1f64 = call <vscale x 1 x double> @llvm.vp.fpext.nxv1float.nxv1double(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
+ %vp_nxv1f16_nxv1f32 = call <vscale x 1 x float> @llvm.vp.fpext.nxv1f16.nxv1f32(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
+ %vp_nxv1f16_nxv1f64 = call <vscale x 1 x double> @llvm.vp.fpext.nxv1f16.nxv1f64(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
+ %vp_nxv1f32_nxv1f64 = call <vscale x 1 x double> @llvm.vp.fpext.nxv1f32.nxv1f64(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
%nxv2f16_nxv2f32 = fpext <vscale x 2 x half> undef to <vscale x 2 x float>
%nxv2f16_nxv2f64 = fpext <vscale x 2 x half> undef to <vscale x 2 x double>
%nxv2f32_nxv2f64 = fpext <vscale x 2 x float> undef to <vscale x 2 x double>
- %vp_nxv2f16_nxv2f32 = call <vscale x 2 x float> @llvm.vp.fpext.nxv2half.nxv2float(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
- %vp_nxv2f16_nxv2f64 = call <vscale x 2 x double> @llvm.vp.fpext.nxv2half.nxv2double(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
- %vp_nxv2f32_nxv2f64 = call <vscale x 2 x double> @llvm.vp.fpext.nxv2float.nxv2double(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
+ %vp_nxv2f16_nxv2f32 = call <vscale x 2 x float> @llvm.vp.fpext.nxv2f16.nxv2f32(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
+ %vp_nxv2f16_nxv2f64 = call <vscale x 2 x double> @llvm.vp.fpext.nxv2f16.nxv2f64(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
+ %vp_nxv2f32_nxv2f64 = call <vscale x 2 x double> @llvm.vp.fpext.nxv2f32.nxv2f64(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
%nxv4f16_nxv4f32 = fpext <vscale x 4 x half> undef to <vscale x 4 x float>
%nxv4f16_nxv4f64 = fpext <vscale x 4 x half> undef to <vscale x 4 x double>
%nxv4f32_nxv4f64 = fpext <vscale x 4 x float> undef to <vscale x 4 x double>
- %vp_nxv4f16_nxv4f32 = call <vscale x 4 x float> @llvm.vp.fpext.nxv4half.nxv4float(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
- %vp_nxv4f16_nxv4f64 = call <vscale x 4 x double> @llvm.vp.fpext.nxv4half.nxv4double(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
- %vp_nxv4f32_nxv4f64 = call <vscale x 4 x double> @llvm.vp.fpext.nxv4float.nxv4double(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+ %vp_nxv4f16_nxv4f32 = call <vscale x 4 x float> @llvm.vp.fpext.nxv4f16.nxv4f32(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
+ %vp_nxv4f16_nxv4f64 = call <vscale x 4 x double> @llvm.vp.fpext.nxv4f16.nxv4f64(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
+ %vp_nxv4f32_nxv4f64 = call <vscale x 4 x double> @llvm.vp.fpext.nxv4f32.nxv4f64(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
%nxv8f16_nxv8f32 = fpext <vscale x 8 x half> undef to <vscale x 8 x float>
%nxv8f16_nxv8f64 = fpext <vscale x 8 x half> undef to <vscale x 8 x double>
%nxv8f32_nxv8f64 = fpext <vscale x 8 x float> undef to <vscale x 8 x double>
- %vp_nxv8f16_nxv8f32 = call <vscale x 8 x float> @llvm.vp.fpext.nxv8half.nxv8float(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
- %vp_nxv8f16_nxv8f64 = call <vscale x 8 x double> @llvm.vp.fpext.nxv8half.nxv8double(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
