maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/CodeGen/fp16vec-ops.c

164 lines
8.3 KiB
C
Raw Normal View History

Promote storage-only __fp16 vector operands to float vectors. This commit fixes a bug in the handling of storage-only __fp16 vectors where clang didn't promote __fp16 vector operands to float vectors. Conceptually, it performs the following transformation on the AST in CreateBuiltinBinOp and CreateBuiltinUnaryOp: (Before) typedef __fp16 half4 __attribute__ ((vector_size (8))); typedef float float4 __attribute__ ((vector_size (16))); half4 hv0, hv1, hv2, hv3; hv0 = hv1 + hv2 + hv3; (After) float4 t0 = (float4)hv1 + (float4)hv2; float4 t1 = t0 + (float4)hv3; hv0 = (half4)t1; Note that this commit fixes the bug for targets that set HalfArgsAndReturns to true (ARM and ARM64). Targets using intrinsics such as llvm.convert.to.fp16 to handle __fp16 are still broken. rdar://problem/20625184 Differential Revision: https://reviews.llvm.org/D32520 llvm-svn: 314056
2017-09-23 13:02:02 +08:00
// REQUIRES: arm-registered-target
// RUN: %clang_cc1 -triple arm64-apple-ios9 -emit-llvm -o - -fallow-half-arguments-and-returns %s | FileCheck %s --check-prefix=CHECK
// RUN: %clang_cc1 -triple armv7-apple-ios9 -emit-llvm -o - -fallow-half-arguments-and-returns %s | FileCheck %s --check-prefix=CHECK
[CodeGen][X86] Fix handling of __fp16 vectors. This commit fixes a bug in IRGen where it generates completely broken code for __fp16 vectors on X86. For example when the following code is compiled: half4 hv0, hv1, hv2; // these are vectors of __fp16. void foo221() { hv0 = hv1 + hv2; } clang generates the following IR, in which two i16 vectors are added: @hv1 = common global <4 x i16> zeroinitializer, align 8 @hv2 = common global <4 x i16> zeroinitializer, align 8 @hv0 = common global <4 x i16> zeroinitializer, align 8 define void @foo221() { %0 = load <4 x i16>, <4 x i16>* @hv1, align 8 %1 = load <4 x i16>, <4 x i16>* @hv2, align 8 %add = add <4 x i16> %0, %1 store <4 x i16> %add, <4 x i16>* @hv0, align 8 ret void } To fix the bug, this commit uses the code committed in r314056, which modified clang to promote and truncate __fp16 vectors to and from float vectors in the AST. It also fixes another IRGen bug where a short value is assigned to an __fp16 variable without any integer-to-floating-point conversion, as shown in the following example: __fp16 a; short b; void foo1() { a = b; } @b = common global i16 0, align 2 @a = common global i16 0, align 2 define void @foo1() #0 { %0 = load i16, i16* @b, align 2 store i16 %0, i16* @a, align 2 ret void } rdar://problem/20625184 Differential Revision: https://reviews.llvm.org/D40112 llvm-svn: 320215
2017-12-09 08:02:37 +08:00
// RUN: %clang_cc1 -triple x86_64-apple-macos10.13 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK
Promote storage-only __fp16 vector operands to float vectors. This commit fixes a bug in the handling of storage-only __fp16 vectors where clang didn't promote __fp16 vector operands to float vectors. Conceptually, it performs the following transformation on the AST in CreateBuiltinBinOp and CreateBuiltinUnaryOp: (Before) typedef __fp16 half4 __attribute__ ((vector_size (8))); typedef float float4 __attribute__ ((vector_size (16))); half4 hv0, hv1, hv2, hv3; hv0 = hv1 + hv2 + hv3; (After) float4 t0 = (float4)hv1 + (float4)hv2; float4 t1 = t0 + (float4)hv3; hv0 = (half4)t1; Note that this commit fixes the bug for targets that set HalfArgsAndReturns to true (ARM and ARM64). Targets using intrinsics such as llvm.convert.to.fp16 to handle __fp16 are still broken. rdar://problem/20625184 Differential Revision: https://reviews.llvm.org/D32520 llvm-svn: 314056
2017-09-23 13:02:02 +08:00
typedef __fp16 half4 __attribute__ ((vector_size (8)));
typedef short short4 __attribute__ ((vector_size (8)));