- %vp_nxv8f32_nxv8f64 = call <vscale x 8 x double> @llvm.vp.fpext.nxv8float.nxv8double(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+ %vp_nxv8f16_nxv8f32 = call <vscale x 8 x float> @llvm.vp.fpext.nxv8f16.nxv8f32(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
+ %vp_nxv8f16_nxv8f64 = call <vscale x 8 x double> @llvm.vp.fpext.nxv8f16.nxv8f64(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
+ %vp_nxv8f32_nxv8f64 = call <vscale x 8 x double> @llvm.vp.fpext.nxv8f32.nxv8f64(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
%nxv16f16_nxv16f32 = fpext <vscale x 16 x half> undef to <vscale x 16 x float>
%nxv16f16_nxv16f64 = fpext <vscale x 16 x half> undef to <vscale x 16 x double>
%nxv16f32_nxv16f64 = fpext <vscale x 16 x float> undef to <vscale x 16 x double>
- %vp_nxv16f16_nxv16f32 = call <vscale x 16 x float> @llvm.vp.fpext.nxv16half.nxv16float(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
- %vp_nxv16f16_nxv16f64 = call <vscale x 16 x double> @llvm.vp.fpext.nxv16half.nxv16double(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
- %vp_nxv16f32_nxv16f64 = call <vscale x 16 x double> @llvm.vp.fpext.nxv16float.nxv16double(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+ %vp_nxv16f16_nxv16f32 = call <vscale x 16 x float> @llvm.vp.fpext.nxv16f16.nxv16f32(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+ %vp_nxv16f16_nxv16f64 = call <vscale x 16 x double> @llvm.vp.fpext.nxv16f16.nxv16f64(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+ %vp_nxv16f32_nxv16f64 = call <vscale x 16 x double> @llvm.vp.fpext.nxv16f32.nxv16f64(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
%nxv32f16_nxv32f32 = fpext <vscale x 32 x half> undef to <vscale x 32 x float>
%nxv32f16_nxv32f64 = fpext <vscale x 32 x half> undef to <vscale x 32 x double>
%nxv32f32_nxv32f64 = fpext <vscale x 32 x float> undef to <vscale x 32 x double>
- %vp_nxv32f16_nxv32f32 = call <vscale x 32 x float> @llvm.vp.fpext.nxv32half.nxv32float(<vscale x 32 x half> undef, <vscale x 32 x i1> undef, i32 undef)
- %vp_nxv32f16_nxv32f64 = call <vscale x 32 x double> @llvm.vp.fpext.nxv32half.nxv32double(<vscale x 32 x half> undef, <vscale x 32 x i1> undef, i32 undef)
- %vp_nxv32f32_nxv32f64 = call <vscale x 32 x double> @llvm.vp.fpext.nxv32float.nxv32double(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
+ %vp_nxv32f16_nxv32f32 = call <vscale x 32 x float> @llvm.vp.fpext.nxv32f16.nxv32f32(<vscale x 32 x half> undef, <vscale x 32 x i1> undef, i32 undef)
+ %vp_nxv32f16_nxv32f64 = call <vscale x 32 x double> @llvm.vp.fpext.nxv32f16.nxv32f64(<vscale x 32 x half> undef, <vscale x 32 x i1> undef, i32 undef)
+ %vp_nxv32f32_nxv32f64 = call <vscale x 32 x double> @llvm.vp.fpext.nxv32f32.nxv32f64(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
%nxv64f16_nxv64f32 = fpext <vscale x 64 x half> undef to <vscale x 64 x float>
%nxv64f16_nxv64f64 = fpext <vscale x 64 x half> undef to <vscale x 64 x double>
%nxv64f32_nxv64f64 = fpext <vscale x 64 x float> undef to <vscale x 64 x double>
- %vp_nxv64f16_nxv64f32 = call <vscale x 64 x float> @llvm.vp.fpext.nxv64half.nxv64float(<vscale x 64 x half> undef, <vscale x 64 x i1> undef, i32 undef)
- %vp_nxv64f16_nxv64f64 = call <vscale x 64 x double> @llvm.vp.fpext.nxv64half.nxv64double(<vscale x 64 x half> undef, <vscale x 64 x i1> undef, i32 undef)
- %vp_nxv64f32_nxv64f64 = call <vscale x 64 x double> @llvm.vp.fpext.nxv64float.nxv64double(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
+ %vp_nxv64f16_nxv64f32 = call <vscale x 64 x float> @llvm.vp.fpext.nxv64f16.nxv64f32(<vscale x 64 x half> undef, <vscale x 64 x i1> undef, i32 undef)
+ %vp_nxv64f16_nxv64f64 = call <vscale x 64 x double> @llvm.vp.fpext.nxv64f16.nxv64f64(<vscale x 64 x half> undef, <vscale x 64 x i1> undef, i32 undef)
+ %vp_nxv64f32_nxv64f64 = call <vscale x 64 x double> @llvm.vp.fpext.nxv64f32.nxv64f64(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
ret void
}
@@ -3274,113 +3274,113 @@ define void @fptrunc() {
%v2f64_v2f16 = fptrunc <2 x double> undef to <2 x half>
%v2f64_v2f32 = fptrunc <2 x double> undef to <2 x float>
- %vp_v2f32_v2f16 = call <2 x half> @llvm.vp.fptrunc.v2float.v2half(<2 x float> undef, <2 x i1> undef, i32 undef)
- %vp_v2f64_v2f16 = call <2 x half> @llvm.vp.fptrunc.v2double.v2half(<2 x double> undef, <2 x i1> undef, i32 undef)
- %vp_v2f64_v2f32 = call <2 x float> @llvm.vp.fptrunc.v2double.v2float(<2 x double> undef, <2 x i1> undef, i32 undef)
+ %vp_v2f32_v2f16 = call <2 x half> @llvm.vp.fptrunc.v2f32.v2f16(<2 x float> undef, <2 x i1> undef, i32 undef)
+ %vp_v2f64_v2f16 = call <2 x half> @llvm.vp.fptrunc.v2f64.v2f16(<2 x double> undef, <2 x i1> undef, i32 undef)
+ %vp_v2f64_v2f32 = call <2 x float> @llvm.vp.fptrunc.v2f64.v2f32(<2 x double> undef, <2 x i1> undef, i32 undef)
%v4f32_v4f16 = fptrunc <4 x float> undef to <4 x half>
%v4f64_v4f16 = fptrunc <4 x double> undef to <4 x half>
%v4f64_v4f32 = fptrunc <4 x double> undef to <4 x float>
- %vp_v4f32_v4f16 = call <4 x half> @llvm.vp.fptrunc.v4float.v4half(<4 x float> undef, <4 x i1> undef, i32 undef)
- %vp_v4f64_v4f16 = call <4 x half> @llvm.vp.fptrunc.v4double.v4half(<4 x double> undef, <4 x i1> undef, i32 undef)
- %vp_v4f64_v4f32 = call <4 x float> @llvm.vp.fptrunc.v4double.v4float(<4 x double> undef, <4 x i1> undef, i32 undef)
+ %vp_v4f32_v4f16 = call <4 x half> @llvm.vp.fptrunc.v4f32.v4f16(<4 x float> undef, <4 x i1> undef, i32 undef)
+ %vp_v4f64_v4f16 = call <4 x half> @llvm.vp.fptrunc.v4f64.v4f16(<4 x double> undef, <4 x i1> undef, i32 undef)
+ %vp_v4f64_v4f32 = call <4 x float> @llvm.vp.fptrunc.v4f64.v4f32(<4 x double> undef, <4 x i1> undef, i32 undef)
%v8f32_v8f16 = fptrunc <8 x float> undef to <8 x half>
%v8f64_v8f16 = fptrunc <8 x double> undef to <8 x half>
%v8f64_v8f32 = fptrunc <8 x double> undef to <8 x float>
- %vp_v8f32_v8f16 = call <8 x half> @llvm.vp.fptrunc.v8float.v8half(<8 x float> undef, <8 x i1> undef, i32 undef)
- %vp_v8f64_v8f16 = call <8 x half> @llvm.vp.fptrunc.v8double.v8half(<8 x double> undef, <8 x i1> undef, i32 undef)
- %vp_v8f64_v8f32 = call <8 x float> @llvm.vp.fptrunc.v8double.v8float(<8 x double> undef, <8 x i1> undef, i32 undef)
+ %vp_v8f32_v8f16 = call <8 x half> @llvm.vp.fptrunc.v8f32.v8f16(<8 x float> undef, <8 x i1> undef, i32 undef)
+ %vp_v8f64_v8f16 = call <8 x half> @llvm.vp.fptrunc.v8f64.v8f16(<8 x double> undef, <8 x i1> undef, i32 undef)
+ %vp_v8f64_v8f32 = call <8 x float> @llvm.vp.fptrunc.v8f64.v8f32(<8 x double> undef, <8 x i1> undef, i32 undef)
%v16f32_v16f16 = fptrunc <16 x float> undef to <16 x half>
%v16f64_v16f16 = fptrunc <16 x double> undef to <16 x half>