half4 hv0, hv1;
short4 sv0;
// CHECK-LABEL: testFP16Vec0
// CHECK: %[[V0:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV:.*]] = fpext <4 x half> %[[V0]] to <4 x float>
// CHECK: %[[V1:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV1:.*]] = fpext <4 x half> %[[V1]] to <4 x float>
// CHECK: %[[ADD:.*]] = fadd <4 x float> %[[CONV]], %[[CONV1]]
// CHECK: %[[CONV2:.*]] = fptrunc <4 x float> %[[ADD]] to <4 x half>
// CHECK: store <4 x half> %[[CONV2]], <4 x half>* @hv0, align 8
// CHECK: %[[V2:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV3:.*]] = fpext <4 x half> %[[V2]] to <4 x float>
// CHECK: %[[V3:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV4:.*]] = fpext <4 x half> %[[V3]] to <4 x float>
// CHECK: %[[SUB:.*]] = fsub <4 x float> %[[CONV3]], %[[CONV4]]
// CHECK: %[[CONV5:.*]] = fptrunc <4 x float> %[[SUB]] to <4 x half>
// CHECK: store <4 x half> %[[CONV5]], <4 x half>* @hv0, align 8
// CHECK: %[[V4:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV6:.*]] = fpext <4 x half> %[[V4]] to <4 x float>
// CHECK: %[[V5:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV7:.*]] = fpext <4 x half> %[[V5]] to <4 x float>
// CHECK: %[[MUL:.*]] = fmul <4 x float> %[[CONV6]], %[[CONV7]]
// CHECK: %[[CONV8:.*]] = fptrunc <4 x float> %[[MUL]] to <4 x half>
// CHECK: store <4 x half> %[[CONV8]], <4 x half>* @hv0, align 8
// CHECK: %[[V6:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV9:.*]] = fpext <4 x half> %[[V6]] to <4 x float>
// CHECK: %[[V7:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV10:.*]] = fpext <4 x half> %[[V7]] to <4 x float>
// CHECK: %[[DIV:.*]] = fdiv <4 x float> %[[CONV9]], %[[CONV10]]
// CHECK: %[[CONV11:.*]] = fptrunc <4 x float> %[[DIV]] to <4 x half>
// CHECK: store <4 x half> %[[CONV11]], <4 x half>* @hv0, align 8
void testFP16Vec0() {
hv0 = hv0 + hv1;
hv0 = hv0 - hv1;
hv0 = hv0 * hv1;
hv0 = hv0 / hv1;
}
// CHECK-LABEL: testFP16Vec1
// CHECK: %[[V0:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV:.*]] = fpext <4 x half> %[[V0]] to <4 x float>
// CHECK: %[[V1:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV1:.*]] = fpext <4 x half> %[[V1]] to <4 x float>
// CHECK: %[[ADD:.*]] = fadd <4 x float> %[[CONV1]], %[[CONV]]
// CHECK: %[[CONV2:.*]] = fptrunc <4 x float> %[[ADD]] to <4 x half>
// CHECK: store <4 x half> %[[CONV2]], <4 x half>* @hv0, align 8
// CHECK: %[[V2:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV3:.*]] = fpext <4 x half> %[[V2]] to <4 x float>
// CHECK: %[[V3:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV4:.*]] = fpext <4 x half> %[[V3]] to <4 x float>
// CHECK: %[[SUB:.*]] = fsub <4 x float> %[[CONV4]], %[[CONV3]]
// CHECK: %[[CONV5:.*]] = fptrunc <4 x float> %[[SUB]] to <4 x half>
// CHECK: store <4 x half> %[[CONV5]], <4 x half>* @hv0, align 8
// CHECK: %[[V4:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV6:.*]] = fpext <4 x half> %[[V4]] to <4 x float>
// CHECK: %[[V5:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV7:.*]] = fpext <4 x half> %[[V5]] to <4 x float>
// CHECK: %[[MUL:.*]] = fmul <4 x float> %[[CONV7]], %[[CONV6]]
// CHECK: %[[CONV8:.*]] = fptrunc <4 x float> %[[MUL]] to <4 x half>
// CHECK: store <4 x half> %[[CONV8]], <4 x half>* @hv0, align 8
// CHECK: %[[V6:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV9:.*]] = fpext <4 x half> %[[V6]] to <4 x float>
// CHECK: %[[V7:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV10:.*]] = fpext <4 x half> %[[V7]] to <4 x float>
// CHECK: %[[DIV:.*]] = fdiv <4 x float> %[[CONV10]], %[[CONV9]]
// CHECK: %[[CONV11:.*]] = fptrunc <4 x float> %[[DIV]] to <4 x half>
// CHECK: store <4 x half> %[[CONV11]], <4 x half>* @hv0, align 8
void testFP16Vec1() {
hv0 += hv1;
hv0 -= hv1;
hv0 *= hv1;
hv0 /= hv1;
}
// CHECK-LABEL: testFP16Vec2
// CHECK: %[[CADDR:.*]] = alloca i32, align 4