%v16f64_v16f32 = fptrunc <16 x double> undef to <16 x float>
- %vp_v16f32_v16f16 = call <16 x half> @llvm.vp.fptrunc.v16float.v16half(<16 x float> undef, <16 x i1> undef, i32 undef)
- %vp_v16f64_v16f16 = call <16 x half> @llvm.vp.fptrunc.v16double.v16half(<16 x double> undef, <16 x i1> undef, i32 undef)
- %vp_v16f64_v16f32 = call <16 x float> @llvm.vp.fptrunc.v16double.v16float(<16 x double> undef, <16 x i1> undef, i32 undef)
+ %vp_v16f32_v16f16 = call <16 x half> @llvm.vp.fptrunc.v16f32.v16f16(<16 x float> undef, <16 x i1> undef, i32 undef)
+ %vp_v16f64_v16f16 = call <16 x half> @llvm.vp.fptrunc.v16f64.v16f16(<16 x double> undef, <16 x i1> undef, i32 undef)
+ %vp_v16f64_v16f32 = call <16 x float> @llvm.vp.fptrunc.v16f64.v16f32(<16 x double> undef, <16 x i1> undef, i32 undef)
%v32f32_v32f16 = fptrunc <32 x float> undef to <32 x half>
%v32f64_v32f16 = fptrunc <32 x double> undef to <32 x half>
%v32f64_v32f32 = fptrunc <32 x double> undef to <32 x float>
- %vp_v32f32_v32f16 = call <32 x half> @llvm.vp.fptrunc.v32float.v32half(<32 x float> undef, <32 x i1> undef, i32 undef)
- %vp_v32f64_v32f16 = call <32 x half> @llvm.vp.fptrunc.v32double.v32half(<32 x double> undef, <32 x i1> undef, i32 undef)
- %vp_v32f64_v32f32 = call <32 x float> @llvm.vp.fptrunc.v32double.v32float(<32 x double> undef, <32 x i1> undef, i32 undef)
+ %vp_v32f32_v32f16 = call <32 x half> @llvm.vp.fptrunc.v32f32.v32f16(<32 x float> undef, <32 x i1> undef, i32 undef)
+ %vp_v32f64_v32f16 = call <32 x half> @llvm.vp.fptrunc.v32f64.v32f16(<32 x double> undef, <32 x i1> undef, i32 undef)
+ %vp_v32f64_v32f32 = call <32 x float> @llvm.vp.fptrunc.v32f64.v32f32(<32 x double> undef, <32 x i1> undef, i32 undef)
%v64f32_v64f16 = fptrunc <64 x float> undef to <64 x half>
%v64f64_v64f16 = fptrunc <64 x double> undef to <64 x half>
%v64f64_v64f32 = fptrunc <64 x double> undef to <64 x float>
- %vp_v64f32_v64f16 = call <64 x half> @llvm.vp.fptrunc.v64float.v64half(<64 x float> undef, <64 x i1> undef, i32 undef)
- %vp_v64f64_v64f16 = call <64 x half> @llvm.vp.fptrunc.v64double.v64half(<64 x double> undef, <64 x i1> undef, i32 undef)
- %vp_v64f64_v64f32 = call <64 x float> @llvm.vp.fptrunc.v64double.v64float(<64 x double> undef, <64 x i1> undef, i32 undef)
+ %vp_v64f32_v64f16 = call <64 x half> @llvm.vp.fptrunc.v64f32.v64f16(<64 x float> undef, <64 x i1> undef, i32 undef)
+ %vp_v64f64_v64f16 = call <64 x half> @llvm.vp.fptrunc.v64f64.v64f16(<64 x double> undef, <64 x i1> undef, i32 undef)
+ %vp_v64f64_v64f32 = call <64 x float> @llvm.vp.fptrunc.v64f64.v64f32(<64 x double> undef, <64 x i1> undef, i32 undef)
%v128f32_v128f16 = fptrunc <128 x float> undef to <128 x half>
%v128f64_v128f16 = fptrunc <128 x double> undef to <128 x half>
%v128f64_v128f32 = fptrunc <128 x double> undef to <128 x float>
- %vp_v128f32_v128f16 = call <128 x half> @llvm.vp.fptrunc.v128float.v128half(<128 x float> undef, <128 x i1> undef, i32 undef)
- %vp_v128f64_v128f16 = call <128 x half> @llvm.vp.fptrunc.v128double.v128half(<128 x double> undef, <128 x i1> undef, i32 undef)
- %vp_v128f64_v128f32 = call <128 x float> @llvm.vp.fptrunc.v128double.v128flo...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/112463
More information about the llvm-commits
mailing list