// CHECK: store i32 %[[C:.*]], i32* %[[CADDR]], align 4
// CHECK: %[[V0:.*]] = load i32, i32* %[[CADDR]], align 4
// CHECK: %[[TOBOOL:.*]] = icmp ne i32 %[[V0]], 0
// CHECK: br i1 %[[TOBOOL]], label %{{.*}}, label %{{.*}}
//
// CHECK: %[[V1:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: br label %{{.*}}
//
// CHECK: %[[V2:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: br label %{{.*}}
//
// CHECK: %[[COND:.*]] = phi <4 x half> [ %[[V1]], %{{.*}} ], [ %[[V2]], %{{.*}} ]
// CHECK: store <4 x half> %[[COND]], <4 x half>* @hv0, align 8
void testFP16Vec2(int c) {
hv0 = c ? hv0 : hv1;
}
// CHECK-LABEL: testFP16Vec3
// CHECK: %[[V0:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV:.*]] = fpext <4 x half> %[[V0]] to <4 x float>
// CHECK: %[[V1:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV1:.*]] = fpext <4 x half> %[[V1]] to <4 x float>
// CHECK: %[[CMP:.*]] = fcmp oeq <4 x float> %[[CONV]], %[[CONV1]]
// CHECK: %[[SEXT:.*]] = sext <4 x i1> %[[CMP]] to <4 x i32>
// CHECK: %[[CONV2:.*]] = trunc <4 x i32> %[[SEXT]] to <4 x i16>
// CHECK: store <4 x i16> %[[CONV2]], <4 x i16>* @sv0, align 8
// CHECK: %[[V2:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV3:.*]] = fpext <4 x half> %[[V2]] to <4 x float>
// CHECK: %[[V3:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV4:.*]] = fpext <4 x half> %[[V3]] to <4 x float>
// CHECK: %[[CMP5:.*]] = fcmp une <4 x float> %[[CONV3]], %[[CONV4]]
// CHECK: %[[SEXT6:.*]] = sext <4 x i1> %[[CMP5]] to <4 x i32>
// CHECK: %[[CONV7:.*]] = trunc <4 x i32> %[[SEXT6]] to <4 x i16>
// CHECK: store <4 x i16> %[[CONV7]], <4 x i16>* @sv0, align 8
// CHECK: %[[V4:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV8:.*]] = fpext <4 x half> %[[V4]] to <4 x float>
// CHECK: %[[V5:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV9:.*]] = fpext <4 x half> %[[V5]] to <4 x float>
// CHECK: %[[CMP10:.*]] = fcmp olt <4 x float> %[[CONV8]], %[[CONV9]]
// CHECK: %[[SEXT11:.*]] = sext <4 x i1> %[[CMP10]] to <4 x i32>
// CHECK: %[[CONV12:.*]] = trunc <4 x i32> %[[SEXT11]] to <4 x i16>
// CHECK: store <4 x i16> %[[CONV12]], <4 x i16>* @sv0, align 8
// CHECK: %[[V6:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV13:.*]] = fpext <4 x half> %[[V6]] to <4 x float>
// CHECK: %[[V7:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV14:.*]] = fpext <4 x half> %[[V7]] to <4 x float>
// CHECK: %[[CMP15:.*]] = fcmp ogt <4 x float> %[[CONV13]], %[[CONV14]]
// CHECK: %[[SEXT16:.*]] = sext <4 x i1> %[[CMP15]] to <4 x i32>
// CHECK: %[[CONV17:.*]] = trunc <4 x i32> %[[SEXT16]] to <4 x i16>
// CHECK: store <4 x i16> %[[CONV17]], <4 x i16>* @sv0, align 8
// CHECK: %[[V8:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV18:.*]] = fpext <4 x half> %[[V8]] to <4 x float>
// CHECK: %[[V9:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV19:.*]] = fpext <4 x half> %[[V9]] to <4 x float>
// CHECK: %[[CMP20:.*]] = fcmp ole <4 x float> %[[CONV18]], %[[CONV19]]
// CHECK: %[[SEXT21:.*]] = sext <4 x i1> %[[CMP20]] to <4 x i32>
// CHECK: %[[CONV22:.*]] = trunc <4 x i32> %[[SEXT21]] to <4 x i16>
// CHECK: store <4 x i16> %[[CONV22]], <4 x i16>* @sv0, align 8
// CHECK: %[[V10:.*]] = load <4 x half>, <4 x half>* @hv0, align 8
// CHECK: %[[CONV23:.*]] = fpext <4 x half> %[[V10]] to <4 x float>
// CHECK: %[[V11:.*]] = load <4 x half>, <4 x half>* @hv1, align 8
// CHECK: %[[CONV24:.*]] = fpext <4 x half> %[[V11]] to <4 x float>
// CHECK: %[[CMP25:.*]] = fcmp oge <4 x float> %[[CONV23]], %[[CONV24]]
// CHECK: %[[SEXT26:.*]] = sext <4 x i1> %[[CMP25]] to <4 x i32>
// CHECK: %[[CONV27:.*]] = trunc <4 x i32> %[[SEXT26]] to <4 x i16>
// CHECK: store <4 x i16> %[[CONV27]], <4 x i16>* @sv0, align 8
void testFP16Vec3() {
sv0 = hv0 == hv1;
sv0 = hv0 != hv1;
sv0 = hv0 < hv1;
sv0 = hv0 > hv1;
sv0 = hv0 <= hv1;
sv0 = hv0 >= hv1;
}